Alter Onboarding is an MCP server published by io.github.AlterAIDev, hosted at mcp.alterauth.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 14 tools, including list_phases, list_skills, get_started, next_step, sdk_integration.
Guide developers from setup through a verified, policy-aware, audited Alter API call.
Nothing else in the archive shares these values.
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.
Inferred from the host name and headers: what a server runs on, not who runs it.
List the lifecycle phases this server serves (setup, modify) and what each is for.
No parameters.
{
"name": "list_phases",
"description": "List the lifecycle phases this server serves (setup, modify) and what each is for.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}
}List the guidance Skills available on this server, with the phase each serves. Read a skill via its resource (skill://alter/<name>).
No parameters.
{
"name": "list_skills",
"description": "List the guidance Skills available on this server, with the phase each serves. Read a skill via its resource (skill://alter/<name>).",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {}
}
}Begin or change an Alter integration. Without args: lists the phases. With `phase`: returns that phase's flows + a heuristic hint — classify the use case YOURSELF and call again with `goal` for the plan. If the use case spans multiple flows, run them sequentially.
| Parameter | Type | Description |
|---|---|---|
| goal | string | The flow id YOU classified. Returns that flow's full plan. |
| phase | string | setup (integrate from scratch) or modify (change an existing integration). |
| use_case | string | Plain-English description of what the developer wants. |
{
"name": "get_started",
"description": "Begin or change an Alter integration. Without args: lists the phases. With `phase`: returns that phase's flows + a heuristic hint — classify the use case YOURSELF and call again with `goal` for the plan. If the use case spans multiple flows, run them sequentially.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"goal": {
"enum": [
"user-data",
"backend-secret",
"agent",
"add-provider",
"add-secret",
"add-agent",
"rotate-key",
"manage-grant",
"set-policy"
],
"type": "string",
"description": "The flow id YOU classified. Returns that flow's full plan."
},
"phase": {
"enum": [
"setup",
"modify"
],
"type": "string",
"description": "setup (integrate from scratch) or modify (change an existing integration)."
},
"use_case": {
"type": "string",
"maxLength": 2000,
"description": "Plain-English description of what the developer wants."
}
}
}
}Return the next step for a flow. Pass the goal (flow id) and the id of the last completed step (omit `after` for the first step). Run each step's detect command FIRST and skip the run command when detection passes. The design step also returns that flow's complete starter ALTER_INTEGRATION.md.
| Parameter | Type | Description |
|---|---|---|
| goal * | string | The flow id (setup goal or modify operation). |
| after | string | Id of the last completed step (e.g. "2", "3a"). |
{
"name": "next_step",
"description": "Return the next step for a flow. Pass the goal (flow id) and the id of the last completed step (omit `after` for the first step). Run each step's detect command FIRST and skip the run command when detection passes. The design step also returns that flow's complete starter ALTER_INTEGRATION.md.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"goal"
],
"properties": {
"goal": {
"enum": [
"user-data",
"backend-secret",
"agent",
"add-provider",
"add-secret",
"add-agent",
"rotate-key",
"manage-grant",
"set-policy"
],
"type": "string",
"description": "The flow id (setup goal or modify operation)."
},
"after": {
"type": "string",
"maxLength": 10,
"description": "Id of the last completed step (e.g. \"2\", \"3a\")."
}
}
}
}Return the Alter SDK wiring (install + client init + request) to write into the developer's codebase, for a language and setup goal.
| Parameter | Type | Description |
|---|---|---|
| goal * | string | The setup goal (user-data | backend-secret | agent). |
| language * | string | Target language. |
{
"name": "sdk_integration",
"description": "Return the Alter SDK wiring (install + client init + request) to write into the developer's codebase, for a language and setup goal.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"language",
"goal"
],
"properties": {
"goal": {
"enum": [
"user-data",
"backend-secret",
"agent"
],
"type": "string",
"description": "The setup goal (user-data | backend-secret | agent)."
},
"language": {
"enum": [
"python",
"typescript"
],
"type": "string",
"description": "Target language."
}
}
}
}Return a runnable Alter SDK call pattern for a language: `proxy-call` (zero-egress proxy_request + HITL), `resolve-grant-by-user` (call as an end user via their delegated grant), `delegate-managed-secret` (the operator-side delegation step), or `resolve-ambiguous-grant` (an identity-mode call matched several of one user's grants: choose deliberately, never the first, and persist it; ask the developer at design time whether users can hold several accounts per provider). Use AFTER `sdk_integration` has wired the client.
| Parameter | Type | Description |
|---|---|---|
| pattern * | string | proxy-call | resolve-grant-by-user | delegate-managed-secret | resolve-ambiguous-grant. |
| language * | string | Target language. |
{
"name": "sdk_pattern",
"description": "Return a runnable Alter SDK call pattern for a language: `proxy-call` (zero-egress proxy_request + HITL), `resolve-grant-by-user` (call as an end user via their delegated grant), `delegate-managed-secret` (the operator-side delegation step), or `resolve-ambiguous-grant` (an identity-mode call matched several of one user's grants: choose deliberately, never the first, and persist it; ask the developer at design time whether users can hold several accounts per provider). Use AFTER `sdk_integration` has wired the client.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"language",
"pattern"
],
"properties": {
"pattern": {
"enum": [
"proxy-call",
"resolve-grant-by-user",
"delegate-managed-secret",
"resolve-ambiguous-grant"
],
"type": "string",
"description": "proxy-call | resolve-grant-by-user | delegate-managed-secret | resolve-ambiguous-grant."
},
"language": {
"enum": [
"python",
"typescript"
],
"type": "string",
"description": "Target language."
}
}
}
}Map a @alter-ai/cli exit code or error message to a remediation.
| Parameter | Type | Description |
|---|---|---|
| error | string | The stderr / error message. |
| exit_code | integer | The CLI process exit code. |
{
"name": "troubleshoot",
"description": "Map a @alter-ai/cli exit code or error message to a remediation.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"error": {
"type": "string",
"maxLength": 10000,
"description": "The stderr / error message."
},
"exit_code": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The CLI process exit code."
}
}
}
}Return a copy-pasteable recipe to VERIFY an integration works: `first-call` (code↔design, an audit row, correct attribution) or `per-user-isolation` (a multi-user/broker server runs two users under different credentials and rejects cross-user access). Guidance only — you run the commands.
| Parameter | Type | Description |
|---|---|---|
| scenario * | string | first-call | per-user-isolation. |
{
"name": "verify_integration",
"description": "Return a copy-pasteable recipe to VERIFY an integration works: `first-call` (code↔design, an audit row, correct attribution) or `per-user-isolation` (a multi-user/broker server runs two users under different credentials and rejects cross-user access). Guidance only — you run the commands.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"scenario"
],
"properties": {
"scenario": {
"enum": [
"first-call",
"per-user-isolation"
],
"type": "string",
"description": "first-call | per-user-isolation."
}
}
}
}Fetch Alter documentation by slug (e.g. "quickstart"). Guides, indexes and skills are served in-band; generated provider operation and model pages link to the full public reference. Accepts any spelling the docs use: a bare slug, a leading slash, a #section anchor, a full docs.alterauth.com URL, or an older path that now redirects. Omit the slug to list every page.
| Parameter | Type | Description |
|---|---|---|
| slug | string | Doc slug, e.g. "guides/call-apis-on-behalf-of-users". |
{
"name": "fetch_doc",
"description": "Fetch Alter documentation by slug (e.g. \"quickstart\"). Guides, indexes and skills are served in-band; generated provider operation and model pages link to the full public reference. Accepts any spelling the docs use: a bare slug, a leading slash, a #section anchor, a full docs.alterauth.com URL, or an older path that now redirects. Omit the slug to list every page.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"slug": {
"type": "string",
"maxLength": 200,
"description": "Doc slug, e.g. \"guides/call-apis-on-behalf-of-users\"."
}
}
}
}Search every bundled page of the Alter documentation (docs and skill pages) by keywords: returns the best-matching pages with the section and a snippet that matched. Use it when a flow step or doc did not point you at the page you need, instead of guessing slugs or listing every page; then read one with fetch_doc and its slug.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | Maximum results (default 8, at most 20). |
| query * | string | Keywords or a short phrase, e.g. "connect widget popup" or "PAT scopes login". |
{
"name": "search_docs",
"description": "Search every bundled page of the Alter documentation (docs and skill pages) by keywords: returns the best-matching pages with the section and a snippet that matched. Use it when a flow step or doc did not point you at the page you need, instead of guessing slugs or listing every page; then read one with fetch_doc and its slug.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"maximum": 20,
"minimum": 1,
"description": "Maximum results (default 8, at most 20)."
},
"query": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "Keywords or a short phrase, e.g. \"connect widget popup\" or \"PAT scopes login\"."
}
}
}
}List every provider with an ingested API spec in Alter's provider-spec catalog, with each spec's source and freshness. Optionally filter by `kind`. Start here, then call list_operations for a provider's operations.
| Parameter | Type | Description |
|---|---|---|
| kind | string | Provider family: oauth (user-authorized) or managed (API-key). |
{
"name": "list_providers",
"description": "List every provider with an ingested API spec in Alter's provider-spec catalog, with each spec's source and freshness. Optionally filter by `kind`. Start here, then call list_operations for a provider's operations.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"kind": {
"enum": [
"oauth",
"managed"
],
"type": "string",
"description": "Provider family: oauth (user-authorized) or managed (API-key)."
}
}
}
}List the API operations a provider exposes, live from Alter's provider-spec catalog (e.g. "what can I call on google?"). Returns operation ids + methods/paths, plus the spec's source and freshness. Omit `kind` to auto-detect the provider family; when the id exists in both oauth and managed you'll be asked to pass `kind`. Machine-readable rows ride in `structuredContent` (see this tool's outputSchema) — read those rather than parsing the prose.
| Parameter | Type | Description |
|---|---|---|
| kind | string | Provider family: oauth (user-authorized) or managed (API-key). |
| limit | integer | Max operations to return (backend default 100, max 500). |
| offset | integer | Zero-based offset for paging through large operation lists. |
| search | string | Case-insensitive filter over operation ids/paths/summaries. |
| provider_id * | string | Provider id, e.g. "google" or "github". |
{
"name": "list_operations",
"description": "List the API operations a provider exposes, live from Alter's provider-spec catalog (e.g. \"what can I call on google?\"). Returns operation ids + methods/paths, plus the spec's source and freshness. Omit `kind` to auto-detect the provider family; when the id exists in both oauth and managed you'll be asked to pass `kind`. Machine-readable rows ride in `structuredContent` (see this tool's outputSchema) — read those rather than parsing the prose.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"provider_id"
],
"properties": {
"kind": {
"enum": [
"oauth",
"managed"
],
"type": "string",
"description": "Provider family: oauth (user-authorized) or managed (API-key)."
},
"limit": {
"type": "integer",
"maximum": 500,
"minimum": 1,
"description": "Max operations to return (backend default 100, max 500)."
},
"offset": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": 0,
"description": "Zero-based offset for paging through large operation lists."
},
"search": {
"type": "string",
"maxLength": 200,
"description": "Case-insensitive filter over operation ids/paths/summaries."
},
"provider_id": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "Provider id, e.g. \"google\" or \"github\"."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"provider_id",
"provider_kind",
"spec_version",
"total",
"offset",
"operations"
],
"properties": {
"total": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Total operations matching the query (before limit/offset)."
},
"offset": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Zero-based offset of the first row."
},
"operations": {
"type": "array",
"items": {
"type": "object",
"required": [
"operation_id",
"method",
"path_template",
"summary"
],
"properties": {
"method": {
"type": "string",
"description": "HTTP method, e.g. GET."
},
"summary": {
"type": [
"string",
"null"
],
"description": "One-line description, or null when the spec omits it."
},
"operation_id": {
"type": "string",
"description": "Pass to get_operation_schema for the full contract."
},
"path_template": {
"type": "string",
"description": "Path with {placeholders}, e.g. /repos/{owner}/{repo}."
}
},
"additionalProperties": false
},
"description": "This page of operations, in the catalog's serving order."
},
"provider_id": {
"type": "string",
"description": "Resolved provider id the rows belong to."
},
"spec_version": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Alter's ingested spec version these rows came from."
},
"provider_kind": {
"enum": [
"oauth",
"managed"
],
"type": "string",
"description": "Resolved provider family: oauth or managed."
}
},
"additionalProperties": false
}
}Fetch one provider API operation's full contract — method, path, parameters, request/response schemas — live from Alter's provider-spec catalog, plus the spec's source and freshness. Get operation ids from list_operations first.
| Parameter | Type | Description |
|---|---|---|
| kind | string | Provider family: oauth (user-authorized) or managed (API-key). |
| provider_id * | string | Provider id, e.g. "google" or "github". |
| operation_id * | string | Operation id from list_operations, e.g. "gmail.users.messages.list". |
{
"name": "get_operation_schema",
"description": "Fetch one provider API operation's full contract — method, path, parameters, request/response schemas — live from Alter's provider-spec catalog, plus the spec's source and freshness. Get operation ids from list_operations first.",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"provider_id",
"operation_id"
],
"properties": {
"kind": {
"enum": [
"oauth",
"managed"
],
"type": "string",
"description": "Provider family: oauth (user-authorized) or managed (API-key)."
},
"provider_id": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"description": "Provider id, e.g. \"google\" or \"github\"."
},
"operation_id": {
"type": "string",
"maxLength": 500,
"minLength": 1,
"description": "Operation id from list_operations, e.g. \"gmail.users.messages.list\"."
}
}
}
}The authoritative grammar of Alter's runtime-policy language, live from the deployed backend: every authorable rule type with its JSON body schema, caps, authorable levels, worked examples, and fail-closed semantics. Call with no arguments for the overview; pass `rule_type` (e.g. "content_match") for one type's full grammar. Use it before authoring rules with `alter policy rules create` — never guess a body shape. Vocabulary: the dashboard's "Runtime policies" surface, the docs' "policy", and `alter policy` are one feature, and the dashboard's "Require human approval" type is the `require_approval` rule type (its grant-editor block is the grant-level baseline of the same gate). The same grammar is what policy files carry: `alter policy validate|test|plan|apply` review rules in Git and CI, and a rule with a `code_owner` is changed through its file, never with `rules update`. Workflow prose: the `set-policy` modify flow (`get_started` with phase=modify), fetch_doc("guides/set-policies"), fetch_doc("guides/add-human-in-the-loop-approvals"), fetch_doc("guides/policy-as-code"), and fetch_doc("reference/cli/commands/policy").
| Parameter | Type | Description |
|---|---|---|
| rule_type | string | One rule type's full grammar, e.g. "content_match" or "quota". |
{
"name": "policy_language",
"description": "The authoritative grammar of Alter's runtime-policy language, live from the deployed backend: every authorable rule type with its JSON body schema, caps, authorable levels, worked examples, and fail-closed semantics. Call with no arguments for the overview; pass `rule_type` (e.g. \"content_match\") for one type's full grammar. Use it before authoring rules with `alter policy rules create` — never guess a body shape. Vocabulary: the dashboard's \"Runtime policies\" surface, the docs' \"policy\", and `alter policy` are one feature, and the dashboard's \"Require human approval\" type is the `require_approval` rule type (its grant-editor block is the grant-level baseline of the same gate). The same grammar is what policy files carry: `alter policy validate|test|plan|apply` review rules in Git and CI, and a rule with a `code_owner` is changed through its file, never with `rules update`. Workflow prose: the `set-policy` modify flow (`get_started` with phase=modify), fetch_doc(\"guides/set-policies\"), fetch_doc(\"guides/add-human-in-the-loop-approvals\"), fetch_doc(\"guides/policy-as-code\"), and fetch_doc(\"reference/cli/commands/policy\").",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"properties": {
"rule_type": {
"type": "string",
"maxLength": 50,
"minLength": 1,
"description": "One rule type's full grammar, e.g. \"content_match\" or \"quota\"."
}
}
}
}Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.