Integrate
Build with AI
Give your assistant these docs as Markdown, and let agents call the API.
Every page here is also Markdown, written for models as much as people. Point your coding assistant at it and it reads the same reference you do, without the page around it.
Docs as MarkdownLink to section
- Any page: add
.mdto its URL (/docs/quickstart.md,/docs/api/rows/list.md), or request it withAccept: text/markdown. - The map:
/docs/llms.txtlists every page with a line on each. - Everything at once:
/docs/llms-full.txtholds every guide and resource page in one file. - The spec:
/docs/openapi.json(or.yaml) describes every endpoint.
On any page, Copy page puts its Markdown on your clipboard, and its menu opens Claude or ChatGPT already reading it.
Connect the docs to your editorLink to section
The docs are also an MCP (opens in a new tab) server at https://anyrow.ai/docs/mcp,
so an assistant can search them and read any page or endpoint while it works. Tools:
search_docs, get_page, get_operation and list_pages.
claude mcp add --transport http anyrow-docs https://anyrow.ai/docs/mcpThe Copy page menu on every page has the same command, and one-click links for Cursor and VS Code.
Prompt your assistantLink to section
Read https://anyrow.ai/docs/llms.txt and the pages it links for what you need.Call the Anyrow API from server code with `Authorization: ApiKey <key>` from ANYROW_API_KEY,base URL https://api.anyrow.ai. Use @anyrow/sdk in TypeScript.Let an agent call AnyrowLink to section
The OpenAPI document works with any tool-calling framework: each
operation becomes a tool with typed inputs. Give the agent a key with only the scopes it needs
(see Authentication): a read-only agent needs tables:read and
rows:read, nothing more.