Anytype MCP Server
Enables AI assistants to interact with Anytype's API through natural language, providing tools for managing spaces, objects, lists, properties, tags, types, and templates. Supports global and space search, as well as creating and managing content in your Anytype knowledge base.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Anytype MCP Servercreate a new task in my Project Ideas space with title 'Research AI trends'"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Anytype MCP Server
The Anytype MCP Server is a Model Context Protocol (MCP) server enabling AI assistants to seamlessly interact with Anytype's API through natural language.
It bridges the gap between AI and Anytype's powerful features by converting Anytype's OpenAPI specification into MCP tools, allowing you to manage your knowledge base through conversation.
Features
Global & Space Search
Spaces & Members
Objects & Lists
Properties & Tags
Types & Templates
Related MCP server: Notion MCP Server
Quick Start
1. Get Your API Key
Open Anytype
Go to App Settings
Navigate to API Keys section
Click on
Create newbutton
You can also get your API key using the command line:
npx -y @anyproto/anytype-mcp get-key2. Configure Your MCP Client
Claude Desktop, Cursor, Windsurf, Raycast, etc.
Add the following configuration to your MCP client settings after replacing <YOUR_API_KEY> with your actual API key:
{
"mcpServers": {
"anytype": {
"command": "npx",
"args": ["-y", "@anyproto/anytype-mcp"],
"env": {
"OPENAPI_MCP_HEADERS": "{\"Authorization\":\"Bearer <YOUR_API_KEY>\", \"Anytype-Version\":\"2025-11-08\"}"
}
}
}
}Tip: After creating an API key in Anytype, you can copy that ready-to-use configuration snippet with your API key already filled in from the API Keys section.
Claude Code (CLI)
Run this command to add the Anytype MCP server after replacing <YOUR_API_KEY> with your actual API key:
claude mcp add anytype -e OPENAPI_MCP_HEADERS='{"Authorization":"Bearer <YOUR_API_KEY>", "Anytype-Version":"2025-11-08"}' -s user -- npx -y @anyproto/anytype-mcpIf you prefer to install the package globally:
Install the package:
npm install -g @anyproto/anytype-mcpUpdate your MCP client configuration to use the global installation:
{
"mcpServers": {
"anytype": {
"command": "anytype-mcp",
"env": {
"OPENAPI_MCP_HEADERS": "{\"Authorization\":\"Bearer <YOUR_API_KEY>\", \"Anytype-Version\":\"2025-11-08\"}"
}
}
}
}Custom API Base URL
By default, the server connects to http://127.0.0.1:31009. For anytype-cli (port 31012) or other custom base URLs, set ANYTYPE_API_BASE_URL:
MCP Client (Claude Desktop, Cursor, etc.):
{
"mcpServers": {
"anytype": {
"command": "npx",
"args": ["-y", "@anyproto/anytype-mcp"],
"env": {
"ANYTYPE_API_BASE_URL": "http://localhost:31012",
"OPENAPI_MCP_HEADERS": "{\"Authorization\":\"Bearer <YOUR_API_KEY>\", \"Anytype-Version\":\"2025-11-08\"}"
}
}
}
}Claude Code (CLI):
claude mcp add anytype \
-e ANYTYPE_API_BASE_URL='http://localhost:31012' \
-e OPENAPI_MCP_HEADERS='{"Authorization":"Bearer <YOUR_API_KEY>", "Anytype-Version":"2025-11-08"}' \
-s user -- npx -y @anyproto/anytype-mcpExample Interactions
Here are some examples of how you can interact with your Anytype:
"Create a new space called 'Project Ideas' with description 'A space for storing project ideas'"
"Add a new object of type 'Task' with title 'Research AI trends' to the 'Project Ideas' space"
"Create a second one with title 'Dive deep into LLMs' with due date in 3 days and assign it to me"
"Now create a collection with the title "Tasks for this week" and add the two tasks to that list. Set due date of the first one to 10 days from now"
Tool behavior and API versions
The server loads one OpenAPI document at startup. With the standard configuration it tries /v2/docs/openapi.json first. If that endpoint returns 404 or 410, it falls back to /docs/openapi.json on the same server, where older apps serve v1. This selects v2 whenever available while supporting apps that only have the legacy API:
"args": ["-y", "@anyproto/anytype-mcp"]To explicitly use the legacy v1 API, select its versioned spec:
"args": ["-y", "@anyproto/anytype-mcp", "run", "http://127.0.0.1:31009/v1/docs/openapi.json"]The versioned /v2/docs/openapi.json URL also remains available for explicitly selecting v2.
Explicit spec URLs and local files are used exactly as supplied, without fallback. Authentication failures, server errors, connection failures, and malformed JSON also fail startup instead of selecting another API. The wrapper uses the routes declared in the selected document without rewriting their version prefixes.
Discovery runs once per MCP process. Tool calls reuse the parsed specification and HTTP client without fetching OpenAPI again. Restart the MCP server after updating Anytype to discover a newly available API version; no persistent spec cache is used.
Tool descriptions contain operation guidance; API errors are returned when calls fail, with isError: true, HTTP status when available, and the API's code, message, issues, and hints.
The server names its own operations by OpenAPI operationId in the prose it serves. In the MCP tool listing and in the field descriptions of a get_schema or get_op_schema response, those names are re-spelled as this wrapper's tool names (list_properties becomes API-list-properties). A repair hint is different: the server spells each operation it names as a REST route and lists it as a typed see_also reference, so the wrapper replaces that route text with the tool name and arguments, and annotates the reference with tool and args. Literal values are never rewritten: enum and example values, op names, endpoint strings and output schemas keep the server's spelling, and so do the OpenAI and Anthropic tool exports, which name tools by operationId.
Successful v1 object creation, updates, deletion, and chat creation return a compact object receipt with its ID, space ID, name, archive state, and type identity when available. The wrapper omits echoed markdown, snippets, property values, icons, and full type definitions. It preserves warnings, generated IDs, and etag/retry metadata. Read the object to retrieve its content when needed. v2 already returns compact create/edit receipts, which are passed through unchanged apart from their warnings, whose hints are re-spelled and whose references gain tool and args; reads, searches, and errors also keep their full API responses.
The shared tool policy controls inputs and request routing:
AuthorizationandAnytype-Versioncome fromOPENAPI_MCP_HEADERS.expected_etagmaps toIf-Match. Use the etag from a previous read to prevent overwriting a changed object. The wrapper does not retry a failed precondition or remove it. Response etags are returned in a separaterequest_metadatatext block when available.request_keymaps toIdempotency-Keyon endpoints that declare that header. Omit it for a new write; the wrapper generates a unique key and returns it inrequest_metadataor an error'srequest_key. Reuse it only to retry the same write. Separate calls get different generated keys, even with identical documents. There are no automatic retries. A globalIdempotency-KeyinOPENAPI_MCP_HEADERSis rejected.Existing callers can still use the exact legacy
If-MatchandIdempotency-Keyargument names. They are not advertised alongside the new names. Conflicting alias values are rejected.Pagination, field selection,
dry_run,create_missing_options, and schema discovery remain available.Pairing and API-key management are excluded. v2
auth_whoamiremains available for inspecting the current credential's permissions; its response does not contain the bearer token.Event-stream tools are excluded because they do not produce a bounded tool result. Use message-listing tools to retrieve chat messages.
File downloads are supported through a binary adapter. The tool streams bytes to a private temporary directory and returns
path,filename,media_type, andsize. The path is local to the machine/container running MCP. Successful files remain there until removed or cleaned up by the operating system; interrupted downloads are removed. Range and cache headers are not model inputs.
Known inputs with HTTP meanings are matched by parameter location, so a document's own fields are preserved. Open-ended JSON documents use the body argument. Objects with declared fields use flat arguments. The existing omission of flattened filters fields and the FilterExpression schema fallback remain separate limitations; this cleanup does not restore filter-schema support.
Duplicate final tool names fail startup with both routes identified. Select separate v1/v2 specs instead of merging operations with overlapping names.
Set ANYTYPE_MCP_DEBUG=1 for concise operation names, response status, and timing on stderr. Arguments, authorization headers, payloads, and entire operation tables are not logged.
Measuring tool definitions
bun run measure-tools
# Or inspect a different local OpenAPI document:
bun run measure-tools ./path/to/openapi.jsonThe default command compares fixed v1 and v2 fixtures. It reports tool count, serialized characters, and UTF-8 bytes, not model-specific token counts.
Development
Installation from Source
Clone the repository:
git clone https://github.com/anyproto/anytype-mcp.git
cd anytype-mcpInstall dependencies (requires Bun):
bun installBuild the project:
bun run buildLink the package globally (optional):
bun linkContribution
Thank you for your desire to develop Anytype together!
❤️ This project and everyone involved in it is governed by the Code of Conduct.
🧑💻 Check out our contributing guide to learn about asking questions, creating issues, or submitting pull requests.
🫢 For security findings, please email security@anytype.io and refer to our security guide for more information.
🤝 Follow us on Github and join the Contributors Community.
Made by Any — a Swiss association 🇨🇭
Licensed under MIT.
This server cannot be deployed
Maintenance
Related MCP Connectors
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Model Context Protocol server for the Apideck Unified API. Connect any MCP-compatible agent framework to 100+ accounting systems, HRIS platforms, file storage providers, and more through one integration. More information https://www.apideck.com/mcp-server
A Model Context Protocol server for Wix AI tools
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- AlicenseBqualityFmaintenanceA Model Context Protocol server that enables AI assistants to read, write, and manipulate notes in your Obsidian vault through a standardized interface.52,509 npm4ISC
- AlicenseNot gradedqualityDmaintenanceA Model Context Protocol server that provides a standardized interface for AI models to access, query, and modify content in Notion workspaces.2,184 npm4MIT
- -licenseNot gradedqualityNot gradedmaintenanceA Model Context Protocol server that enables AI assistants to interact with Notion's API for reading, creating, and modifying Notion content through natural language interactions.-
- FlicenseBqualityDmaintenanceA Model Context Protocol server implementation that can be run directly or through Docker, enabling AI assistants to interact with external systems through the MCP standard.2-