Skip to main content
Glama

get_transcript

Extract meeting transcripts from recordings, with options to retrieve full content or specific time segments for efficient analysis.

Instructions

Get the transcript for a meeting recording. Returns plaintext lines.

For long meetings, use start_time/end_time to fetch a specific window. First call without time params to get metadata (duration, line count), then request specific chunks as needed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
recording_idYesThe recording ID (from list_meetings).
start_timeNoStart of time window in HH:MM:SS format (e.g. "00:10:00").
end_timeNoEnd of time window in HH:MM:SS format (e.g. "00:20:00").

Implementation Reference

  • The actual client method that fetches transcript data from the Fathom API.
    async getTranscript(recordingId: number): Promise<Record<string, unknown>> {
      return this._get(`/recordings/${recordingId}/transcript`);
    }
  • src/server.ts:365-388 (registration)
    MCP tool registration for get_transcript, including schema definition and description.
      server.registerTool(
        'get_transcript',
        {
          description: `Get the transcript for a meeting recording. Returns plaintext lines.
    
    For long meetings, use start_time/end_time to fetch a specific window.
    First call without time params to get metadata (duration, line count),
    then request specific chunks as needed.`,
          inputSchema: {
            recording_id: z
              .number()
              .int()
              .positive()
              .describe('The recording ID (from list_meetings).'),
            start_time: z
              .string()
              .optional()
              .describe('Start of time window in HH:MM:SS format (e.g. "00:10:00").'),
            end_time: z
              .string()
              .optional()
              .describe('End of time window in HH:MM:SS format (e.g. "00:20:00").'),
          },
        },
  • The MCP tool handler in src/server.ts, which includes caching logic and calls the fathom client.
    async args => {
      const client = getClient();
      const cached = _transcriptCache.get(args.recording_id);
      const isExpired = cached !== undefined && Date.now() - cached.fetchedAt > CACHE_TTL_MS;
      if (!cached || isExpired) {
        try {
          const result = await client.getTranscript(args.recording_id);
          const transcript = (result.transcript as Record<string, unknown>[]) ?? [];
          _transcriptCache.set(args.recording_id, { items: transcript, fetchedAt: Date.now() });
        } catch (err) {
          const msg = err instanceof Error ? err.message : String(err);
          return { content: [{ type: 'text', text: `Error fetching transcript: ${msg}` }] };
        }
      }
      let items = [..._transcriptCache.get(args.recording_id)!.items];
    
      if (items.length === 0) {
        return { content: [{ type: 'text', text: 'No transcript available.' }] };
      }
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: the tool returns plaintext lines, supports chunking for long meetings via time parameters, and has a two-step workflow (metadata first, then chunks). However, it lacks details on error handling, rate limits, or authentication needs, which could be important for a read operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose, followed by actionable usage guidelines in two concise sentences. Every sentence earns its place by providing essential information without redundancy, making it efficient and well-structured for quick understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (3 parameters, no output schema, no annotations), the description is largely complete: it covers purpose, usage, and parameter semantics. However, it lacks details on output format beyond 'plaintext lines' (e.g., structure or pagination) and behavioral aspects like errors or limits, leaving minor gaps for a read tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters well. The description adds value by explaining the semantic use of parameters: start_time/end_time are for fetching specific windows in long meetings, and calling without them first gets metadata. This clarifies the parameter interactions beyond the schema's technical descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Get the transcript') and resource ('for a meeting recording'), distinguishing it from siblings like get_summary (which likely provides summaries) and list_meetings (which lists meetings). It also specifies the return format ('Returns plaintext lines'), making the purpose explicit and distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool vs. alternatives: it advises calling without time parameters first to get metadata (duration, line count) and then using start_time/end_time for specific chunks in long meetings. This offers clear context and a workflow, though it doesn't explicitly mention sibling tools, the guidance is comprehensive for its own use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jerichosequitin/fathom-ai-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server