bear-notes-mcp CLAUDE.md

Project instructions for an MCP server that connects AI coding tools to Bear Notes, a note-taking app. They describe the server's purpose, structure, rules, and tests.

In plain words
What is it for?
Understanding the Bear Notes connection, managing dependencies, choosing system tests, and navigating the source and documentation.
Why use it?
They give an AI agent the project context and important working rules before it changes the code.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/vasylenko/bear-notes-mcp/claude-md
Clone the repo
git clone --depth 1 https://github.com/vasylenko/bear-notes-mcp
Per session 1,025 This file is loaded in full into every session.
When invoked 1,025 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.01025 $0.01025
Opus 5 $0.00513 $0.00513
Sonnet 5 $0.00205 $0.00205
Haiku 4.5 $0.00103 $0.00103

Measured 3d ago against content hash 137b1759dc34, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bear-notes-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 3d 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Purpose

MCP server for Bear Notes, distributed through two channels:

  • MCP Bundle (.mcpb) — a one-click installable extension for Claude Desktop. MCP Bundles are zip archives containing a local MCP server and a manifest.json, similar to Chrome extensions (.crx) or VS Code extensions (.vsix).
  • npm package (bear-notes-mcp) — a standalone MCP server for Claude Code, Cursor, Codex, and any other MCP client.

Rules of Absolute Importance

  • All project dependencies must be managed ONLY through their respective CLI tools, and NEVER through editing package lock files.
  • Tests:
    • System tests are the default. Unit tests are justified only when a situation is genuinely hard to recreate via system tests due to test setup complexity. Unit tests are a last resort.
    • If the assertion is about something the server decided before calling Bear (input validation, schema rejection, response format with no Bear interaction), it's almost always a misplaced unit test. System tests should verify behavior at the Bear-integration boundary — anything else is paying the spawn-Inspector / open-Bear cost for no integration risk.
    • Exception: when an input composition step is exhaustively unit-tested AND one system test exercises the URL roundtrip, additional system tests covering other input shapes are redundant — Bear's URL boundary doesn't discriminate between composed strings.

Core Technical Documentation for this project

Source Layout

src/ is layered as infra → operations → tools. Adapters to external systems (SQLite, filesystem, Bear URL scheme) live in infra/; pure business logic in operations/; MCP tool registrations and handlers in tools/. Dependencies flow downward only — tools/ may import from operations/ and infra/, operations/ from infra/, never the reverse. Tests are co-located with their source files using the .test.ts suffix. Use find src -type f for the current file list; the rules above are what's load-bearing.

Read the full file on GitHub · 53 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.

  1. 3d ago First seen · 53 lines · 1,025 tokens per session scan A 137b1759dc34

Subscribe to this mod's changes

bear-notes-mcp CLAUDE.md is an instructions file published in the GitHub repository vasylenko/bear-notes-mcp (206 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,025 tokens to every session, about $0.0051 per session on Opus 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.