Mindee MCP by usefulapi is an MCP server published by io.usefulapi, hosted at mindee.usefulapi.io. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 4 tools, including mindee_list_models, mindee_get_job, mindee_get_inference, mindee_extract_document.
Turn PDFs and images into typed fields — invoices, receipts, IDs and custom models — via Mindee OCR.
4,062 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
List the document-extraction models available to your Mindee account (id, name, type). Use a model's `id` as the model_id for mindee_extract_document. V2 API: GET /v2/search/models.
| Parameter | Type | Description |
|---|---|---|
| name | string | Optional case-insensitive name filter, e.g. 'invoice'. |
| model_type | string | Optional model type filter. |
{
"name": "mindee_list_models",
"title": "List extraction models",
"description": "List the document-extraction models available to your Mindee account (id, name, type). Use a model's `id` as the model_id for mindee_extract_document. V2 API: GET /v2/search/models.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"properties": {
"name": {
"type": "string",
"description": "Optional case-insensitive name filter, e.g. 'invoice'."
},
"model_type": {
"type": "string",
"description": "Optional model type filter."
}
}
},
"annotations": {
"title": "List extraction models",
"readOnlyHint": true,
"openWorldHint": true
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Check the processing status of an enqueued document by job id. Status is Waiting | Processing | Processed | Failed. When Processed, the response carries a result_url; pass that inference id to mindee_get_inference. V2 API: GET /v2/jobs/{job_id}.
| Parameter | Type | Description |
|---|---|---|
| job_id * | string | Job id returned by mindee_extract_document (when it times out) or an enqueue call. |
{
"name": "mindee_get_job",
"title": "Get job status",
"description": "Check the processing status of an enqueued document by job id. Status is Waiting | Processing | Processed | Failed. When Processed, the response carries a result_url; pass that inference id to mindee_get_inference. V2 API: GET /v2/jobs/{job_id}.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string",
"description": "Job id returned by mindee_extract_document (when it times out) or an enqueue call."
}
}
},
"annotations": {
"title": "Get job status",
"readOnlyHint": true,
"openWorldHint": true
}
}Fetch the structured result of a completed inference by id, returned as a compact map of extracted fields (plus raw_text if it was requested). V2 API: GET /v2/inferences/{inference_id}.
| Parameter | Type | Description |
|---|---|---|
| raw | boolean | Return the full unshaped API response instead of the compact fields map. Default false. |
| inference_id * | string | Inference id (from a Processed job's result_url, or from mindee_extract_document). |
{
"name": "mindee_get_inference",
"title": "Get extraction result",
"description": "Fetch the structured result of a completed inference by id, returned as a compact map of extracted fields (plus raw_text if it was requested). V2 API: GET /v2/inferences/{inference_id}.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"inference_id"
],
"properties": {
"raw": {
"type": "boolean",
"description": "Return the full unshaped API response instead of the compact fields map. Default false."
},
"inference_id": {
"type": "string",
"description": "Inference id (from a Processed job's result_url, or from mindee_extract_document)."
}
}
},
"annotations": {
"title": "Get extraction result",
"readOnlyHint": true,
"openWorldHint": true
}
}Submit a document (PDF or image) to a Mindee extraction model and return the structured fields. Provide EITHER document_url (a public URL) OR file_base64 (+ filename). This enqueues an inference and polls until it completes (up to ~30s); if it is still processing it returns a job_id you can poll with mindee_get_job then read with mindee_get_inference. NOTE: consumes Mindee API credits (paid, billed per page). V2 API: POST /v2/inferences/enqueue.
| Parameter | Type | Description |
|---|---|---|
| rag | boolean | Enable Retrieval-Augmented Generation for the model, if configured. |
| alias | string | Your own reference tag echoed back in the job/result. |
| polygon | boolean | Return bounding-box polygons for fields. |
| filename | string | Filename for file_base64 uploads, e.g. 'invoice.pdf'. |
| model_id * | string | Extraction model id (from mindee_list_models). |
| raw_text | boolean | Also return the full OCR raw text of the document. |
| confidence | boolean | Return per-field confidence levels (Certain/High/Medium/Low). |
| file_base64 | string | Base64-encoded document bytes, files up to about 2.3 MB (use document_url for larger ones). Use this OR document_url; set `filename` too. |
| webhook_ids | array | Webhook ids to notify on completion (async flows). |
| document_url | string | Public URL of the document to process. Use this OR file_base64. |
{
"name": "mindee_extract_document",
"title": "Extract data from a document",
"description": "Submit a document (PDF or image) to a Mindee extraction model and return the structured fields. Provide EITHER document_url (a public URL) OR file_base64 (+ filename). This enqueues an inference and polls until it completes (up to ~30s); if it is still processing it returns a job_id you can poll with mindee_get_job then read with mindee_get_inference. NOTE: consumes Mindee API credits (paid, billed per page). V2 API: POST /v2/inferences/enqueue.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"model_id"
],
"properties": {
"rag": {
"type": "boolean",
"description": "Enable Retrieval-Augmented Generation for the model, if configured."
},
"alias": {
"type": "string",
"description": "Your own reference tag echoed back in the job/result."
},
"polygon": {
"type": "boolean",
"description": "Return bounding-box polygons for fields."
},
"filename": {
"type": "string",
"description": "Filename for file_base64 uploads, e.g. 'invoice.pdf'."
},
"model_id": {
"type": "string",
"description": "Extraction model id (from mindee_list_models)."
},
"raw_text": {
"type": "boolean",
"description": "Also return the full OCR raw text of the document."
},
"confidence": {
"type": "boolean",
"description": "Return per-field confidence levels (Certain/High/Medium/Low)."
},
"file_base64": {
"type": "string",
"maxLength": 3145728,
"description": "Base64-encoded document bytes, files up to about 2.3 MB (use document_url for larger ones). Use this OR document_url; set `filename` too."
},
"webhook_ids": {
"type": "array",
"items": {
"type": "string"
},
"description": "Webhook ids to notify on completion (async flows)."
},
"document_url": {
"type": "string",
"format": "uri",
"description": "Public URL of the document to process. Use this OR file_base64."
}
}
},
"annotations": {
"title": "Extract data from a document",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Tools for Mindee, hosted by usefulapi.io. If the user is new or asks what this server can do, suggest requests such as: "Which document extraction models are available on my account?"; "Is there an invoice or receipt extraction model on my account?"; "Extract the invoice number and due date from the invoice at this link.". Read-only tools never change data; ask the user before a tool that creates, changes or deletes Mindee data. Free plan: 50 tool calls per month. Run mindee_usage_status to see the calls used this month. If the user asks for something none of these tools can do, tell the user and, with their OK, run mindee_request_feature to record the request. Paid plans: Pro (10,000 tool calls a month, $9/month or $90/year, for normal use) and Pro+ (100,000 tool calls a month, $39/month or $390/year, for automations and heavy use). A plan can be cancelled at any time and then runs to the end of the paid period, so it also suits a one-time job. When the user wants more calls or reaches the limit, run mindee_upgrade without a plan: it returns both plans, each with a payment link for the user to open. mindee_cancel_subscription cancels Pro at the end of the paid period.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.