MCP Server | Parrot Scribe Docs

What is MCP?

Requires Parrot Scribe Pro. MCP server access is part of Parrot Scribe Pro. Existing licenses already include Pro.

The Model Context Protocol (MCP) is an open standard that lets AI assistants interact with external tools and data sources through a structured interface. Parrot Scribe includes a built-in MCP server, so there is nothing extra to install.

How It Works

The MCP server runs inside Parrot Scribe as a single process. There is no separate server to manage.

Built-in: The server is part of Parrot Scribe itself - no external packages or dependencies required.
Unix domain socket: Communication uses a local Unix socket with owner-only access.
Shim bridge: The bundled parrotscribe-mcp-shim bridges stdio MCP hosts to the local socket.
Token authentication: Clients must present a valid token during handshake.
Off by default: The MCP listener is disabled until you explicitly enable it. When disabled, no MCP socket is exposed.

Enabling the MCP Server

Open Parrot Scribe.
Go to Settings > MCP.
Toggle Enable MCP Server.
In the Clients section, create a token for each MCP client you want to allow.
Copy the token immediately when shown. It is only shown once.

Configuring AI Hosts

Host-specific install steps live on Listen Install.

Listen and Recap

How /parrot:listen and /parrot:recap work is on Listen and Recap. Install and maintenance for named hosts is on Listen Install.

See It In Action

This is a simulated run that showcases different scenarios where Parrot Scribe MCP can be useful. Each example is built from real functionality available after you enable the MCP server and connect a client such as OpenCode, Claude Code, or a similar extension with behavioral and role-specific instructions.

Access Model

Parrot Scribe applies controls at two layers:

Client access level (set per client in Settings):
- Disabled: No tool access.
- Enabled: Default once a client authenticates with a valid token. Status and operational tools are allowed; destructive tools always prompt.
- Trusted: Status, operational, and destructive tools are allowed without prompts.
Tool class:

Status tools - Always Allowed

No approval needed. Read-only status information.

Tool	Description
`get_status`	Recording state: `recording`, `listening`, `paused`, `error`, or `downloading`

Operational tools

Allowed for clients in Enabled or Trusted mode.

Tool	Description
`list_sessions`	Session metadata and speaker names
`read_transcript`	TOON-formatted transcript content
`search_sessions`	Content search across recent sessions
`live_transcript`	A best-effort in-memory ring filtered by `sinceSequence`. The feed is lost on restart; `sinceSequence` is not a crash-safe cursor.
`list_speakers`	Enrolled speakers with metadata
`identify_speakers`	Identify speakers in a session using provided names
`reassign_segment_speaker`	Reassign a specific transcript segment to an existing speaker
`start_recording`	Start transcription recording
`stop_recording`	Stop transcription recording

Destructive tools

For Enabled clients, every call prompts. Trusted clients can run these without prompts.

Tool	Description
`remove_speaker`	Delete voice model (reversible - can re-enroll later)
`forget_speaker`	Permanently remove a voice model and delete sessions containing that speaker
`delete_session`	Delete session and associated audio

Mutation Delivery and Audit

Parrot Scribe returns a mutating tool response only after the operation reaches a terminal success or failure. It does not return an accepted or still-running result.

Before domain work starts, Parrot Scribe durably records a started audit fact containing only an operation ID, tool name, and outcome. Once domain work starts, it continues to a terminal result even if the MCP caller disconnects. A disconnected caller may not receive that result, but disconnecting does not cancel or roll back the operation.

After the operation finishes, Parrot Scribe appends a correlated succeeded or failed audit fact. If the app crashes after started was saved but before a terminal fact was saved, the lone started fact means the outcome is unknown. It does not claim that the mutation failed. This audit trail is not a durable job queue and does not provide automatic recovery, retry, or polling.

Token Lifecycle

Issue one token per client from Settings > MCP in the Clients section.
Tokens are stored as hashed records at rest.
Revoking a token immediately removes that client access and disconnects active sessions for that token.

Security Model

Four layers protect your data:

Transport: Local Unix socket with owner-only access.
Authentication: Token is required at connection handshake.
Authorization: Per-client access levels and destructive-operation prompts.
Rate controls: Per-client throttling and bulk-access safeguards reduce automated misuse.

Use Cases

Meeting monitor - AI follows a live call and surfaces relevant context
Action item tracker - AI detects commitments and prepares follow-up tasks
Session summarizer - AI generates structured summaries after recordings
Research assistant - AI searches historical transcripts for patterns

For the end-to-end capture, review, retrieval, and optional AI workflow, read Meeting Notes Workflow.

Learn More

Model Context Protocol Documentation