Borrowing it
Nothing to install: this file belongs to proofsh/granola-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/proofsh/granola-mcp-server/main/CLAUDE.mdgit clone --depth 1 https://github.com/proofsh/granola-mcp-serverWrote 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.
[](https://agentmods.dev/instructions/proofsh/granola-mcp-server/claude-md)<a href="https://agentmods.dev/instructions/proofsh/granola-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/proofsh/granola-mcp-server/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.
<a href="https://agentmods.dev/instructions/proofsh/granola-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/proofsh/granola-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00770 | $0.00770 |
| Opus 5.5 | $0.00308 | $0.00308 |
| Sonnet 5.5 | $0.00154 | $0.00154 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
granola-mcp-server 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.
How it starts
The opening of the file, as written. The whole thing — 65 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.
Project Overview
MCP server that exposes Granola.ai meeting data (notes, transcripts, participants) to AI assistants. It reads directly from Granola's local cache file (~/Library/Application Support/Granola/cache-v*.json) — no API keys needed, macOS only. The server auto-detects the highest available cache version (v6, v4, v3, etc.) via glob.
Commands
# Run the server
uv run granola-mcp-server
# Run unit tests (synthetic cache data)
uv run python test_server.py
# Run integration tests (requires Granola desktop app with real cache)
uv run python test_real_cache.py
# Install dependencies
uv sync
Architecture
Single-server design — almost all logic lives in granola_mcp_server/server.py (~760 lines):
GranolaMCPServerclass: Handles cache loading, data parsing, tool dispatch, and response formattingmodels.py: Pydantic models (CacheData,MeetingMetadata,MeetingDocument,MeetingTranscript) — thin data containers only- Entry point:
main()at bottom ofserver.py, registered asgranola-mcp-serverCLI via pyproject.toml
MCP Tools (5 total, defined in _setup_handlers)
| Tool | Purpose |
|---|---|
search_meetings |
Keyword search across titles, participants, transcripts with relevance scoring |
get_meeting_details |
Full meeting info by ID (notes, participants, time) |
get_meeting_transcript |
Raw transcript with speaker attribution |
get_meeting_documents |
Document/notes content for a meeting |
analyze_meeting_patterns |
Aggregate analysis: topics, participants, or frequency |
Cache Parsing Pipeline
Granola's cache format has evolved across versions. In v3 (cache-v3.json), the cache key contains a JSON string (double-encoded). In v4+ (cache-v4.json, cache-v6.json, etc.), the cache key is a dict directly. The server auto-detects the highest available cache version via glob and handles both formats. The parsing flow:
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 · 65 lines · 770 tokens per session scan A 3315f7f81602
granola-mcp-server CLAUDE.md is an instructions file published in the GitHub repository proofsh/granola-mcp-server (94 stars, last pushed 5mo ago), licensed MIT. It adds 770 tokens to every session, about $0.0031 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.
granola-mcp-server CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| granola-mcp-server CLAUDE.mdproofsh/granola-mcp-server | Instructions file | 94 | 5mo ago | MIT | A | 770 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |