mcp_granola

mcp_granola is a skill for Claude Code, Codex from NimbleBrainInc/mcp-granola. It costs 0 tokens per session (1,210 once invoked), scanned A, original, MIT.

A skill guide for using the Granola meeting-notes MCP server. It explains how to find meetings, retrieve notes or transcripts, review attendees, summarize meetings, and extract action items, using the meetingid from search results.

In plain words
What is it for?
It is for browsing and searching meeting history, opening full notes or transcripts, finding meetings by person, creating recaps, and collecting follow-up tasks.
Why use it?
It prevents requests from failing because the wrong identifier or parameter name is used when working with meeting data.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for browsing and searching meeting history, opening full notes or transcripts, finding meetings by person, creating recaps, and collecting follow-up tasks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nimblebraininc/mcp-granola/mcp_granola
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.

Any agent
npx skills add NimbleBrainInc/mcp-granola --skill mcp_granola
Clone the repo
git clone --depth 1 https://github.com/NimbleBrainInc/mcp-granola

Made for: Claude Code, Codex.

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.

agentmods badge for mcp_granola

README.md
[![agentmods](https://agentmods.dev/badge/skills/nimblebraininc/mcp-granola/mcp_granola/github.svg)](https://agentmods.dev/skills/nimblebraininc/mcp-granola/mcp_granola)
Your own site
<a href="https://agentmods.dev/skills/nimblebraininc/mcp-granola/mcp_granola"><img src="https://agentmods.dev/badge/skills/nimblebraininc/mcp-granola/mcp_granola/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.

agentmods 80×15 button for mcp_granola

Your own site · 80×15
<a href="https://agentmods.dev/skills/nimblebraininc/mcp-granola/mcp_granola"><img src="https://agentmods.dev/badge/skills/nimblebraininc/mcp-granola/mcp_granola.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,210 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01210
Opus 5 $0.00000 $0.00605
Sonnet 5 $0.00000 $0.00242
Haiku 4.5 $0.00000 $0.00121

Measured 12d ago against content hash ed33b024de01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

mcp_granola 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 12d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (__init__.py, data.py, models.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

src/mcp_granola/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Granola MCP Server — Skill Guide

Tools

Tool Use when...
list_meetings You need to browse recent meetings or paginate through history
search_meetings You have a keyword or phrase to search across all meeting notes
search_by_person You want all meetings involving a specific person (by name or email)
get_meeting You have a meeting_id and need the full notes, attendees, and panels
get_transcript You need the raw transcript segments for a specific meeting
get_meeting_stats You need an overview of how much data is available
summarize_meetings You need a recap of meetings over a time period (returns notes + attendees)
extract_action_items You need TODOs, next steps, or action items from one or more meetings

Parameter Reference

All tools that accept meeting identifiers use meeting_id (not doc_id, id, or document_id). The meeting_id value comes from the id field in search results and meeting lists.

Date Parameters

Tools that accept time ranges (summarize_meetings, extract_action_items, list_meetings, search_meetings, search_by_person) support two ways to specify dates:

  • date_from / date_to (YYYY-MM-DD): Explicit date range. Use when the user asks for a calendar-aligned period. Compute the actual YYYY-MM-DD dates yourself.
  • days (integer, summarize_meetings and extract_action_items only): Shortcut for "last N days from today". Use when the user says "recent" or "last N days".

If neither is provided, summarize_meetings and extract_action_items default to the last 7 days.

Examples of how to translate user requests:

  • "What happened last week?" → compute Monday–Sunday dates, use date_from/date_to
  • "Summarize my last 30 days" → use days=30
  • "Action items from January" → use date_from="2026-01-01", date_to="2026-01-31"
  • "What did I discuss with Carol recently?" → use days=14 with person="Carol"

Context Reuse

Read the full file on GitHub · 85 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 12d ago First seen · 85 lines · 0 tokens per session scan A ed33b024de01

Subscribe to this mod's changes

mcp_granola is a skill published in the GitHub repository NimbleBrainInc/mcp-granola (0 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,210 tokens. 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 2026-08-31.

Related

Other skills, from other repositories

minutes-record

Start or stop recording a meeting, call, or voice memo. Use this whenever the user says "record", "start recording", "capture this meeting", "stop recording", "I'm in a meeting", "take notes on this call", or wants to transcribe live audio. Also use when they ask about recording status or want to know if something is…

silverstein/minutes · 77 tokens

minutes-note

Add a note to the current recording or annotate a past meeting. Use whenever the user says "note that", "remember this", "mark this as important", "add a note about", "annotate the meeting", or wants to capture a thought during or after a recording. Plain text input — no markdown needed.

silverstein/minutes · 67 tokens

granola-to-steno

Sync Granola meeting notes into Steno's file-based store. Reads recent meetings from the Granola MCP (titles, dates, participants, AI summaries, verbatim transcripts) and regenerates Steno's output/summary.md and transcripts/transcript.txt files in a target folder (e.g. an iCloud Drive directory). The operation is…

stenolabs/stenoai · 163 tokens

granola

Access and process Granola meeting notes and transcripts via the granola CLI (MCP-backed). Use when pulling meeting data, analyzing transcripts, backfilling meetings, or any task involving Granola meeting content.

joelhooks/joelclaw · 45 tokens

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

ppt-template-creator

Creates self-contained PPT template SKILLS (not presentations) from user-provided PowerPoint templates. Use ONLY when a user wants to create a reusable skill from their template. For creating actual presentations, use the pptx skill instead.

anthropics/financial-services · 51 tokens