What is anytype-mcp CLAUDE.md?

A set of project instructions for working on anyproto/anytype-mcp, an MCP server that connects Anytype's API to AI assistants. It documents commands for installing, developing, testing, building, and checking the TypeScript project.

Use it to run the development server, build the project, run Vitest tests, lint and format code, check TypeScript types, or parse an OpenAPI specification.

It gives a coding agent the repository's expected commands and quality checks, reducing guesswork when changing or reviewing the code.

How anyproto/anytype-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to anyproto/anytype-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/anyproto/anytype-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/anyproto/anytype-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/anyproto/anytype-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/anyproto/anytype-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/anyproto/anytype-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/anyproto/anytype-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/anyproto/anytype-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/anyproto/anytype-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 742 This file is loaded in full into every session.

When invoked 742 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00742	$0.00742
Opus 5.5	$0.00297	$0.00297
Sonnet 5.5	$0.00148	$0.00148
Haiku 4.5	$0.00074	$0.00074

Measured 2mo ago against content hash deac386f35f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

anytype-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Common Commands

This project uses Bun as its package manager and script runner (lockfile: bun.lock). The published artifact still targets Node.js.

Development

bun install - Install all dependencies including devDependencies
bun run dev - Start the development server with file watching (uses tsx watch)
bun run build - Build the TypeScript project and generate CLI binary (bin/cli.mjs)

Testing

bun run test - Run all tests once with Vitest
bun run test:dev - Run tests in watch mode
Run a specific test file: bunx vitest run src/openapi/__tests__/parser.test.ts

Code Quality

bun run lint - Check code formatting with ESLint
bun run lint:fix - Auto-fix formatting issues with ESLint
bun run format - Auto-fix formatting issues with Prettier
bun run typecheck - Run TypeScript type checking without emitting files

Utility Scripts

bun run parse-openapi - Parse OpenAPI specification

Architecture Overview

This is an MCP (Model Context Protocol) server that bridges Anytype's API with AI assistants. The architecture follows a proxy pattern where OpenAPI specifications are dynamically converted to MCP tools.

Core Components

MCP Proxy Layer (src/mcp/proxy.ts)

Central orchestrator that implements the MCP server protocol
Converts OpenAPI operations to MCP tools dynamically at runtime
Handles tool listing and execution through the MCP protocol
Maintains a lookup table mapping MCP tool names to OpenAPI operations

OpenAPI Parser (src/openapi/parser.ts)

Converts OpenAPI schemas to JSON Schema format for MCP compatibility
Handles $ref resolution with cycle detection
Supports multipart/form-data for file uploads
Generates MCP tool definitions from OpenAPI paths and operations

HTTP Client (src/client/http-client.ts)

Built on openapi-client-axios for OpenAPI-aware HTTP requests
Handles authentication headers from environment variables
Supports file uploads via FormData
Executes OpenAPI operations with proper parameter mapping

Read the full file on GitHub · 81 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 81 lines · 742 tokens per session scan A deac386f35f3

Subscribe to this mod's changes

anytype-mcp CLAUDE.md is an instructions file published in the GitHub repository anyproto/anytype-mcp (536 stars, last pushed 4d ago), licensed MIT. It adds 742 tokens to every session, about $0.0030 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

anytype api mcp mcp-server modelcontextprotocol

anytype-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
anytype-mcp CLAUDE.mdanyproto/anytype-mcp	Instructions file	536	4d ago	MIT	A	742	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

anytype-mcp: Instructions file for Claude Code