Lets an AI client record, transcribe, and search local meeting history stored as Markdown files.
Also known as silverstein/minutes, minutes-mcp
- Stars
- 1,605
- Tools
- 34
- Downloads, 30 days
- —
- Latest version
- 0.33.2
- Last commit
- Nov 13, 2026
- License
- MIT
What is minutes MCP?
minutes lets an AI client record, transcribe, and search local meeting history stored as Markdown files. It exposes 34 tools, such as start_recording, stop_recording, get_status.
Summary generated from the project's README
About minutes MCP server
Minutes serves as a local conversation memory layer for developers and agent-first users who want to maintain ownership of their meeting history. It allows you to record, transcribe, and search meetings, calls, and voice memos directly on your device. All records are stored as Markdown files with structured YAML frontmatter in your local ~/meetings/ directory, making them compatible with tools like Obsidian or Logseq.
Users can connect the MCP server to various AI clients such as Claude Code, Cursor, Codex, or Claude Desktop using npx. While transcription and storage happen locally to ensure privacy, any context you explicitly authorize can be sent to cloud AI providers for summarization or analysis. The system provides 34 specific tools through the MCP interface to manage these local files and 60 commands via the CLI for automation and processing.
What you can do with it
- 1Retrieve specific meeting detailsAsk your AI agent to find specific promises or updates mentioned during past discussions.
- 2Search local conversation historyUse the search tool to query your stored meeting files for specific topics.
- 3Transcribe local audio recordingsRecord a live session and then trigger the transcription process to create a text record.
- 4Integrate meeting data into workflowsConnect your meeting history to an MCP client to provide context for coding or research tasks.
Written from the project's README. Every use case is checked against a quote from it.
How to install minutes MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall minutes MCP in Claude Code
$ claude mcp add minutes -- npx -y minutes-mcpInstall minutes MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"minutes": {
"command": "npx",
"args": [
"-y",
"minutes-mcp"
]
}
}
}Install minutes MCP in VS Code
.vscode/mcp.json
{
"servers": {
"minutes": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"minutes-mcp"
]
}
}
}Install minutes MCP in VS Code CLI
$ code --add-mcp '{"name":"minutes","type":"stdio","command":"npx","args":["-y","minutes-mcp"]}'Install minutes MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"minutes": {
"command": "npx",
"args": [
"-y",
"minutes-mcp"
]
}
}
}Install minutes MCP in Codex
$ codex mcp add minutes -- npx -y minutes-mcpInstall minutes MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.minutes] command = "npx" args = ["-y", "minutes-mcp"]
Install minutes MCP in Gemini CLI
$ gemini mcp add -s user minutes npx -- -y minutes-mcpInstall minutes MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"minutes": {
"command": "npx",
"args": [
"-y",
"minutes-mcp"
]
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for minutes-mcp 0.33.2 in an isolated container with no network and no keys. It answered and listed 34 tools.
minutes MCP tools 34
Read from the server with tools/liststart_recordingActionStart recording audio with call-aware preflight. When a known call app is active, Minutes can infer call intent and block silent mic-only call captures unless explicitly allowed. Note: this server does not listen to audio content. Recordings are stopped by invoking stop_recording after the user types a request in chat — never promise the user they can speak a 'stop recording' voice command. Docs: https://useminutes.app/docs/mcp/tools#tool-start_recording
stop_recordingActionStop the current recording and process it (transcribe, diarize, summarize). Docs: https://useminutes.app/docs/mcp/tools#tool-stop_recording
get_statusRead-onlyCheck if a recording is currently in progress. Docs: https://useminutes.app/docs/mcp/tools#tool-get_status
list_processing_jobsRead-onlyList background processing jobs for recent recordings, including queued, transcript-ready, needs-review, failed, and completed work. Docs: https://useminutes.app/docs/mcp/tools#tool-list_processing_jobs
list_meetingsRead-onlyList recent meetings, voice memos, and dictations. Restricted meetings are excluded. An override requires both an operator launch grant and include_restricted=true, and is durably audited. Docs: https://useminutes.app/docs/mcp/tools#tool-list_meetings
search_meetingsRead-onlySearch meeting transcripts, voice memos, and dictations. Restricted meetings are excluded. An override requires both an operator launch grant and include_restricted=true, and is durably audited. Docs: https://useminutes.app/docs/mcp/tools#tool-search_meetings
activity_summaryRead-onlySummarize meeting-adjacent desktop context bound to one exact normal meeting source. Docs: https://useminutes.app/docs/mcp/tools#tool-activity_summary
search_contextRead-onlySearch desktop-context events bound to one exact normal meeting source. Docs: https://useminutes.app/docs/mcp/tools#tool-search_context
get_momentRead-onlyShow the local rewind bound to one exact normal meeting source. Docs: https://useminutes.app/docs/mcp/tools#tool-get_moment
get_screen_contextRead-onlyRetrieve up to three verified PNG screenshots bound to one exact normal meeting source, optionally nearest a timestamp. Docs: https://useminutes.app/docs/mcp/tools#tool-get_screen_context
consistency_reportRead-onlyFlag conflicting decisions and stale commitments across meetings using structured intent data. Meetings designated `sensitivity: restricted` are always excluded from this report. Docs: https://useminutes.app/docs/mcp/tools#tool-consistency_report
get_person_profileRead-onlyGet a relationship profile derived from live, policy-authorized meeting snapshots within the supported corpus bounds. Restricted meetings are excluded unless an operator launch grant plus include_restricted=true is durably audited. Docs: https://useminutes.app/docs/mcp/tools#tool-get_person_profile
| start_recording | Start recording audio with call-aware preflight. When a known call app is active, Minutes can infer call intent and block silent mic-only call captures unless explicitly allowed. Note: this server does not listen to audio content. Recordings are stopped by invoking stop_recording after the user types a request in chat — never promise the user they can speak a 'stop recording' voice command. Docs: https://useminutes.app/docs/mcp/tools#tool-start_recording | Action |
| stop_recording | Stop the current recording and process it (transcribe, diarize, summarize). Docs: https://useminutes.app/docs/mcp/tools#tool-stop_recording | Action |
| get_status | Check if a recording is currently in progress. Docs: https://useminutes.app/docs/mcp/tools#tool-get_status | Read-only |
| list_processing_jobs | List background processing jobs for recent recordings, including queued, transcript-ready, needs-review, failed, and completed work. Docs: https://useminutes.app/docs/mcp/tools#tool-list_processing_jobs | Read-only |
| list_meetings | List recent meetings, voice memos, and dictations. Restricted meetings are excluded. An override requires both an operator launch grant and include_restricted=true, and is durably audited. Docs: https://useminutes.app/docs/mcp/tools#tool-list_meetings | Read-only |
| search_meetings | Search meeting transcripts, voice memos, and dictations. Restricted meetings are excluded. An override requires both an operator launch grant and include_restricted=true, and is durably audited. Docs: https://useminutes.app/docs/mcp/tools#tool-search_meetings | Read-only |
| activity_summary | Summarize meeting-adjacent desktop context bound to one exact normal meeting source. Docs: https://useminutes.app/docs/mcp/tools#tool-activity_summary | Read-only |
| search_context | Search desktop-context events bound to one exact normal meeting source. Docs: https://useminutes.app/docs/mcp/tools#tool-search_context | Read-only |
| get_moment | Show the local rewind bound to one exact normal meeting source. Docs: https://useminutes.app/docs/mcp/tools#tool-get_moment | Read-only |
| get_screen_context | Retrieve up to three verified PNG screenshots bound to one exact normal meeting source, optionally nearest a timestamp. Docs: https://useminutes.app/docs/mcp/tools#tool-get_screen_context | Read-only |
| consistency_report | Flag conflicting decisions and stale commitments across meetings using structured intent data. Meetings designated `sensitivity: restricted` are always excluded from this report. Docs: https://useminutes.app/docs/mcp/tools#tool-consistency_report | Read-only |
| get_person_profile | Get a relationship profile derived from live, policy-authorized meeting snapshots within the supported corpus bounds. Restricted meetings are excluded unless an operator launch grant plus include_restricted=true is durably audited. Docs: https://useminutes.app/docs/mcp/tools#tool-get_person_profile | Read-only |
Show all 34 toolsShow fewer tools
research_topicRead-onlyResearch a topic across policy-authorized meetings within the supported corpus bounds. Restricted meetings are excluded. An override requires an operator launch grant plus include_restricted=true and is durably audited. Docs: https://useminutes.app/docs/mcp/tools#tool-research_topic
get_meetingRead-onlyGet a full meeting transcript with speaker overlays. A restricted meeting returns a stub. Full access requires an operator launch grant plus include_restricted=true and is durably audited. Docs: https://useminutes.app/docs/mcp/tools#tool-get_meeting
process_audioActionOn macOS and Linux, process a bounded WAV file from the Minutes inbox or Downloads through the transcription pipeline. Compressed/private containers and Windows fail closed without reading audio. Retained meeting-library audio is unavailable to agent surfaces. Docs: https://useminutes.app/docs/mcp/tools#tool-process_audio
add_noteActionAdd a note to the current active recording. Notes are timestamped and included in that recording's meeting summary. Existing meeting files cannot be mutated from this assistant tool. Docs: https://useminutes.app/docs/mcp/tools#tool-add_note
track_commitmentsRead-onlyList open and stale action items and explicit intent commitments from live meeting frontmatter. Optionally filter by person. Answers: 'What did I promise Sarah?' or 'What's overdue?' Meetings designated `sensitivity: restricted` never enter this live-source view. Docs: https://useminutes.app/docs/mcp/tools#tool-track_commitments
relationship_mapRead-onlyShow contacts with relationship scores, meeting frequency, and losing-touch alerts from the bounded process-private graph projection. Restricted meetings never enter the projection. Docs: https://useminutes.app/docs/mcp/tools#tool-relationship_map
start_dictationActionStart dictation mode. Speak naturally — text accumulates across pauses and the combined result is written when dictation ends. Runs until stop_dictation is called or silence timeout. Docs: https://useminutes.app/docs/mcp/tools#tool-start_dictation
stop_dictationActionStop the current dictation session. Docs: https://useminutes.app/docs/mcp/tools#tool-stop_dictation
list_voicesRead-onlyList active voice enrollments for speaker identification. Shows who has been enrolled, sample count, and model version. Docs: https://useminutes.app/docs/mcp/tools#tool-list_voices
confirm_speakerActionCompatibility registration for speaker confirmation. Agent-controlled mutation is intentionally unavailable; confirm in the Minutes app or a human CLI session so identity changes cannot race policy authorization. Docs: https://useminutes.app/docs/mcp/tools#tool-confirm_speaker
add_agent_annotationActionAppend attributed agent commentary as an agent.annotation event. This never edits meeting markdown/frontmatter and is rejected unless the agent_id is allowed in ~/.minutes/agents.allow. Docs: https://useminutes.app/docs/mcp/tools#tool-add_agent_annotation
get_agent_annotationsRead-onlyCompatibility name only: unavailable in MCP because an annotation's source pointer and body are both author-supplied, so revalidating the pointer cannot bound what the body discloses. Docs: https://useminutes.app/docs/mcp/tools#tool-get_agent_annotations
get_meeting_insightsRead-onlyQuery structured insights extracted from meetings, decisions, commitments and questions with confidence levels. Each insight records a path to the meeting it was derived from; that path is resolved to a meeting in the live corpus, and the resolved meeting is re-read from disk and re-verified against the live sensitivity policy before the insight is released. A path that cannot be resolved into this corpus is withheld. Released records carry the source title and path as they were recorded, which may name a location outside this corpus. Withheld records are reported as a partial view rather than an empty one. Docs: https://useminutes.app/docs/mcp/tools#tool-get_meeting_insights
start_copilotActionStart the independent Minutes real-time copilot for a goal. This launches `minutes copilot start`; MCP does not run model inference, own capture, or need to stay connected for the engine to produce nudges. The stdout surface is recommended for complete structured nudge observation. Docs: https://useminutes.app/docs/mcp/tools#tool-start_copilot
stop_copilotActionRequest that the active Minutes copilot stop. This invokes `minutes copilot stop` and never stops recording or live transcription. Calling it while no copilot is active returns a calm not-active status. Docs: https://useminutes.app/docs/mcp/tools#tool-stop_copilot
copilot_statusRead-onlyRead the current operational copilot state from the strict `minutes copilot status --json` contract. This is observation only and returns a clear Off/not-active payload when no engine is running. Docs: https://useminutes.app/docs/mcp/tools#tool-copilot_status
read_copilot_nudgesRead-onlyRead nudges observed from the active real CLI copilot stream. Use cursor (or a numeric since value) for lossless delta reads; since also accepts durations such as '5m'/'30s' and ISO timestamps. MCP never generates nudges itself. Docs: https://useminutes.app/docs/mcp/tools#tool-read_copilot_nudges
start_live_transcriptActionStart real-time transcription. If a recording is already running, it already includes a live transcript — use read_live_transcript to read it. Runs until stop is called. Docs: https://useminutes.app/docs/mcp/tools#tool-start_live_transcript
read_live_transcriptRead-onlyRead the live transcript — works during both recordings and live transcript sessions. Use 'since' to get new finalized lines after a cursor (line number) or time window (e.g., '5m', '30s'). Set include_current for one fresh, clearly provisional current-speech draft. Use 'status' mode to check if a session is active. Docs: https://useminutes.app/docs/mcp/tools#tool-read_live_transcript
ingest_meetingActionExtract facts from a meeting and update the knowledge base (person profiles, log, index). Requires [knowledge] to be configured in config.toml. Uses structured frontmatter data only by default (zero hallucination risk). Set engine to 'agent' for richer LLM-based extraction. Docs: https://useminutes.app/docs/mcp/tools#tool-ingest_meeting
resummarize_meetingActionRe-run the AI pass (summary, action items, decisions) on an edited meeting or memo. Preview by default: returns the regenerated content WITHOUT writing — note the summarization model IS still invoked (cost applies even in preview). Set apply=true to write the file (a timestamped backup is created and derived views — graph, search index, vault, QMD — refresh automatically). User edits outside AI-owned sections are never touched; checked action items and decision notes are carried forward by the merge. Docs: https://useminutes.app/docs/mcp/tools#tool-resummarize_meeting
knowledge_statusActionReconcile persistent meeting derivatives and show the privacy-safe knowledge-base status. This cleanup/status tool cannot create or register an external index. Docs: https://useminutes.app/docs/mcp/tools#tool-knowledge_status
| research_topic | Research a topic across policy-authorized meetings within the supported corpus bounds. Restricted meetings are excluded. An override requires an operator launch grant plus include_restricted=true and is durably audited. Docs: https://useminutes.app/docs/mcp/tools#tool-research_topic | Read-only |
| get_meeting | Get a full meeting transcript with speaker overlays. A restricted meeting returns a stub. Full access requires an operator launch grant plus include_restricted=true and is durably audited. Docs: https://useminutes.app/docs/mcp/tools#tool-get_meeting | Read-only |
| process_audio | On macOS and Linux, process a bounded WAV file from the Minutes inbox or Downloads through the transcription pipeline. Compressed/private containers and Windows fail closed without reading audio. Retained meeting-library audio is unavailable to agent surfaces. Docs: https://useminutes.app/docs/mcp/tools#tool-process_audio | Action |
| add_note | Add a note to the current active recording. Notes are timestamped and included in that recording's meeting summary. Existing meeting files cannot be mutated from this assistant tool. Docs: https://useminutes.app/docs/mcp/tools#tool-add_note | Action |
| track_commitments | List open and stale action items and explicit intent commitments from live meeting frontmatter. Optionally filter by person. Answers: 'What did I promise Sarah?' or 'What's overdue?' Meetings designated `sensitivity: restricted` never enter this live-source view. Docs: https://useminutes.app/docs/mcp/tools#tool-track_commitments | Read-only |
| relationship_map | Show contacts with relationship scores, meeting frequency, and losing-touch alerts from the bounded process-private graph projection. Restricted meetings never enter the projection. Docs: https://useminutes.app/docs/mcp/tools#tool-relationship_map | Read-only |
| start_dictation | Start dictation mode. Speak naturally — text accumulates across pauses and the combined result is written when dictation ends. Runs until stop_dictation is called or silence timeout. Docs: https://useminutes.app/docs/mcp/tools#tool-start_dictation | Action |
| stop_dictation | Stop the current dictation session. Docs: https://useminutes.app/docs/mcp/tools#tool-stop_dictation | Action |
| list_voices | List active voice enrollments for speaker identification. Shows who has been enrolled, sample count, and model version. Docs: https://useminutes.app/docs/mcp/tools#tool-list_voices | Read-only |
| confirm_speaker | Compatibility registration for speaker confirmation. Agent-controlled mutation is intentionally unavailable; confirm in the Minutes app or a human CLI session so identity changes cannot race policy authorization. Docs: https://useminutes.app/docs/mcp/tools#tool-confirm_speaker | Action |
| add_agent_annotation | Append attributed agent commentary as an agent.annotation event. This never edits meeting markdown/frontmatter and is rejected unless the agent_id is allowed in ~/.minutes/agents.allow. Docs: https://useminutes.app/docs/mcp/tools#tool-add_agent_annotation | Action |
| get_agent_annotations | Compatibility name only: unavailable in MCP because an annotation's source pointer and body are both author-supplied, so revalidating the pointer cannot bound what the body discloses. Docs: https://useminutes.app/docs/mcp/tools#tool-get_agent_annotations | Read-only |
| get_meeting_insights | Query structured insights extracted from meetings, decisions, commitments and questions with confidence levels. Each insight records a path to the meeting it was derived from; that path is resolved to a meeting in the live corpus, and the resolved meeting is re-read from disk and re-verified against the live sensitivity policy before the insight is released. A path that cannot be resolved into this corpus is withheld. Released records carry the source title and path as they were recorded, which may name a location outside this corpus. Withheld records are reported as a partial view rather than an empty one. Docs: https://useminutes.app/docs/mcp/tools#tool-get_meeting_insights | Read-only |
| start_copilot | Start the independent Minutes real-time copilot for a goal. This launches `minutes copilot start`; MCP does not run model inference, own capture, or need to stay connected for the engine to produce nudges. The stdout surface is recommended for complete structured nudge observation. Docs: https://useminutes.app/docs/mcp/tools#tool-start_copilot | Action |
| stop_copilot | Request that the active Minutes copilot stop. This invokes `minutes copilot stop` and never stops recording or live transcription. Calling it while no copilot is active returns a calm not-active status. Docs: https://useminutes.app/docs/mcp/tools#tool-stop_copilot | Action |
| copilot_status | Read the current operational copilot state from the strict `minutes copilot status --json` contract. This is observation only and returns a clear Off/not-active payload when no engine is running. Docs: https://useminutes.app/docs/mcp/tools#tool-copilot_status | Read-only |
| read_copilot_nudges | Read nudges observed from the active real CLI copilot stream. Use cursor (or a numeric since value) for lossless delta reads; since also accepts durations such as '5m'/'30s' and ISO timestamps. MCP never generates nudges itself. Docs: https://useminutes.app/docs/mcp/tools#tool-read_copilot_nudges | Read-only |
| start_live_transcript | Start real-time transcription. If a recording is already running, it already includes a live transcript — use read_live_transcript to read it. Runs until stop is called. Docs: https://useminutes.app/docs/mcp/tools#tool-start_live_transcript | Action |
| read_live_transcript | Read the live transcript — works during both recordings and live transcript sessions. Use 'since' to get new finalized lines after a cursor (line number) or time window (e.g., '5m', '30s'). Set include_current for one fresh, clearly provisional current-speech draft. Use 'status' mode to check if a session is active. Docs: https://useminutes.app/docs/mcp/tools#tool-read_live_transcript | Read-only |
| ingest_meeting | Extract facts from a meeting and update the knowledge base (person profiles, log, index). Requires [knowledge] to be configured in config.toml. Uses structured frontmatter data only by default (zero hallucination risk). Set engine to 'agent' for richer LLM-based extraction. Docs: https://useminutes.app/docs/mcp/tools#tool-ingest_meeting | Action |
| resummarize_meeting | Re-run the AI pass (summary, action items, decisions) on an edited meeting or memo. Preview by default: returns the regenerated content WITHOUT writing — note the summarization model IS still invoked (cost applies even in preview). Set apply=true to write the file (a timestamped backup is created and derived views — graph, search index, vault, QMD — refresh automatically). User edits outside AI-owned sections are never touched; checked action items and decision notes are carried forward by the merge. Docs: https://useminutes.app/docs/mcp/tools#tool-resummarize_meeting | Action |
| knowledge_status | Reconcile persistent meeting derivatives and show the privacy-safe knowledge-base status. This cleanup/status tool cannot create or register an external index. Docs: https://useminutes.app/docs/mcp/tools#tool-knowledge_status | Action |
Automated checks
Ran Nov 16, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablesilverstein/minutes is public and reachablegithub.com/silverstein/minutes ↗Pass
- Package names this repository as its sourceminutes-mcp names silverstein/minutes as sourcenpmjs.com/package/minutes-mcp ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for minutes-mcpnpmjs.com/package/minutes-mcp/v/0.33.2#provenance ↗Pass
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/silverstein/minutes ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from minutes-mcpPass
- No critical advisory in the package or its dependenciesthe package checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model34 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubminutes
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.
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.
On Linux x86-64, follow the prebuilt CLI quickstart for Ubuntu 24.04 or a compatible distribution. The same guide covers building from source on older distributions.
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, we recommend Node.js 22. Add the MCP server 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 Da5id promise about the rendering pipeline, and did he deliver?
Da5id promised a fix by Friday in Metaverse Infrastructure Standup. In Intel Debrief, Hiro reported that the fix still hadn't landed.
A direct MCP call uses the same local meeting files:
search_meetings({"query":"rendering pipeline"})
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
| Workflow | Granola | Otter.ai | Anarlog (formerly Hyprnote) | Minutes |
|---|---|---|---|---|
| Product | Hosted meeting notepad | Hosted meeting assistant | Local meeting notepad | Local conversation memory |
| Agent access | Hosted MCP | Hosted integrations | CLI + MCP | Local files, MCP, CLI, SDK |
| Primary storage | Hosted workspace | Hosted workspace | Local SQLite + files | Local Markdown + YAML |
| Local AI | Cloud transcription | Cloud transcription | With local providers | Local 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
| Surface | What it provides | Docs |
|---|---|---|
| Desktop app | Menu bar capture, dictation, Recall, documents, and Coach. | Install |
| CLI (60 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 |
| SDK | TypeScript access to meeting files without MCP. | Agent architecture |
Dictation
The desktop Dictation settings bring writing preferences, personal spellings and snippets, microphone selection, and recent text together. Cursor context is optional and stays on the Mac. Recovery restores text for review; local edits use an explicit Ollama preview, and spelling corrections require confirmation.
See dictation behavior and evaluation boundaries for supported fields, safe insertion and undo, clipboard restoration, and the synthetic benchmark.
Voice Live
Voice Live's optional local-agent handoff prepares bounded recent dialogue and already-shared evidence while you talk. The exact context is included in the existing local review before dispatch. It uses your configured agent CLI and authentication; context preparation needs no OpenAI API key or model request. See voice delegation context for disclosure, truncation, and verification boundaries.
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
- Features and commands
- Install, setup, updating, and troubleshooting
- Agent and MCP client integrations
- Phone voice memo pipeline
- Summarization and automation
- Configuration
- Architecture and agent development
- Evidence, retrieval, and decision-history contracts
- Recall and speech evaluation
- Switching from Granola and importing archives
- Frontmatter schema
- Security
- Personas
- Native call capture recovery (
minutes recover-stem) - Opt-in automatic call recording for Teams and Zoom desktop on macOS
- MCP tools
- Error reference
- Agent index
- Full agent index
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
minutes MCP questions
How do I add minutes MCP to Claude Code?
Run claude mcp add minutes -- npx -y minutes-mcp in your terminal. Add --scope user to make it available in every project.
How do I add minutes MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does minutes MCP provide?
It exposes 34 tools, including start_recording, stop_recording, get_status, list_processing_jobs, list_meetings.
Where are my meeting records stored?
Your records are stored locally on your device as Markdown files in the ~/meetings/ directory.
Does transcription happen in the cloud?
No, capture, transcription, and storage run locally on your device.
How can I add Minutes to my AI agent?
You can add it using the command claude mcp add minutes -- npx -y minutes-mcp or by running npx minutes-mcp in other MCP clients.
Is the data sent to cloud providers?
Text only leaves your machine if you explicitly authorize sending meeting context to a cloud AI assistant or summarizer.