What is GranolaMCP CLAUDE.md?

Repository instructions for GranolaMCP, a Python library that reads Granola meeting data and exposes it through command-line commands and an MCP server.

Use it when developing, testing, packaging, or running GranolaMCP to list meetings, view transcripts, export data, or start its MCP server.

It documents installation, commands, packaging, and the code layers needed to work with meeting records and transcripts.

How pedramamini/GranolaMCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to pedramamini/GranolaMCP. 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/pedramamini/GranolaMCP/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/pedramamini/GranolaMCP

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/pedramamini/granolamcp/claude-md/github.svg)](https://agentmods.dev/instructions/pedramamini/granolamcp/claude-md)

Your own site

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

Per session 831 This file is loaded in full into every session.

When invoked 831 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	$0.00831	$0.00831
Opus 5.5	$0.00332	$0.00332
Sonnet 5.5	$0.00166	$0.00166
Haiku 4.5	$0.00083	$0.00083

Measured 2mo ago against content hash f50c146240a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

GranolaMCP 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 · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 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

GranolaMCP is a Python library providing programmatic access to Granola.ai meeting data with zero external dependencies. It offers three main interfaces: Core Foundation (JSON parsing, timezone conversion), CLI Tools (5 commands), and MCP Server (8 tools for LLM integration).

Development Commands

Installation & Setup

# Install in development mode
pip install -e .

# Test installation
python -c "import granola_mcp; print(granola_mcp.__version__)"

Running the Application

# CLI usage (after installation)
granola list --last 7d
granola show <meeting-id> --transcript
granola export <meeting-id>

# CLI usage (development)
python -m granola_mcp.cli.main list --last 7d

# MCP server
python -m granola_mcp.mcp --debug

Building & Packaging

# Build package
python setup.py sdist bdist_wheel

Architecture

The codebase follows a modular architecture with three main layers:

granola_mcp/core/ - Core data parsing and models
- parser.py - Handles Granola's nested JSON cache structure with double parsing
- meeting.py - Meeting data model with timezone conversion (UTC to CST)
- transcript.py - Transcript processing and speaker identification
- timezone_utils.py - UTC to CST conversion using Python's zoneinfo
granola_mcp/cli/ - Command-line interface with 5 commands
- commands/ - Individual CLI commands (list, show, export, stats, json)
- formatters/ - Output formatting with colors, tables, ASCII charts
granola_mcp/mcp/ - MCP Server for LLM integration
- server.py - JSON-RPC STDIO server implementation
- tools.py - 8 MCP tools for comprehensive meeting data access

Key Technical Details

Data Source Structure

Granola cache files require double JSON parsing due to nested structure:

data = json.loads(open("cache-v3.json").read())
cache = json.loads(data['cache'])
meetings = cache['state']['documents']
transcripts = cache['state']['transcripts']

Read the full file on GitHub · 93 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 · 93 lines · 831 tokens per session scan A f50c146240a1

Subscribe to this mod's changes

GranolaMCP CLAUDE.md is an instructions file published in the GitHub repository pedramamini/GranolaMCP (47 stars, last pushed 1y ago), licensed Apache-2.0. It adds 831 tokens to every session, about $0.0033 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.

Backend and APIs

GranolaMCP CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
GranolaMCP CLAUDE.mdpedramamini/GranolaMCP	Instructions file	47	1y ago	Apache-2.0	A	831	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	yesterday	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

GranolaMCP: Instructions file for Claude Code