Developer Integration
MCP Server
Up to 31 tools that let AI assistants record, transcribe, rename speakers, search, and create, all through the Model Context Protocol.
Watch your agent run the recorder
Install — let your agent do it
Already inside a coding agent (Claude Code, Codex, Cursor…)? Paste this — it fetches the guide and installs itself:
Install the SeaMeet MCP server — 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.Works with the desktop app running for the full recorder toolset — or in cloud mode against your synced library, no app required.
What is MCP?
The Model Context Protocol (MCP) is an open standard for connecting AI assistants to external data sources and tools. Instead of copying and pasting text into a chat window, MCP lets AI tools query your data directly through a structured interface.
SeaMeet's MCP server has up to 31 tools. 17 drive the desktop app and stay on your computer: start recordings, take screenshots, search every transcript, manage templates, read the live transcript, and save generated content. 11 work with your synced cloud library from any device once you authorize, including renaming speakers and regenerating summaries. 3 run in the npx @seameet/mcp client itself, including uploading a file from your computer for transcription.
31 Tools — Full Reference
Desktop app — 17 tools
Available while the SeaMeet desktop app is running. Nothing leaves your computer.
Data & Read (5 tools)
seameet_list_recordings List recordings & screenshots with metadata. Filter by type, date range, and limit.
seameet_get_artifact Read a specific artifact: summary, transcription, action-items, chapters, key-decisions, description, or ocr-text.
seameet_get_asset_bundle Get the full manifest of all artifacts for a recording.
seameet_get_settings Get app settings: save directory, mic gain, recording format, language.
seameet_list_files List raw files in the recording save directory.
Write (2 tools)
seameet_save_artifact Save AI-generated content (summary, slides, etc.) alongside a recording.
seameet_rename_file Rename a recording or screenshot file.
Actions (6 tools) — require running app
seameet_start_recording Start audio or video recording. Supports source: "microphone", "screen", or "both".
seameet_stop_recording Stop the current recording. Returns the saved file path.
seameet_take_screenshot Capture a screenshot of the current screen.
seameet_recording_status Get current state: is recording active, paused, elapsed time, video included.
seameet_pause_recording Pause an active audio-only recording.
seameet_resume_recording Resume a paused audio recording.
Search (1 tool)
seameet_search_text Search across all artifact text (case-insensitive). Returns matching snippets.
Templates & Live (3 tools)
seameet_list_templates List all available AI summary templates.
seameet_regenerate_summary Regenerate a summary with a chosen template.
seameet_get_live_transcript Get live transcript during active recording.
Cloud library — 11 tools
Work with your synced library from any device once you authorize with your SeaMeet account. Tools that change something need a read + write key.
seameet_list_recent_recordings List recordings in your cloud library, newest first, including files transcribed on app.seameet.ai.
seameet_get_recording Get a recording's summary, speaker-labeled transcript, chapters, action items or key decisions, with its speakers and transcription status.
seameet_rename_speakers Rename speakers in a recording: the transcript, summary, chapters, action items and key decisions all update. Needs a read + write key.
seameet_regenerate_recording_summary Regenerate a recording's AI summary from its current transcript. Needs a read + write key; up to once per recording every 5 minutes and 20 times a day.
seameet_get_media_url Get a temporary link to stream or download a recording.
seameet_get_usage Show how much cloud storage you use against your plan's quota.
seameet_create_webhook Register a webhook SeaMeet calls when a recording syncs or its AI summary is ready. Needs a read + write key.
seameet_list_webhooks List your webhooks with their signing secrets and delivery health.
seameet_update_webhook Re-enable a webhook or change its URL or events. Needs a read + write key.
seameet_delete_webhook Delete a webhook. Needs a read + write key.
seameet_desktop_recording_help Tell an agent how to install the desktop app when it is asked to record something.
In the npx client — 3 tools
Run inside npx @seameet/mcp on your computer.
seameet_transcribe_file Upload an audio or video file from your computer (up to 512 MB) and transcribe it, with speaker labels, in 50+ languages.
seameet_status Show whether the desktop app and your cloud account are connected.
seameet_logout Forget the cloud key saved on this computer.
Artifact Keys
Use these keys with {toolName} to retrieve specific data:
summarytranscriptionaction-itemschapterskey-decisionsdescriptionocr-text How it works
SeaMeet runs an MCP server locally
When the app is running, it spawns a local MCP server as a child process communicating over stdio. No network traffic leaves your device.
Configure your AI tool
Add SeaMeet to your MCP client config (Claude Code, Cursor, or any MCP-compatible tool). One line in your config file.
AI tools call SeaMeet directly
Your AI tool discovers the tools automatically, up to 31 of them, and can list and read recordings, start recordings, take screenshots, rename speakers, regenerate summaries, upload files for transcription, and save AI-generated artifacts, all through structured MCP tool calls.
How To Use
No manual configuration needed. SeaMeet handles everything automatically:
Run SeaMeet
When SeaMeet starts, it automatically spawns the MCP server and registers all 17 tools. No setup required.
Use the built-in AI Agent
Click the Agent tab in SeaMeet. The AI agent (GitHub Copilot or Claude) already has access to all 17 MCP tools — ask it to list recordings, search transcripts, or start a recording.
Or use Claude Code / Codex externally
Connect any MCP client with one command: claude mcp add seameet -- npx -y @seameet/mcp. Works with Claude Code, Codex, and Cursor while the app is running — see the setup guide at seameet.ai/en/docs/agents.
Open the setup guide →How it works under the hood: SeaMeet spawns the MCP server as a local child process (stdio transport). For tools that control the app (start recording, take screenshot), the MCP server calls back to the Electron main process via a local HTTP bridge, authenticated with a per-session secret that regenerates on each restart. Developers never need to configure ports or secrets manually.
MCP Bridge & LLM.txt
MCP Bridge routes
SeaMeet exposes MCP bridge routes for external access with secret authentication. This allows AI tools running on your machine to connect to SeaMeet's MCP server without additional configuration.
LLM.txt generation
SeaMeet auto-generates an LLM.txt file — an ASCII reference document that helps AI tools understand your recordings and artifacts. This file is updated automatically as your recording library grows.
Example usage
Once configured, your AI tool can interact with SeaMeet naturally:
You ask:
"List my recordings from this week"
AI calls:
seameet_list_recordings with dateFrom filter You ask:
"What were the action items from the product review?"
AI calls:
seameet_get_artifact with key: "action-items" You ask:
"Search all my meetings for mentions of the Q3 budget"
AI calls:
seameet_search_text with query: "Q3 budget" You ask:
"Start recording this meeting"
AI calls:
seameet_start_recording with source: "microphone" For developers: Full API reference including all 18+ HTTP bridge endpoints, error codes, and authentication details is available at {url} when the app is running.
llms.txt — Machine-Readable Reference
SeaMeet publishes a {filename} file — a plain-text reference of every tool, endpoint, parameter, response shape, and error code. AI agents can read this file to understand SeaMeet's full API surface.