Skip to main content
Glama
Transcript MCP spike

Transcript MCP spike

Transcript MCP spike

A small Model Context Protocol server that lets an LLM inspect and search mock transcripts stored in data/transcripts.json.

Requirements

  • Node.js 18 or newer

  • npm

Related MCP server: AskElephant MCP

Transports

This server supports two transports:

  1. stdio — the MCP client spawns the process (default)

  2. Streamable HTTP — you run the server and point the client at http://127.0.0.1:3000/mcp

HTTP (localhost)

Start the server:

npm run mcp:http

Or with auto-reload while editing TypeScript:

npm run dev:http

Then configure the client with a URL:

{
  "mcpServers": {
    "transcripts": {
      "url": "http://127.0.0.1:3000/mcp"
    }
  }
}

Optional env vars:

  • PORT — listen port (default 3000)

  • MCP_TRANSPORT=http — same as passing --http

Inspector:

npx @modelcontextprotocol/inspector http://127.0.0.1:3000/mcp

stdio (spawned by the client)

No separate server process. Point the client at the TypeScript source:

{
  "mcpServers": {
    "transcripts": {
      "command": "npx",
      "args": [
        "tsx",
        "/absolute/path/to/mcp-spike/src/server.ts"
      ]
    }
  }
}

Or use the compiled build after npm run build:

{
  "mcpServers": {
    "transcripts": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-spike/dist/server.js"]
    }
  }
}

MCP capabilities

Resource:

  • transcripts://all returns the complete JSON dataset.

Tools:

  • list_transcripts lists metadata and supports participant and tag filters.

  • get_transcript returns a full transcript by ID.

  • search_transcripts searches titles, participants, tags, speakers, and spoken text.

Edits to data/transcripts.json are picked up on the next tool/resource call. Invalid data is rejected using a Zod schema.

Available Tools

3 tools
get_transcriptGet transcriptA
Read-only

Get one complete transcript by its ID.

Inputs: id (required).

list_transcriptsList transcriptsA
Read-only

List transcript metadata. Optionally filter by participant or tag.

Inputs: tag, limit, participant.

search_transcriptsSearch transcriptsA
Read-only

Search titles, participants, tags, speakers, and spoken transcript text.

Inputs: query (required), limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: listing metadata, retrieving a single transcript by ID, and searching across transcript content. No overlap or ambiguity.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (list_transcripts, get_transcript, search_transcripts), with minor singular/plural variation that does not undermine the pattern.

    Tool Count5/5

    Three tools is a well-scoped set for a transcript retrieval service, covering the essential read operations without unnecessary bloat.

    Completeness4/5

    The read side is well covered (list, get, search), but write operations like create, update, or delete are absent. For a 'spike' server, this is a minor gap.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers