Emboss is an MCP server published by io.github.edwinorange, hosted at api.getemboss.ai. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 28 tools, including list_forms, get_form, find_form, get_usage, create_form.
Make any PDF form fillable, fill it from data or documents, read it back, and fax the result.
7 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Forms in the user's Emboss library. state: ready (default), processing, failed, or all. Paginate with cursor.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| state | string | |
| cursor | any |
{
"name": "list_forms",
"title": "List your forms",
"description": "Forms in the user's Emboss library. state: ready (default), processing, failed, or all. Paginate with cursor.",
"inputSchema": {
"type": "object",
"title": "list_formsArguments",
"examples": [
{
"limit": 20,
"state": "ready"
}
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 20
},
"state": {
"type": "string",
"title": "State",
"default": "ready"
},
"cursor": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Cursor",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "list_formsDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "List your forms",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Status of one form. When ready, returns every field (id, label, kind, options, required) and a download link for the fillable PDF.
| Parameter | Type | Description |
|---|---|---|
| form_id * | string |
{
"name": "get_form",
"title": "Get a form and its fields",
"description": "Status of one form. When ready, returns every field (id, label, kind, options, required) and a download link for the fillable PDF.",
"inputSchema": {
"type": "object",
"title": "get_formArguments",
"examples": [
{
"form_id": "11111111-2222-3333-4444-555555555555"
}
],
"required": [
"form_id"
],
"properties": {
"form_id": {
"type": "string",
"title": "Form Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_formDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Get a form and its fields",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Find a blank government form in the Emboss library by name or number, ready to fill. Search the Emboss library of blank government forms by name, number, alias or place (w9, W-9, form w 9 and taxpayer identification all find the same form). When a form belongs to a state or country, say so in the query or pass region or country. Leave query empty and pass region, country or category to list every form that fits. Returns each match's slug, title, agency, number, place, category, edition and page count, plus a note when the library holds a different year than the one asked for or needs to know the state. Send the whole query once, and do not search as the user types: each search spends one of the account's rate-limit slots. Up to 20 matches come back at a time (limit sets up to 50); when next_cursor is set, pass it as cursor for the next ones. Pass a slug as create_form's library argument to start from that form. Free.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| query * | string | |
| cursor | any | |
| region | any | |
| country | any | |
| category | any |
{
"name": "find_form",
"title": "Find a blank government form",
"description": "Find a blank government form in the Emboss library by name or number, ready to fill. Search the Emboss library of blank government forms by name, number, alias or place (w9, W-9, form w 9 and taxpayer identification all find the same form). When a form belongs to a state or country, say so in the query or pass region or country. Leave query empty and pass region, country or category to list every form that fits. Returns each match's slug, title, agency, number, place, category, edition and page count, plus a note when the library holds a different year than the one asked for or needs to know the state. Send the whole query once, and do not search as the user types: each search spends one of the account's rate-limit slots. Up to 20 matches come back at a time (limit sets up to 50); when next_cursor is set, pass it as cursor for the next ones. Pass a slug as create_form's library argument to start from that form. Free.",
"inputSchema": {
"type": "object",
"title": "find_formArguments",
"examples": [
{
"query": "IRS Form W-9 request for taxpayer identification number"
}
],
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 20
},
"query": {
"type": "string",
"title": "Query"
},
"cursor": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Cursor",
"default": null
},
"region": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Region",
"default": null
},
"country": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Country",
"default": null
},
"category": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Category",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "find_formDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Find a blank government form",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}This month's usage and how many free operations remain, plus the billing page link. It also says whether a payment method is on file (payment_method_on_file) and whether the account can send a fax today (fax_ready). Faxes need a payment method: check fax_ready before send_fax.
No parameters.
{
"name": "get_usage",
"title": "Check free tier and usage",
"description": "This month's usage and how many free operations remain, plus the billing page link. It also says whether a payment method is on file (payment_method_on_file) and whether the account can send a fax today (fax_ready). Faxes need a payment method: check fax_ready before send_fax.",
"inputSchema": {
"type": "object",
"title": "get_usageArguments",
"examples": [
{}
],
"properties": {}
},
"outputSchema": {
"type": "object",
"title": "get_usageDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Check free tier and usage",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Turn a flat or scanned PDF form into a fillable PDF with detected fields. Upload a PDF (pdf_url: public https link, or pdf_base64) and detect its fields. Returns when detection finishes (usually under two minutes). Give library=<slug> from find_form to start from a form Emboss already keeps. Billed as one form creation; the first 5 each month are free. Optional retention: ephemeral or account_default (default: the account's own setting). Ephemeral processing: source and output documents are deleted 60 to 70 minutes after the last activity on a form. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
| Parameter | Type | Description |
|---|---|---|
| title | any | |
| dry_run | boolean | |
| library | any | |
| pdf_url | any | |
| retention | any | |
| pdf_base64 | any |
{
"name": "create_form",
"title": "Create a fillable form from a PDF",
"description": "Turn a flat or scanned PDF form into a fillable PDF with detected fields. Upload a PDF (pdf_url: public https link, or pdf_base64) and detect its fields. Returns when detection finishes (usually under two minutes). Give library=<slug> from find_form to start from a form Emboss already keeps. Billed as one form creation; the first 5 each month are free. Optional retention: ephemeral or account_default (default: the account's own setting). Ephemeral processing: source and output documents are deleted 60 to 70 minutes after the last activity on a form. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.",
"inputSchema": {
"type": "object",
"title": "create_formArguments",
"examples": [
{
"pdf_url": "https://example.com/forms/building-permit.pdf",
"retention": "ephemeral"
},
{
"dry_run": true,
"pdf_url": "https://example.com/forms/building-permit.pdf",
"retention": "ephemeral"
}
],
"properties": {
"title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Title",
"default": null
},
"dry_run": {
"type": "boolean",
"title": "Dry Run",
"default": false
},
"library": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Library",
"default": null
},
"pdf_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Pdf Url",
"default": null
},
"retention": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Retention",
"default": null
},
"pdf_base64": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Pdf Base64",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "create_formDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Create a fillable form from a PDF",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Permanently removes a form and its PDFs from the user's library. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
| Parameter | Type | Description |
|---|---|---|
| dry_run | boolean | |
| form_id * | string |
{
"name": "delete_form",
"title": "Delete a form",
"description": "Permanently removes a form and its PDFs from the user's library. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.",
"inputSchema": {
"type": "object",
"title": "delete_formArguments",
"examples": [
{
"form_id": "11111111-2222-3333-4444-555555555555"
},
{
"dry_run": true,
"form_id": "11111111-2222-3333-4444-555555555555"
}
],
"required": [
"form_id"
],
"properties": {
"dry_run": {
"type": "boolean",
"title": "Dry Run",
"default": false
},
"form_id": {
"type": "string",
"title": "Form Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "delete_formDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Delete a form",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": true
}
}Fill a PDF form from structured data such as JSON or key-value answers. Fill a ready form with values keyed by field id or field label. Checkboxes take yes or no; choice fields need one of their options. To lock the filled PDF, call flatten_pdf with its artifact_id; fill_form itself never flattens. Returns a download link plus any labels that did not match (ask the user about those). Billed as one fill; the first 5 each month are free. retention (ephemeral or account_default) is accepted but changes nothing: the form keeps the setting it was created with. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
| Parameter | Type | Description |
|---|---|---|
| values * | object | |
| dry_run | boolean | |
| flatten | boolean | |
| form_id * | string | |
| retention | any |
{
"name": "fill_form",
"title": "Fill a form from values",
"description": "Fill a PDF form from structured data such as JSON or key-value answers. Fill a ready form with values keyed by field id or field label. Checkboxes take yes or no; choice fields need one of their options. To lock the filled PDF, call flatten_pdf with its artifact_id; fill_form itself never flattens. Returns a download link plus any labels that did not match (ask the user about those). Billed as one fill; the first 5 each month are free. retention (ephemeral or account_default) is accepted but changes nothing: the form keeps the setting it was created with. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.",
"inputSchema": {
"type": "object",
"title": "fill_formArguments",
"examples": [
{
"values": {
"Email": "grace@example.com",
"Full Name": "Grace Hopper"
},
"form_id": "11111111-2222-3333-4444-555555555555"
},
{
"values": {
"Email": "grace@example.com",
"Full Name": "Grace Hopper"
},
"dry_run": true,
"form_id": "11111111-2222-3333-4444-555555555555"
}
],
"required": [
"form_id",
"values"
],
"properties": {
"values": {
"type": "object",
"title": "Values",
"additionalProperties": true
},
"dry_run": {
"type": "boolean",
"title": "Dry Run",
"default": false
},
"flatten": {
"type": "boolean",
"title": "Flatten",
"default": false
},
"form_id": {
"type": "string",
"title": "Form Id"
},
"retention": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Retention",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "fill_formDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Fill a form from values",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Fill a PDF form using facts found in supporting documents. Emboss reads the answers out of context_text and/or context_urls (public https links to PDFs, Word, spreadsheets, images, or text) and fills the form. Give form_id for a form already in the library, or pdf_url/pdf_base64 for a new one. Give library=<slug> from find_form to start from a form Emboss already keeps. policy is safe (write high and medium confidence) or strict (high only). Returns a job_id; poll get_job about every 20 seconds. Billed as one context fill; the first 5 each month are free. Optional retention: ephemeral or account_default (default: the account's own setting); it applies only when this call creates the form (pdf_url, pdf_base64 or library), since an existing form keeps the setting it was created with. Ephemeral processing: source and output documents are deleted 60 to 70 minutes after the last activity on a form. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
| Parameter | Type | Description |
|---|---|---|
| policy | string | |
| dry_run | boolean | |
| form_id | any | |
| library | any | |
| pdf_url | any | |
| retention | any | |
| pdf_base64 | any | |
| context_text | any | |
| context_urls | any |
{
"name": "fill_form_from_context",
"title": "Fill a form from documents or notes",
"description": "Fill a PDF form using facts found in supporting documents. Emboss reads the answers out of context_text and/or context_urls (public https links to PDFs, Word, spreadsheets, images, or text) and fills the form. Give form_id for a form already in the library, or pdf_url/pdf_base64 for a new one. Give library=<slug> from find_form to start from a form Emboss already keeps. policy is safe (write high and medium confidence) or strict (high only). Returns a job_id; poll get_job about every 20 seconds. Billed as one context fill; the first 5 each month are free. Optional retention: ephemeral or account_default (default: the account's own setting); it applies only when this call creates the form (pdf_url, pdf_base64 or library), since an existing form keeps the setting it was created with. Ephemeral processing: source and output documents are deleted 60 to 70 minutes after the last activity on a form. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.",
"inputSchema": {
"type": "object",
"title": "fill_form_from_contextArguments",
"examples": [
{
"policy": "safe",
"form_id": "11111111-2222-3333-4444-555555555555",
"context_text": "Grace Hopper, born 9 December 1906, 1 Navy Way, Arlington, VA 22202."
},
{
"policy": "safe",
"dry_run": true,
"form_id": "11111111-2222-3333-4444-555555555555",
"context_text": "Grace Hopper, born 9 December 1906, 1 Navy Way, Arlington, VA 22202."
}
],
"properties": {
"policy": {
"type": "string",
"title": "Policy",
"default": "safe"
},
"dry_run": {
"type": "boolean",
"title": "Dry Run",
"default": false
},
"form_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Form Id",
"default": null
},
"library": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Library",
"default": null
},
"pdf_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Pdf Url",
"default": null
},
"retention": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Retention",
"default": null
},
"pdf_base64": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Pdf Base64",
"default": null
},
"context_text": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Context Text",
"default": null
},
"context_urls": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Context Urls",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "fill_form_from_contextDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Fill a form from documents or notes",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Prepare a form from documents: a proposal of every answer with its source, what is missing, and where documents disagree, before writing, plus attachments for a package. Same inputs as fill_form_from_context (form_id for a form already in the library, or pdf_url/pdf_base64 for a new one, plus context_text and/or context_urls), but nothing is written into the PDF: read the proposal, answer what is missing, then commit. policy is safe (write high and medium confidence) or strict (high only). Returns a job_id and a proposal_id; poll get_job about every 20 seconds. Billed as one context fill; the first 5 each month are free. Optional retention: ephemeral or account_default (default: the account's own setting); it applies only when this call creates the form (pdf_url, pdf_base64 or library), since an existing form keeps the setting it was created with. Ephemeral processing: source and output documents are deleted 60 to 70 minutes after the last activity on a form. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
| Parameter | Type | Description |
|---|---|---|
| policy | string | |
| dry_run | boolean | |
| form_id | any | |
| library | any | |
| pdf_url | any | |
| retention | any | |
| pdf_base64 | any | |
| context_text | any | |
| context_urls | any |
{
"name": "prepare_form",
"title": "Prepare a form from documents",
"description": "Prepare a form from documents: a proposal of every answer with its source, what is missing, and where documents disagree, before writing, plus attachments for a package. Same inputs as fill_form_from_context (form_id for a form already in the library, or pdf_url/pdf_base64 for a new one, plus context_text and/or context_urls), but nothing is written into the PDF: read the proposal, answer what is missing, then commit. policy is safe (write high and medium confidence) or strict (high only). Returns a job_id and a proposal_id; poll get_job about every 20 seconds. Billed as one context fill; the first 5 each month are free. Optional retention: ephemeral or account_default (default: the account's own setting); it applies only when this call creates the form (pdf_url, pdf_base64 or library), since an existing form keeps the setting it was created with. Ephemeral processing: source and output documents are deleted 60 to 70 minutes after the last activity on a form. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.",
"inputSchema": {
"type": "object",
"title": "prepare_formArguments",
"examples": [
{
"policy": "safe",
"library": "irs-w-9",
"context_text": "Hopper Analytical LLC, EIN 12-3456789, 1 Navy Way, Arlington, VA 22202."
},
{
"policy": "safe",
"dry_run": true,
"library": "irs-w-9",
"context_text": "Hopper Analytical LLC, EIN 12-3456789, 1 Navy Way, Arlington, VA 22202."
}
],
"properties": {
"policy": {
"type": "string",
"title": "Policy",
"default": "safe"
},
"dry_run": {
"type": "boolean",
"title": "Dry Run",
"default": false
},
"form_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Form Id",
"default": null
},
"library": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Library",
"default": null
},
"pdf_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Pdf Url",
"default": null
},
"retention": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Retention",
"default": null
},
"pdf_base64": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Pdf Base64",
"default": null
},
"context_text": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Context Text",
"default": null
},
"context_urls": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Context Urls",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "prepare_formDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Prepare a form from documents",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Status of a fill_form_from_context, prepare_form, or commit_proposal job. When ready, returns the download link, how many fields were filled, and for a commit, the result, receipt_url and, when one was asked for, package_url.
| Parameter | Type | Description |
|---|---|---|
| job_id * | string |
{
"name": "get_job",
"title": "Check a context fill job",
"description": "Status of a fill_form_from_context, prepare_form, or commit_proposal job. When ready, returns the download link, how many fields were filled, and for a commit, the result, receipt_url and, when one was asked for, package_url.",
"inputSchema": {
"type": "object",
"title": "get_jobArguments",
"examples": [
{
"job_id": "77777777-8888-9999-aaaa-bbbbbbbbbbbb"
}
],
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string",
"title": "Job Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_jobDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Check a context fill job",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Propose which spreadsheet columns fill which PDF form fields. Given a CSV (csv_text or csv_url), proposes which column fills which field. Only the header row matters. Billed as one context fill (5 free each month). Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
| Parameter | Type | Description |
|---|---|---|
| csv_url | any | |
| dry_run | boolean | |
| form_id * | string | |
| csv_text | any |
{
"name": "suggest_mapping",
"title": "Map spreadsheet columns to form fields",
"description": "Propose which spreadsheet columns fill which PDF form fields. Given a CSV (csv_text or csv_url), proposes which column fills which field. Only the header row matters. Billed as one context fill (5 free each month). Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.",
"inputSchema": {
"type": "object",
"title": "suggest_mappingArguments",
"examples": [
{
"form_id": "11111111-2222-3333-4444-555555555555",
"csv_text": "Full Name,Email\nGrace Hopper,grace@example.com\n"
},
{
"dry_run": true,
"form_id": "11111111-2222-3333-4444-555555555555",
"csv_text": "Full Name,Email\nGrace Hopper,grace@example.com\n"
}
],
"required": [
"form_id"
],
"properties": {
"csv_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Csv Url",
"default": null
},
"dry_run": {
"type": "boolean",
"title": "Dry Run",
"default": false
},
"form_id": {
"type": "string",
"title": "Form Id"
},
"csv_text": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Csv Text",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "suggest_mappingDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Map spreadsheet columns to form fields",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Fill one copy of a PDF form for every row of a spreadsheet. Fill a form for every row of a CSV (csv_text or csv_url, up to 1000 rows). mapping is {column: field_id}; omit it to use the suggested mapping. If mapping is omitted, suggest_mapping runs first and is billed as one context fill. Batches up to 50 rows finish before this returns; larger ones keep running, poll get_batch. Each row is billed as one fill. retention (ephemeral or account_default) is accepted but changes nothing: the form keeps the setting it was created with. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
| Parameter | Type | Description |
|---|---|---|
| csv_url | any | |
| dry_run | boolean | |
| form_id * | string | |
| mapping | any | |
| csv_text | any | |
| retention | any |
{
"name": "fill_batch",
"title": "Fill the form once per spreadsheet row",
"description": "Fill one copy of a PDF form for every row of a spreadsheet. Fill a form for every row of a CSV (csv_text or csv_url, up to 1000 rows). mapping is {column: field_id}; omit it to use the suggested mapping. If mapping is omitted, suggest_mapping runs first and is billed as one context fill. Batches up to 50 rows finish before this returns; larger ones keep running, poll get_batch. Each row is billed as one fill. retention (ephemeral or account_default) is accepted but changes nothing: the form keeps the setting it was created with. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.",
"inputSchema": {
"type": "object",
"title": "fill_batchArguments",
"examples": [
{
"form_id": "11111111-2222-3333-4444-555555555555",
"mapping": {
"Email": 2,
"Full Name": 1
},
"csv_text": "Full Name,Email\nGrace Hopper,grace@example.com\nAda Lovelace,ada@example.com\n"
},
{
"dry_run": true,
"form_id": "11111111-2222-3333-4444-555555555555",
"mapping": {
"Email": 2,
"Full Name": 1
},
"csv_text": "Full Name,Email\nGrace Hopper,grace@example.com\nAda Lovelace,ada@example.com\n"
}
],
"required": [
"form_id"
],
"properties": {
"csv_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Csv Url",
"default": null
},
"dry_run": {
"type": "boolean",
"title": "Dry Run",
"default": false
},
"form_id": {
"type": "string",
"title": "Form Id"
},
"mapping": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"title": "Mapping",
"default": null
},
"csv_text": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Csv Text",
"default": null
},
"retention": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Retention",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "fill_batchDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Fill the form once per spreadsheet row",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Progress of a fill_batch run with a download link per finished row (100 at a time; pass next_cursor as cursor for the next 100) and a zip link when done.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| cursor | any | |
| batch_id * | string |
{
"name": "get_batch",
"title": "Check a batch fill",
"description": "Progress of a fill_batch run with a download link per finished row (100 at a time; pass next_cursor as cursor for the next 100) and a zip link when done.",
"inputSchema": {
"type": "object",
"title": "get_batchArguments",
"examples": [
{
"batch_id": "44444444-5555-6666-7777-888888888888"
}
],
"required": [
"batch_id"
],
"properties": {
"limit": {
"type": "integer",
"title": "Limit",
"default": 100
},
"cursor": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Cursor",
"default": null
},
"batch_id": {
"type": "string",
"title": "Batch Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_batchDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Check a batch fill",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Write or confirm the answers, render the form with text that fits, check it, and return the PDF with a report and a receipt, or one submission package. Give the proposal_id from prepare_form; confirm is a list of field ids whose proposed value is accepted as it is (the ids get_proposal lists under confirmations); plus any values the agent decided for fields still open (field_id, value, and an optional note), and a policy (safe or strict) to override the proposal's own. Set package to true to also receive one submission package: the filled form, the attachments added to this proposal in the order the form asks for them, and the receipt embedded in the file; that is billed as one package. Returns a job_id; poll get_job about every 20 seconds for the download link, report, receipt and, when asked for, package_url. Free within the proposal's already-billed prepare, up to 10 commits per proposal. Checkboxes take yes or no; yes ticks that box. In a Yes/No pair, say yes to the box you want; two yeses in one pair are refused. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
| Parameter | Type | Description |
|---|---|---|
| policy | any | |
| values | any | |
| confirm | any | |
| dry_run | boolean | |
| package | boolean | |
| proposal_id * | string |
{
"name": "commit_proposal",
"title": "Commit a proposal and produce the PDF",
"description": "Write or confirm the answers, render the form with text that fits, check it, and return the PDF with a report and a receipt, or one submission package. Give the proposal_id from prepare_form; confirm is a list of field ids whose proposed value is accepted as it is (the ids get_proposal lists under confirmations); plus any values the agent decided for fields still open (field_id, value, and an optional note), and a policy (safe or strict) to override the proposal's own. Set package to true to also receive one submission package: the filled form, the attachments added to this proposal in the order the form asks for them, and the receipt embedded in the file; that is billed as one package. Returns a job_id; poll get_job about every 20 seconds for the download link, report, receipt and, when asked for, package_url. Free within the proposal's already-billed prepare, up to 10 commits per proposal. Checkboxes take yes or no; yes ticks that box. In a Yes/No pair, say yes to the box you want; two yeses in one pair are refused. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.",
"inputSchema": {
"type": "object",
"title": "commit_proposalArguments",
"examples": [
{
"values": [
{
"value": "Grace Hopper",
"field_id": 5
}
],
"confirm": [
3
],
"package": false,
"proposal_id": "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee"
},
{
"values": [
{
"value": "Grace Hopper",
"field_id": 5
}
],
"confirm": [
3
],
"dry_run": true,
"package": false,
"proposal_id": "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee"
}
],
"required": [
"proposal_id"
],
"properties": {
"policy": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Policy",
"default": null
},
"values": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
{
"type": "null"
}
],
"title": "Values",
"default": null
},
"confirm": {
"anyOf": [
{
"type": "array",
"items": {
"type": "integer"
}
},
{
"type": "null"
}
],
"title": "Confirm",
"default": null
},
"dry_run": {
"type": "boolean",
"title": "Dry Run",
"default": false
},
"package": {
"type": "boolean",
"title": "Package",
"default": false
},
"proposal_id": {
"type": "string",
"title": "Proposal Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "commit_proposalDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Commit a proposal and produce the PDF",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Prepare a form from documents: a proposal of every answer with its source, what is missing, and where documents disagree, before writing, plus attachments for a package. Read a proposal by its proposal_id: every field's state, its candidate values with evidence, and the questions still open. No charge to read it.
| Parameter | Type | Description |
|---|---|---|
| proposal_id * | string |
{
"name": "get_proposal",
"title": "Read a proposal",
"description": "Prepare a form from documents: a proposal of every answer with its source, what is missing, and where documents disagree, before writing, plus attachments for a package. Read a proposal by its proposal_id: every field's state, its candidate values with evidence, and the questions still open. No charge to read it.",
"inputSchema": {
"type": "object",
"title": "get_proposalArguments",
"examples": [
{
"proposal_id": "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee"
}
],
"required": [
"proposal_id"
],
"properties": {
"proposal_id": {
"type": "string",
"title": "Proposal Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_proposalDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Read a proposal",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Check a filled form: required fields, allowed options, consistent choices, text that fits, empty signature boxes; returns complete, review required or incomplete. Give a form_id and the filled PDF (pdf_url: public https link, or pdf_base64). Billed as one verify; the first 5 each month are free. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
| Parameter | Type | Description |
|---|---|---|
| dry_run | boolean | |
| form_id * | string | |
| pdf_url | any | |
| pdf_base64 | any |
{
"name": "verify_form",
"title": "Check a filled form",
"description": "Check a filled form: required fields, allowed options, consistent choices, text that fits, empty signature boxes; returns complete, review required or incomplete. Give a form_id and the filled PDF (pdf_url: public https link, or pdf_base64). Billed as one verify; the first 5 each month are free. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.",
"inputSchema": {
"type": "object",
"title": "verify_formArguments",
"examples": [
{
"form_id": "11111111-2222-3333-4444-555555555555",
"pdf_url": "https://example.com/filled/building-permit.pdf"
},
{
"dry_run": true,
"form_id": "11111111-2222-3333-4444-555555555555",
"pdf_url": "https://example.com/filled/building-permit.pdf"
}
],
"required": [
"form_id"
],
"properties": {
"dry_run": {
"type": "boolean",
"title": "Dry Run",
"default": false
},
"form_id": {
"type": "string",
"title": "Form Id"
},
"pdf_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Pdf Url",
"default": null
},
"pdf_base64": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Pdf Base64",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "verify_formDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Check a filled form",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Read the values out of a filled PDF form, labelled by field, with a completeness verdict when the form is known. Give the filled PDF (pdf_url: public https link, or pdf_base64) and, when you know it, form_id. Returns every form box in the file with its value and whether it is filled; when the form is recognised, each value also carries its label and whether it was required, plus a completeness verdict. Nothing is stored: read-back never keeps your file. Billed as one read; the first 5 each month are free. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
| Parameter | Type | Description |
|---|---|---|
| dry_run | boolean | |
| form_id | any | |
| pdf_url | any | |
| pdf_base64 | any |
{
"name": "read_form",
"title": "Read a filled form back",
"description": "Read the values out of a filled PDF form, labelled by field, with a completeness verdict when the form is known. Give the filled PDF (pdf_url: public https link, or pdf_base64) and, when you know it, form_id. Returns every form box in the file with its value and whether it is filled; when the form is recognised, each value also carries its label and whether it was required, plus a completeness verdict. Nothing is stored: read-back never keeps your file. Billed as one read; the first 5 each month are free. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.",
"inputSchema": {
"type": "object",
"title": "read_formArguments",
"examples": [
{
"form_id": "11111111-2222-3333-4444-555555555555",
"pdf_url": "https://example.com/filled/building-permit.pdf"
},
{
"dry_run": true,
"form_id": "11111111-2222-3333-4444-555555555555",
"pdf_url": "https://example.com/filled/building-permit.pdf"
}
],
"properties": {
"dry_run": {
"type": "boolean",
"title": "Dry Run",
"default": false
},
"form_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Form Id",
"default": null
},
"pdf_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Pdf Url",
"default": null
},
"pdf_base64": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Pdf Base64",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "read_formDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Read a filled form back",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Prepare a form from documents: a proposal of every answer with its source, what is missing, and where documents disagree, before writing, plus attachments for a package. Attach one document (file_url: public https link, or file_base64) to a proposal from prepare_form. PDF, PNG and JPEG only, at most 20 per proposal. requirement: the name of an entry in the form's attachments_required list to satisfy it; uploading a second document for the same requirement replaces the first. Free: attachments are part of the already-billed prepare.
| Parameter | Type | Description |
|---|---|---|
| file_url | any | |
| file_base64 | any | |
| proposal_id * | string | |
| requirement | any |
{
"name": "add_attachment",
"title": "Attach a document to a proposal",
"description": "Prepare a form from documents: a proposal of every answer with its source, what is missing, and where documents disagree, before writing, plus attachments for a package. Attach one document (file_url: public https link, or file_base64) to a proposal from prepare_form. PDF, PNG and JPEG only, at most 20 per proposal. requirement: the name of an entry in the form's attachments_required list to satisfy it; uploading a second document for the same requirement replaces the first. Free: attachments are part of the already-billed prepare.",
"inputSchema": {
"type": "object",
"title": "add_attachmentArguments",
"examples": [
{
"file_url": "https://example.com/docs/proof-of-insurance.pdf",
"proposal_id": "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee",
"requirement": "Proof of insurance"
}
],
"required": [
"proposal_id"
],
"properties": {
"file_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "File Url",
"default": null
},
"file_base64": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "File Base64",
"default": null
},
"proposal_id": {
"type": "string",
"title": "Proposal Id"
},
"requirement": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Requirement",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "add_attachmentDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Attach a document to a proposal",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Send a PDF to a fax number and track delivery, priced per transmitted page. Give a destination in E.164 form (for example +15025551212; US, Canadian and Mexican numbers only) and the PDF: an artifact_id from any earlier result, a job_id from fill_form_from_context or commit_proposal once get_job reports ready, a form_id for the fillable form, or one PDF by pdf_url or pdf_base64, or a sources list of artifact ids (each with an optional pages range such as 1-3,7) faxed together as one packet. Returns a job id at once; poll get_fax for delivery. Billed per page at delivery; a failed fax is not charged. Needs a payment method on the account; get_usage reports fax_ready. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.
| Parameter | Type | Description |
|---|---|---|
| to * | string | |
| job_id | any | |
| dry_run | boolean | |
| form_id | any | |
| pdf_url | any | |
| sources | any | |
| pdf_base64 | any | |
| artifact_id | any |
{
"name": "send_fax",
"title": "Send a PDF by fax",
"description": "Send a PDF to a fax number and track delivery, priced per transmitted page. Give a destination in E.164 form (for example +15025551212; US, Canadian and Mexican numbers only) and the PDF: an artifact_id from any earlier result, a job_id from fill_form_from_context or commit_proposal once get_job reports ready, a form_id for the fillable form, or one PDF by pdf_url or pdf_base64, or a sources list of artifact ids (each with an optional pages range such as 1-3,7) faxed together as one packet. Returns a job id at once; poll get_fax for delivery. Billed per page at delivery; a failed fax is not charged. Needs a payment method on the account; get_usage reports fax_ready. Pass dry_run=true to rehearse this call without doing it: nothing is stored, charged or sent, and no AI is used. The answer says whether the real call would succeed or be refused, what it would cost, and what a rehearsal cannot check.",
"inputSchema": {
"type": "object",
"title": "send_faxArguments",
"examples": [
{
"to": "+15025550123",
"job_id": "77777777-8888-9999-aaaa-bbbbbbbbbbbb"
},
{
"to": "+15025550123",
"job_id": "77777777-8888-9999-aaaa-bbbbbbbbbbbb",
"dry_run": true
}
],
"required": [
"to"
],
"properties": {
"to": {
"type": "string",
"title": "To"
},
"job_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Job Id",
"default": null
},
"dry_run": {
"type": "boolean",
"title": "Dry Run",
"default": false
},
"form_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Form Id",
"default": null
},
"pdf_url": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Pdf Url",
"default": null
},
"sources": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
{
"type": "null"
}
],
"title": "Sources",
"default": null
},
"pdf_base64": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Pdf Base64",
"default": null
},
"artifact_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Artifact Id",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "send_faxDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Send a PDF by fax",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Delivery status and receipt of a send_fax job. status is queued, working, delivered, failed or expired; keep checking about every 20 seconds until it is delivered, failed or expired. A busy, unanswered or dropped call is retried automatically up to three more times over about 17 minutes while the status stays working; attempts, max_attempts and next_attempt_at say where it is. A failed or expired fax carries failure_category, failure_reason, retryable, refund and a plain failure_message saying what happened.
| Parameter | Type | Description |
|---|---|---|
| job_id * | string |
{
"name": "get_fax",
"title": "Check a fax",
"description": "Delivery status and receipt of a send_fax job. status is queued, working, delivered, failed or expired; keep checking about every 20 seconds until it is delivered, failed or expired. A busy, unanswered or dropped call is retried automatically up to three more times over about 17 minutes while the status stays working; attempts, max_attempts and next_attempt_at say where it is. A failed or expired fax carries failure_category, failure_reason, retryable, refund and a plain failure_message saying what happened.",
"inputSchema": {
"type": "object",
"title": "get_faxArguments",
"examples": [
{
"job_id": "cccccccc-dddd-eeee-ffff-000000000000"
}
],
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string",
"title": "Job Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_faxDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Check a fax",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Free. Build one PDF from pages of several artifacts, in the order and rotation you name. Build one PDF from several artifacts: sources is a list of {artifact_id, pages, rotate}; pages is a selection like 1-3,7 (omit for every page), rotate is 90, 180 or 270. Returns the new artifact_id and a download_url (a link that works for about an hour). Page selections: https://getemboss.ai/docs/artifacts.
| Parameter | Type | Description |
|---|---|---|
| sources * | array |
{
"name": "compose_pdf",
"title": "Compose a PDF from artifacts",
"description": "Free. Build one PDF from pages of several artifacts, in the order and rotation you name. Build one PDF from several artifacts: sources is a list of {artifact_id, pages, rotate}; pages is a selection like 1-3,7 (omit for every page), rotate is 90, 180 or 270. Returns the new artifact_id and a download_url (a link that works for about an hour). Page selections: https://getemboss.ai/docs/artifacts.",
"inputSchema": {
"type": "object",
"title": "compose_pdfArguments",
"examples": [
{
"sources": [
{
"pages": "1-2",
"artifact_id": "22222222-3333-4444-5555-666666666666"
},
{
"artifact_id": "99999999-aaaa-bbbb-cccc-dddddddddddd"
}
]
}
],
"required": [
"sources"
],
"properties": {
"sources": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
},
"title": "Sources"
}
}
},
"outputSchema": {
"type": "object",
"title": "compose_pdfDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Compose a PDF from artifacts",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Free. Join whole PDFs into one file in the order given. Join whole PDFs in order: sources is a list of {artifact_id}. Returns the new artifact_id and a download_url (a link that works for about an hour). For page selections use compose_pdf.
| Parameter | Type | Description |
|---|---|---|
| sources * | array |
{
"name": "merge_pdf",
"title": "Merge PDFs",
"description": "Free. Join whole PDFs into one file in the order given. Join whole PDFs in order: sources is a list of {artifact_id}. Returns the new artifact_id and a download_url (a link that works for about an hour). For page selections use compose_pdf.",
"inputSchema": {
"type": "object",
"title": "merge_pdfArguments",
"examples": [
{
"sources": [
{
"artifact_id": "22222222-3333-4444-5555-666666666666"
},
{
"artifact_id": "99999999-aaaa-bbbb-cccc-dddddddddddd"
}
]
}
],
"required": [
"sources"
],
"properties": {
"sources": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
},
"title": "Sources"
}
}
},
"outputSchema": {
"type": "object",
"title": "merge_pdfDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Merge PDFs",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Free. Keep only the pages you name from a PDF, in the order you name them. Keep only the pages named in pages (1-based, like 2,5-9, repeats and any order allowed) from artifact_id. Returns the new artifact_id and a download_url (a link that works for about an hour).
| Parameter | Type | Description |
|---|---|---|
| pages * | string | |
| artifact_id * | string |
{
"name": "extract_pages",
"title": "Extract pages",
"description": "Free. Keep only the pages you name from a PDF, in the order you name them. Keep only the pages named in pages (1-based, like 2,5-9, repeats and any order allowed) from artifact_id. Returns the new artifact_id and a download_url (a link that works for about an hour).",
"inputSchema": {
"type": "object",
"title": "extract_pagesArguments",
"examples": [
{
"pages": "1-3",
"artifact_id": "99999999-aaaa-bbbb-cccc-dddddddddddd"
}
],
"required": [
"artifact_id",
"pages"
],
"properties": {
"pages": {
"type": "string",
"title": "Pages"
},
"artifact_id": {
"type": "string",
"title": "Artifact Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "extract_pagesDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Extract pages",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Free. Remove the pages you name from a PDF and keep the rest in order. Remove the pages named in pages (1-based, like 1-2,17) from artifact_id; every other page stays in order. Returns the new artifact_id and a download_url (a link that works for about an hour).
| Parameter | Type | Description |
|---|---|---|
| pages * | string | |
| artifact_id * | string |
{
"name": "delete_pages",
"title": "Delete pages",
"description": "Free. Remove the pages you name from a PDF and keep the rest in order. Remove the pages named in pages (1-based, like 1-2,17) from artifact_id; every other page stays in order. Returns the new artifact_id and a download_url (a link that works for about an hour).",
"inputSchema": {
"type": "object",
"title": "delete_pagesArguments",
"examples": [
{
"pages": "2",
"artifact_id": "99999999-aaaa-bbbb-cccc-dddddddddddd"
}
],
"required": [
"artifact_id",
"pages"
],
"properties": {
"pages": {
"type": "string",
"title": "Pages"
},
"artifact_id": {
"type": "string",
"title": "Artifact Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "delete_pagesDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Delete pages",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Free. Put a PDF's pages in a new order you give, every page exactly once. Reorder artifact_id's pages: order lists every page number exactly once, in the new order. Returns the new artifact_id and a download_url (a link that works for about an hour).
| Parameter | Type | Description |
|---|---|---|
| order * | array | |
| artifact_id * | string |
{
"name": "reorder_pages",
"title": "Reorder pages",
"description": "Free. Put a PDF's pages in a new order you give, every page exactly once. Reorder artifact_id's pages: order lists every page number exactly once, in the new order. Returns the new artifact_id and a download_url (a link that works for about an hour).",
"inputSchema": {
"type": "object",
"title": "reorder_pagesArguments",
"examples": [
{
"order": [
2,
1,
3
],
"artifact_id": "99999999-aaaa-bbbb-cccc-dddddddddddd"
}
],
"required": [
"artifact_id",
"order"
],
"properties": {
"order": {
"type": "array",
"items": {
"type": "integer"
},
"title": "Order"
},
"artifact_id": {
"type": "string",
"title": "Artifact Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "reorder_pagesDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Reorder pages",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Free. Rotate the pages you name by 90, 180 or 270 degrees. Rotate pages of artifact_id: rotations is a list of {pages, degrees} with degrees 90, 180 or 270, added clockwise to each page's current rotation. Returns the new artifact_id and a download_url (a link that works for about an hour).
| Parameter | Type | Description |
|---|---|---|
| rotations * | array | |
| artifact_id * | string |
{
"name": "rotate_pages",
"title": "Rotate pages",
"description": "Free. Rotate the pages you name by 90, 180 or 270 degrees. Rotate pages of artifact_id: rotations is a list of {pages, degrees} with degrees 90, 180 or 270, added clockwise to each page's current rotation. Returns the new artifact_id and a download_url (a link that works for about an hour).",
"inputSchema": {
"type": "object",
"title": "rotate_pagesArguments",
"examples": [
{
"rotations": [
{
"pages": "1",
"degrees": 90
}
],
"artifact_id": "99999999-aaaa-bbbb-cccc-dddddddddddd"
}
],
"required": [
"artifact_id",
"rotations"
],
"properties": {
"rotations": {
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
},
"title": "Rotations"
},
"artifact_id": {
"type": "string",
"title": "Artifact Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "rotate_pagesDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Rotate pages",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Free. Report a PDF's structure: page count, page sizes and rotations, encryption, form fields, annotations. Structural facts about artifact_id: page count, page sizes and rotations, whether it is encrypted, has form fields, annotations, outlines, embedded files or JavaScript. No text, no field values.
| Parameter | Type | Description |
|---|---|---|
| artifact_id * | string |
{
"name": "inspect_pdf",
"title": "Inspect a PDF",
"description": "Free. Report a PDF's structure: page count, page sizes and rotations, encryption, form fields, annotations. Structural facts about artifact_id: page count, page sizes and rotations, whether it is encrypted, has form fields, annotations, outlines, embedded files or JavaScript. No text, no field values.",
"inputSchema": {
"type": "object",
"title": "inspect_pdfArguments",
"examples": [
{
"artifact_id": "99999999-aaaa-bbbb-cccc-dddddddddddd"
}
],
"required": [
"artifact_id"
],
"properties": {
"artifact_id": {
"type": "string",
"title": "Artifact Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "inspect_pdfDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Inspect a PDF",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Free. Lock a filled form: draw every field's value and every comment into the page so nothing can be edited. Lock artifact_id, usually the filled PDF from fill_form: every field's value, checkbox and comment becomes part of the page, no fields stay editable, links keep working, and the original stays as it is. Returns the new artifact_id, a download_url (a link that works for about an hour) and a report: fields_locked, annotations_locked, pages, and calculated_left_blank (the labels of boxes the form totals itself that were empty). A locked form can't be read back or checked, so run read_form or verify_form first. Refuses a digitally signed PDF (pdf_signed) and a dynamic XFA form (xfa_dynamic).
| Parameter | Type | Description |
|---|---|---|
| artifact_id * | string |
{
"name": "flatten_pdf",
"title": "Lock a filled form",
"description": "Free. Lock a filled form: draw every field's value and every comment into the page so nothing can be edited. Lock artifact_id, usually the filled PDF from fill_form: every field's value, checkbox and comment becomes part of the page, no fields stay editable, links keep working, and the original stays as it is. Returns the new artifact_id, a download_url (a link that works for about an hour) and a report: fields_locked, annotations_locked, pages, and calculated_left_blank (the labels of boxes the form totals itself that were empty). A locked form can't be read back or checked, so run read_form or verify_form first. Refuses a digitally signed PDF (pdf_signed) and a dynamic XFA form (xfa_dynamic).",
"inputSchema": {
"type": "object",
"title": "flatten_pdfArguments",
"examples": [
{
"artifact_id": "99999999-aaaa-bbbb-cccc-dddddddddddd"
}
],
"required": [
"artifact_id"
],
"properties": {
"artifact_id": {
"type": "string",
"title": "Artifact Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "flatten_pdfDictOutput",
"additionalProperties": true
},
"annotations": {
"title": "Lock a filled form",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Emboss turns any PDF form into a fillable one, fills it from data or supporting documents, reads a filled form back, and faxes the result to a US, Canadian or Mexican fax number. Start with list_forms (forms the user already uploaded) or create_form (a new PDF by URL or base64). Long operations return a job or batch id: poll get_job or get_batch about every 20 seconds. Every finished PDF comes back as a download link on getemboss.ai; show it to the user as a link. send_fax faxes a finished PDF to a fax number and returns a job id; poll get_fax for delivery. Never invent field values; when fill_form reports unmatched labels, ask the user.
Names, descriptions and schemas were written by the server and are shown as data.