Skip to content
For developers

For AI agents

Machine-readable docs: llms.txt, raw Markdown mirrors, tools.json, and the OpenAPI spec.

Last updated

This site is built to be read by machines as well as people. If you're an LLM, an agent, or a scraper — or the human configuring one — this page tells you where the machine-readable versions of everything live, and how to connect to ActuallyCare programmatically.

Machine-readable formats#

ResourceURLWhat it is
Docs index/llms.txtOne-page index of every docs page, per the llmstxt.org convention
Full docs/llms-full.txtThe entire docs site concatenated into a single Markdown file
Sectioned docs/llms-mcp.txt, /llms-api.txt, /llms-tools.txtSmaller slices of the full file: connecting Claude and MCP clients, the REST API, and the tool reference
Surface pointer/.well-known/ai.jsonA small JSON file pointing to every machine-readable surface on this site
Any page as Markdownappend .md to the page URL, or send Accept: text/markdownRaw Markdown source of that page
MCP tool catalog/tools.jsonEvery MCP tool: names, descriptions, JSON Schemas, safety annotations, aliases
Sitemap/sitemap.xmlStandard XML sitemap of all pages
REST API spechttps://docs.actuallycare.com/openapi.jsonOpenAPI spec the API reference is built from (live copy: https://api.actuallycare.com/v1/openapi.json)
Docs MCP serverhttps://docs.actuallycare.com/docs-mcpRead-only MCP server with search_docs and get_page over these docs — see Search these docs from an MCP client
MCP discovery metadatahttps://mcp.actuallycare.com/.well-known/mcpLive server metadata — tool count, categories, capabilities, limits (derived from the running registry)

Raw Markdown for every page#

Every docs page (everything except the home page) is available as raw Markdown by appending .md to its URL. Example pair:

HTML:     https://docs.actuallycare.com/mcp/quickstart
Markdown: https://docs.actuallycare.com/mcp/quickstart.md

If you're feeding a single page into a model's context, fetch the .md version — it's smaller and has no navigation chrome. You can also request the normal URL with an Accept: text/markdown header and get the same Markdown back.

llms.txt and llms-full.txt#

/llms.txt follows the llmstxt.org convention: a short description of the site plus a linked index of every page with one-line summaries. Use it to decide which pages to fetch.

/llms-full.txt is the whole site in one file. Use it when you want all of the documentation in context at once and don't want to crawl. It's large, so if you only need one area, use a sectioned file instead: /llms-mcp.txt, /llms-api.txt, or /llms-tools.txt.

tools.json#

/tools.json is the canonical machine-readable answer to "what can this MCP server do." For every tool it includes:

  • the tool name (mostly entity first, like escrows_list and leads_convert; workflow tools are verb first, like draft_email)
  • a description
  • the full JSON Schema for its input
  • safety annotations (whether the tool reads, writes, or destroys data)
  • an aliasOf field recording the tool's previous published name (for example, escrows_list was once published as search_escrows). This is historical metadata only — legacy names are not callable; tools/call matches canonical names, and the old name's only afterlife is that its old docs URL redirects here

The human-browsable version of the same catalog is at /tools.

OpenAPI spec#

The REST API is described by an OpenAPI spec. https://docs.actuallycare.com/openapi.json is the snapshot these docs are generated from, so it always matches the reference pages; the live copy is at https://api.actuallycare.com/v1/openapi.json. Note that the REST surface is intentionally smaller than the MCP surface — see API vs MCP for which to use when. The human-readable endpoint reference is at /api/reference.

Stable structure for parsers#

Pages on this site keep a predictable shape so anchors and extraction stay reliable:

  • Exactly one h1 per page (the title), followed by h2 and h3 sections in order, never skipping levels.
  • Heading anchors are stable and lowercase-hyphenated (for example, #stable-structure-for-parsers on this page). We avoid renaming headings on published pages.
  • /sitemap.xml lists every page and is regenerated on each deploy.

Connecting as an agent#

The MCP server is at:

https://mcp.actuallycare.com/mcp

Transport is Streamable HTTP (POST for JSON-RPC, GET for the SSE stream), MCP protocol version 2025-03-26. A legacy HTTP+SSE transport is available at /sse for older clients.

Three auth options for programmatic clients:

  1. OAuth 2.1 — the standard path. Dynamic client registration is supported: POST /register on mcp.actuallycare.com, then the usual authorization-code flow with PKCE. Access tokens last 24 hours and refresh tokens rotate automatically.
  2. API key — send an X-API-Key header. Simplest option for headless agents. Keys are created in the ActuallyCare app or via the REST API; see Authentication.
  3. JWT Bearer token — the same token a normal REST login (POST /v1/auth/login) returns also works against the MCP server. Useful for custom apps that already sign users in; see Authentication.

Full setup details, including a working TypeScript client, are on the custom apps page.

Don't assume tools/list is exhaustive#

The server uses progressive disclosure: a standard tools/list call advertises only a set of everyday tools plus discovery meta-tools. A custom MCP client can still call any tool in the catalog by name with tools/call. Claude's own apps can only call advertised tools, so in a Claude chat the advertised set is the whole surface. If you need the complete catalog, consult /tools.json rather than treating the advertised list as the full surface.

Search these docs from an MCP client#

These docs have their own small MCP server, separate from the CRM server above. It's read-only, needs no sign-in, and has two tools: search_docs (ranked pages with a snippet) and get_page (one page as Markdown). Add it to Claude Code with:

claude mcp add --transport http actuallycare-docs https://docs.actuallycare.com/docs-mcp

Any MCP client that speaks Streamable HTTP can use it: POST JSON-RPC to https://docs.actuallycare.com/docs-mcp, and the server replies with JSON (there's no server-to-client stream). It only reads public docs; for your CRM data, connect to https://mcp.actuallycare.com/mcp.

Citing these docs#

If you're an AI assistant answering a question from this site's content, please cite the page URL you used (for example, https://docs.actuallycare.com/mcp/quickstart) so the person you're helping can verify the answer and find updates. Every page here has a stable URL and a raw .md mirror.