SeaMeet MCP
SeaMeet MCP connects Claude, Cursor, Codex, and other AI agents to SeaMeet meeting recordings, transcripts, AI summaries, screenshots, action items, webhooks, and desktop recording controls. Use it to search meeting memory, read synced cloud recordings, and automate meeting notes through the Model Context Protocol.
README
@seameet/mcp
The SeaMeet MCP server β let AI agents record, transcribe, and mine your meetings. One install works whether or not you have the desktop app, in Claude Code, Claude Desktop, Codex, Antigravity, Cursor, OpenCode, GitHub Copilot CLI, Windsurf, and any MCP client.
It picks the richest available backend automatically and exposes the union of both:
- Desktop mode β when the SeaMeet desktop app is running, agents get the full recorder toolset (start/stop recordings, screenshots, live transcript, AI artifacts, search). No auth; nothing leaves your machine.
- Cloud mode β when the app isn't there, agents read your synced library (recordings, transcripts, summaries) and manage webhooks over the network. Authorized by logging into the web app β no key copy/paste, works on a headless terminal.
tools/list returns the superset of whatever's available; call seameet_status any time to see the current mode(s).
What you can do
ποΈ Record & capture (desktop mode)
- Start a recording β microphone, screen, or screen + system audio β
seameet_start_recording - Stop β
seameet_stop_recordingΒ· pause/resume audio-only βseameet_pause_recording/seameet_resume_recording - Check recording status β
seameet_recording_statusΒ· read the live transcript mid-recording βseameet_get_live_transcript - Take a screenshot through SeaMeet β
seameet_take_screenshot
π Work with recordings (desktop = local files Β· cloud = synced library)
- List recordings & screenshots β
seameet_list_recordingsΒ· browse files in the save directory βseameet_list_filesΒ· app settings βseameet_get_settings - Read generated artifacts (summary, transcript, SRT, chapters, action items, key decisions, screenshot OCR/description) β
seameet_get_artifact - Search across artifact text β
seameet_search_text - Fetch a recording's asset-bundle manifest β
seameet_get_asset_bundle - Rename a file β
seameet_rename_fileΒ· save a new artifact βseameet_save_artifactΒ· regenerate a summary from a template βseameet_regenerate_summaryΒ· list templates βseameet_list_templates
βοΈ Cloud library (cloud mode)
- List recent synced recordings β
seameet_list_recent_recordingsΒ· fetch summary / transcript / chapters / action items / key decisions βseameet_get_recording - Get a temporary media stream/download URL β
seameet_get_media_url - Check storage usage β
seameet_get_usage - Manage outbound webhooks (signed deliveries on
ai.ready/recording.synced) βseameet_create_webhookΒ·seameet_list_webhooksΒ·seameet_update_webhookΒ·seameet_delete_webhook
π Connection (any mode)
- Which modes are connected β
seameet_statusΒ· disconnect cloud / switch accounts βseameet_logout
That's 17 desktop tools + 8 cloud tools (fetched live, so new releases appear automatically). A tool the current backend can't serve returns a clear, structured error instead of failing silently.
Install
Every client runs the same command β npx -y @seameet/mcp β only the config format differs. Full per-tool recipes: INSTALL.md (mirrored at app.seameet.ai/mcp/install.md).
Let your agent do it β already inside a coding agent? Paste:
Install the SeaMeet MCP server β fetch
https://raw.githubusercontent.com/seameet-ai/seameet-mcp/main/INSTALL.md, apply the section for whichever tool you're running in, and tell me how to reload.
Or pick your tool:
| Tool | Fastest install |
|---|---|
| Claude Code | claude mcp add seameet -- npx -y @seameet/mcp |
| Codex CLI / IDE | codex mcp add seameet -- npx -y @seameet/mcp |
| GitHub Copilot CLI | copilot mcp add seameet -- npx -y @seameet/mcp |
| Cursor | Add to Cursor (one-click) |
| Claude Desktop | one-click .mcpb bundle β see below |
| Antigravity Β· OpenCode Β· anything else | see INSTALL.md |
The generic block, accepted by most MCP clients:
{
"mcpServers": {
"seameet": { "command": "npx", "args": ["-y", "@seameet/mcp"] }
}
}
Requirements
- Node.js β₯ 18.
- For desktop mode: the SeaMeet desktop app installed and running β
brew install --cask seameet-ai/tap/seameet(macOS) orwinget install seameet(Windows). Needs v3.2.0+; an older running app reportsapp_outdated. - Cloud mode is opt-in and needs no app β the first cloud tool call starts a one-time authorization (below).
Cloud authorization (one-time, no key copy/paste)
Cloud mode never activates unless you provide SEAMEET_API_KEY or complete the device flow. On the first cloud tool call with no key, the agent shows a short code + https://app.seameet.ai/link; you open it (signed in), click Authorize, and a read+write key is minted and cached at ~/.seameet/credentials.json. Silent thereafter; revoke any time under API keys on your account. To disconnect or switch accounts, call seameet_logout (or rm ~/.seameet/credentials.json).
Claude Desktop one-click bundle
manifest.json is an MCPB bundle manifest, so the server ships as a one-click Claude Desktop extension:
npm install && npm run build:mcpb # β dist/seameet.mcpb
Install via Settings β Extensions β Advanced β Install extensionβ¦ and pick dist/seameet.mcpb. Claude Desktop runs it with its own Node.js β no terminal needed. (The desktop app still needs to be installed + running for desktop mode.)
Claude Code plugin (adds a /seameet skill)
This repo doubles as a Claude Code plugin marketplace. The plugin registers the MCP server and a /seameet skill that teaches the core workflows (record + transcribe, capture a bug report, mine meetings for action items):
claude plugin marketplace add seameet-ai/seameet-mcp
claude plugin install seameet@seameet
Try it
Just ask in plain language β the agent picks the right tool (and the right backend). A few starters:
Record my screen for 2 minutes, then give me the transcript.
What were the action items from my last meeting?
Take a screenshot and describe what's on it.
<details> <summary><b>Desktop mode</b> β a full recording session (app running)</summary>
- "What are my SeaMeet settings β where does it save recordings?"
- "List my summary templates."
- "List my local recordings." Β· "List the files in my SeaMeet save folder."
- "What's my current recording status?"
- "Start recording my microphone." (or: "record my whole screen")
- "Check the recording status now."
- "Show me the live transcript so far."
- "Pause the recording." Β· "Resume it."
- "Take a screenshot."
- "Stop the recording."
- "List my recordings again β the new one should be on top."
- "Give me the summary and transcript of that recording."
- "Regenerate its summary using one of my templates."
- "Search my recordings for the word '<keyword>'."
- "Rename that recording to 'MCP dual-mode test'."
- "Get the full asset bundle for it."
- "Save this text as a note/artifact on that recording: <text>."
</details>
<details> <summary><b>Cloud mode</b> β your synced library (no app needed)</summary>
- "List my 5 most recent SeaMeet recordings." Β· "What did I record in the last 7 days?"
- "Give me the summary of the top recording."
- "Now show its action items and key decisions."
- "Pull the full speaker-labeled transcript for it, and its chapters."
- "Get me a download/stream link for that recording's media."
- "How much SeaMeet storage am I using versus my quota?"
- "Create a webhook to
https://webhook.site/<your-id>that fires when AI results are ready." - "List my webhooks with their delivery health and signing secret."
- "Update that webhook to also fire on
recording.synced." - "Delete that webhook."
- "What's my SeaMeet connection status?"
- "Disconnect my SeaMeet cloud account." (forgets the cached key; the next cloud call re-authorizes)
</details>
How it works
A thin stdioβHTTP proxy. The SeaMeet desktop app hosts a localhost-only bridge (127.0.0.1:3741, fallbacks 3742/3743) authenticated with a per-launch random secret; on startup it writes credentials to $TMPDIR/seameet-mcp-bridge-<username>.json (mode 0600), which this server reads and proxies (tools/list β GET /mcp-bridge/tools, tools/call β POST /mcp-bridge/call-tool). Nothing leaves your machine in desktop mode. Cloud mode talks to the hosted SeaMeet worker over HTTPS with your minted key.
Full tool reference (for LLMs): seameet.ai/llms.txt β also served locally at http://localhost:3741/llms.txt while the app runs.
Errors are machine-readable
Tool failures return structured JSON your agent can branch on:
{ "success": false, "error": { "code": "app_not_running", "tool": "seameet_start_recording",
"message": "The SeaMeet desktop app is not running.",
"install": { "macos": "brew install --cask seameet-ai/tap/seameet", "windows": "winget install seameet" },
"hint": "Ask the user to install and launch it, then retry." } }
| Code | Meaning |
|---|---|
app_not_running |
Desktop app is closed β launch it (payload carries install commands + downloadUrl) |
app_outdated |
App is running but too old β update to requiredVersion (don't reinstall the same build) |
auth_required |
Cloud tool needs authorization β the payload has a user_code + the /link URL |
app_not_ready |
App is starting up β retry in a few seconds |
invalid_request |
A required parameter is missing/invalid β re-check the tool schema |
path_forbidden |
filePath must be inside the SeaMeet save directory |
not_found |
File or artifact doesn't exist β discover it with a list/search tool first |
timeout |
App didn't respond in time β check status, retry once |
unknown_tool |
Includes did_you_mean suggestions |
Configuration (rarely needed)
| Env var | Purpose |
|---|---|
SEAMEET_API_KEY |
Cloud API key (smk_β¦) β skips the device authorization flow |
SEAMEET_MCP_CREDENTIALS_FILE |
Explicit path to the desktop-bridge credentials file |
SEAMEET_BRIDGE_PORT + SEAMEET_BRIDGE_SECRET |
Bypass the bridge credentials file entirely |
SEAMEET_CLOUD_CREDENTIALS_FILE |
Where the minted cloud key is cached (default ~/.seameet/credentials.json) |
SEAMEET_REMOTE_URL / SEAMEET_DEVICE_URL |
Override the cloud endpoints (default: production) |
Development
npm install
npm test # credentials discovery + end-to-end stdio client against a fake bridge + fake cloud
npm run build:mcpb # validate manifest.json + pack the Claude Desktop extension
Releasing is automated β see PUBLISHING.md.
License
MIT Β© Seasalt.ai
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.