AnytypeSAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
https://github.com/anyproto/anytype-mcp
Anytype MCP Server
[](https://smithery.ai/server/@Qwinty/anytype-mcp)
An MCP (Model Context Protocol) server that provides access to the Anytype API, allowing AI assistants and other MCP clients to interact with your Anytype data.
Based on the Anytype API definition v0.46+ (2025-03-17). Ensure your Anytype Desktop version is compatible.
Features
- Get list of spaces (
get_spaces) - Search/Get objects within a space (
get_objects,search_space) or globally (global_search) - Get detailed object content (
get_object_content, supports retrieving full text) - Create and delete spaces (
create_space) and objects (create_object,delete_object) - Export objects as markdown (
export_object) - Manage list views and objects within lists (
get_list_views,get_list_view_objects,add_objects_to_list,remove_object_from_list) - Get space members (
get_space_members) - Get types and templates (
get_types,get_type_details,get_templates,get_template_details)
Prerequisites
- Node.js 18 or higher
- Anytype desktop application running locally
- An Anytype account
Installation
Manual Installation
- Clone this repository:
git clone https://github.com/Qwinty/anytype-mcp.git cd anytype-mcp
- Install dependencies:
npm install
- Build the project (compiles TypeScript to JavaScript in
build/):
npm run build
- Obtain an App Key: Before configuring the server, you need an App Key from Anytype. See the "Getting an App Key" section below.
- Add the MCP server to your MCP configuration file
Getting an App Key
Before using the MCP server, you need to obtain an app key from the Anytype desktop application:
- Make sure Anytype desktop is running
- Run the helper script:
npm run get-key
3.
8a69df09a543OBSERVED · 2026-10-09Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add anytype-mcp-server --env ANYTYPE_APP_KEY=${ANYTYPE_APP_KEY} -- npx -y [email protected]{
"mcpServers": {
"anytype-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"ANYTYPE_APP_KEY": "${ANYTYPE_APP_KEY}"
}
}
}
}Exposed tools (18)
13 read · 3 write · 2 destructive. Blast radius: 2 tools can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
add_objects_to_list | write | Adds one or more objects to a specific list in a space. |
create_object | write | Creates a new object within a specified Anytype space. This tool allows you to add various types of content (pages, notes, tasks, etc.) to your spaces. You can specify the object |
create_space | write | Creates a new Anytype space with the specified name. This tool allows you to set up a fresh workspace for organizing objects and collaborating with others. Use this tool when you need to establish a new organizational container for your Anytype content. |
delete_object | destructive | Permanently removes an object from a specified Anytype space. This tool deletes the object and all its content. Use this tool with caution as deleted objects cannot be recovered. Always verify the object ID before deletion to avoid removing important content. |
export_object | read | |
get_list_view_objects | read | Retrieves objects from a specific list view with applied filters and sorting. |
get_list_views | read | Retrieves views configured for a specific list in a space. Views define how objects in the list are filtered and sorted. |
get_object_content | read | Retrieves detailed content and metadata for a specific object in an Anytype space. This tool provides comprehensive information about an object including its properties, relations, and content. Use this tool when you need to examine a specific object |
get_objects | read | |
get_space_members | read | |
get_spaces | read | Retrieves all available Anytype spaces for the current user. This tool returns a list of spaces with their IDs, names, and other metadata. Use this tool to get an overview of all spaces or to find a specific space ID for use with other tools. No parameters are required. |
get_template_details | read | Retrieves detailed information about a specific template in an Anytype space. This tool provides comprehensive details about the template |
get_templates | read | |
get_type_details | read | Retrieves detailed information about a specific object type in an Anytype space. This tool provides comprehensive details about the type |
get_types | read | |
global_search | read | Executes a search across all spaces the user has access to, with options for filtering by type and sorting. |
remove_object_from_list | destructive | Removes an object from a specific list in a space. |
search_space | read | Executes a search within a specific space, with options for filtering by type and sorting. |
Trust audit
SAFEgrade B · trust 88/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (2 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
delete_object, remove_object_from_list
@modelcontextprotocol/sdk, axios, tsx, zod, @types/node, typescript
Gates applied: no_behavioural_pass, no_license.
8a69df09a543full audit observations/trust-audit/mcp-server/qwinty__anytype-1.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-09 | 8a69df09a543 | SAFE | B | 88 | first audit |
Questions
What tools does Anytype expose?
18 in total: 13 read-only, 3 that write, and 2 that can delete or overwrite (delete_object, remove_object_from_list). Every one is listed on this page with its risk.
Is Anytype safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (88/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 2 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Anytype need?
It reads ANYTYPE_APP_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Anytype run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as anytype-mcp-server at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (8a69df09a543), read on 2026-10-09. The repository is watched and re-audited when it changes.