PluginBench
MCP Server
Active
MIT

io.github.silverstein/minutes MCP Server

io.github.silverstein/minutes

Local conversation memory for AI: record, transcribe, and search meetings you own.

What is the io.github.silverstein/minutes MCP server?

Minutes is a free, open-source conversation memory app that records and transcribes meetings, calls, and voice memos locally, then lets Claude, Cursor, and other MCP clients search your meeting history. Your records are Markdown files stored in ~/meetings/ that you fully own and control.

Minutes captures audio locally on your device, transcribes it, and stores meetings as searchable Markdown files with structured metadata. You can then ask Claude, Cursor, or other AI agents to search and recall meeting context. It's designed for agent-first users building a local second brain, with privacy-first architecture where transcription and storage happen on-device.

How to install io.github.silverstein/minutes

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "minutes": {
      "command": "npx",
      "args": [
        "-y",
        "minutes-mcp"
      ]
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • search_meetings — Search meeting history by query to find decisions, action items, and context across multiple meetings.
  • list_meetings — List available meetings with metadata including title, date, duration, and status.
  • get_meeting — Retrieve full content of a specific meeting including transcript and frontmatter.
  • create_meeting — Create a new meeting record with title, context, and metadata.
  • update_meeting — Update meeting details, action items, decisions, and other frontmatter fields.
  • add_note — Add notes or context to an existing meeting.
  • export_meeting — Export meeting content in various formats for external use.

Use cases

  • Ask Claude or Cursor to recall decisions made across multiple meetings over time
  • Search meeting history to find action items assigned to specific people with due dates
  • Build a searchable archive of all your calls and voice memos without cloud storage
  • Integrate meeting context into your AI-powered workflows and second brain
  • Transcribe phone calls and voice memos locally while maintaining full privacy

io.github.silverstein/minutes MCP server FAQ

What is Minutes?

Minutes is a free, open-source app that records and transcribes meetings locally on your device, then lets AI agents like Claude and Cursor search your meeting history. All your data stays in Markdown files you own.

Is Minutes free?

Yes, Minutes is completely free and open-source under the MIT license. There is no paid tier for any features in the repository.

How do I install Minutes in Cursor or Claude?

For Claude Desktop or Cursor, run: `claude mcp add minutes -- npx -y minutes-mcp`. For other MCP clients, use `npx minutes-mcp`. You can also install the desktop app via Homebrew or the CLI via Cargo.

Does Minutes require authentication or cloud services?

No. Transcription and storage run entirely on your device. Text only leaves your machine if you explicitly send authorized meeting context to a cloud AI assistant or summarizer.

What file format does Minutes use?

Meetings are stored as plain Markdown files with structured YAML frontmatter containing metadata like title, date, duration, action items, and decisions. Files work with Obsidian, Logseq, grep, and any Markdown tool.

Which AI agents and clients does Minutes work with?

Minutes works with Claude Code, Cursor, Codex, OpenCode, Pi, Gemini CLI, Claude Desktop, Mistral Vibe, Cowork, Dispatch, and any MCP client. It also integrates with Obsidian and Logseq.

README (reference)

Source of truth, from the repository.

minutes

GitHub stars License: MIT crates.io npm

useminutes.app

Minutes is a free, open-source conversation memory app for the AI you already use. Record and transcribe meetings, calls, voice memos, and dictation on your device, then let Claude Code, Codex, Cursor, or another MCP client search the history you choose to share. Your records are Markdown files you own in ~/meetings/.

Capture, transcription, and storage run locally. If you choose a cloud AI assistant or summarizer, the meeting context you authorize is sent to that provider.

Your conversations. Your memory. Ready for the AI you use.

<p align="center"> <img src="docs/assets/demo.gif" alt="minutes demo; record, dictate, phone sync, AI recall" width="750"> </p>

Install

Choose the desktop app or one standalone CLI installation. The desktop app includes a CLI: use About Minutes → Set up CLI to add it to your PATH.

brew install --cask silverstein/tap/minutes  # Desktop app, with bundled CLI
brew install silverstein/tap/minutes         # Standalone CLI alternative
cargo install minutes-cli                   # Standalone CLI via Cargo

For an agent connection, add the MCP server separately with claude mcp add minutes -- npx -y minutes-mcp (or run npx minutes-mcp from another MCP client).

If Homebrew reports an untrusted tap, run brew trust silverstein/tap once.

Ask your agent

Add Minutes to your agent, seed five sample meetings (no mic needed), then ask about them:

claude mcp add minutes -- npx -y minutes-mcp
minutes demo --full

What did we decide about monthly billing, and did it stick?

The answer spans two meetings a month apart: launched on Feb 28, reversed on Mar 25.

A direct MCP call uses the same local meeting files:

search_meetings({"query":"monthly billing decision"})

Record a real one with minutes record, then minutes stop to transcribe. minutes demo --clean removes the samples. Setup: Codex, Gemini CLI, and Claude Desktop, Cursor, OpenCode, Pi, Mistral Vibe, and Cowork or Dispatch.

Works with

Claude Code · Codex · Cursor · OpenCode · Pi · Gemini CLI · Claude Desktop · Mistral Vibe · Cowork · Dispatch · Obsidian · Logseq · any MCP client

How it compares

WorkflowGranolaOtter.aiAnarlog (formerly Hyprnote)Minutes
ProductHosted meeting notepadHosted meeting assistantLocal meeting notepadLocal conversation memory
Agent accessHosted MCPHosted integrationsCLI + MCPLocal files, MCP, CLI, SDK
Primary storageHosted workspaceHosted workspaceLocal SQLite + filesLocal Markdown + YAML
Local AICloud transcriptionCloud transcriptionWith local providersLocal transcription; AI provider of your choice

Reviewed September 5, 2026 against Granola MCP, Otter privacy and security, and the Anarlog repository. Anarlog's community app is MIT; its enterprise components use a commercial license. See the detailed comparison and open-source alternatives for fit and limitations.

Who it's for

Agent-first users treat Minutes as the capture layer of a local second brain. They search meetings through Claude Code, Cursor, Codex, OpenCode, MCP, or the CLI, then fold useful context into a vault or wiki they own.

Desktop notetaker users record and read results in the app. They value reliable setup, clear processing and recovery, Recall, documents, Coach, and summary quality. See the full persona notes.

Surfaces

SurfaceWhat it providesDocs
Desktop appMenu bar capture, Recall, documents, and Coach.Install
CLI (58 commands)Local recording, processing, search, import, and automation.Commands
MCP server (34 tools)Local meeting tools and resources for any MCP client.MCP reference
Claude Code plugin (23 skills)Prep, capture, live help, debrief, and memory workflows.Client setup
SDKTypeScript access to meeting files without MCP.Agent architecture

Output format

Meetings are plain markdown with structured YAML frontmatter:

---
title: Q2 Pricing Discussion with Alex
type: meeting
date: 2026-03-17T14:00:00
duration: 42m
context: Discuss Q2 pricing
action_items:
  - assignee: mat
    task: Send pricing doc
    due: Friday
    status: open
decisions:
  - text: Test monthly billing with 10 advisors
---

See the frontmatter schema. Files work with Obsidian, grep, and any markdown tool.

Privacy & consent

  • Transcription and speaker processing run on-device. Audio stays on your machine.
  • Sensitive meetings save typed markers without audio and default to restricted.
  • Consent reminders, acknowledgement, and provenance help you disclose recording.
  • Text leaves the machine only when you send authorized context to a cloud agent or summarizer.

See the security documentation and consent enforcement design.

Docs

Contributing

See CONTRIBUTING.md. Minutes is MIT licensed and staying that way: no relicensing, no paid tier for anything in this repo.

MIT. Built by Mat Silverstein, founder of X1 Wealth.

Star History

Star History Chart

Related MCP servers

Git-native project memory for AI assistants with enterprise-grade audit compliance

1
Python
Apache-2.0
View repository →

Search 500+ Toronto Tech Week 2026 events by date, theme, audience, format, and neighborhood.

View repository →

Simlir MCP server for semantic product search, visual search, and exact product lookup.

View repository →

A plug-and-play MCP Server for automated, low-cost C2PA provenance stamping via Base L2.

Flight price comparison MCP server. Search multiple booking sources to find better flight prices.

0
JavaScript
View repository →
KWKwork logo

Kwork

Active

Account-bound, typed and durable stdio MCP gateway for the Kwork freelance marketplace

3
Python
MIT
View repository →