Skip to main content
Glama

list_meetings

Retrieve and filter meeting records from Fathom AI with options for participants, dates, types, and pagination to manage meeting data efficiently.

Instructions

List meetings with optional filtering and pagination. All timestamps are UTC. Use get_summary or get_transcript for detailed content.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoPage number (starts at 1). Any page can be requested directly.
page_sizeNoNumber of meetings per page (default 10).
participantsNoFilter by participant email addresses (calendar invitees and recorder). Use with participants_match to control matching logic.
participants_matchNoHow to match participants: 'any' returns meetings with at least one match, 'all' returns only meetings where every listed participant is present.any
created_afterNoISO timestamp to filter meetings created after this date.
created_beforeNoISO timestamp to filter meetings created before this date.
meeting_typeNoFilter by 'internal' or 'external'.
calendar_invitees_domainsNoFilter by invitee email domains (e.g. ["acme.com"]).
calendar_invitees_domains_typeNoFilter invitee type: 'all', 'only_internal', or 'one_or_more_external'.
recorded_byNoFilter by recorder email addresses.
teamsNoFilter by team names.

Implementation Reference

  • The listMeetings method in FathomClient performs the actual API request to fetch meetings.
    async listMeetings(
      options: {
        cursor?: string | null;
        created_after?: string | null;
        created_before?: string | null;
        meeting_type?: string | null;
        calendar_invitees_domains?: string[] | null;
        calendar_invitees_domains_type?: string | null;
        recorded_by?: string[] | null;
        teams?: string[] | null;
      } = {}
    ): Promise<Record<string, unknown>> {
      const params: Record<string, unknown> = {
        cursor: options.cursor,
        created_after: options.created_after,
        created_before: options.created_before,
        meeting_type: options.meeting_type,
        calendar_invitees_domains_type: options.calendar_invitees_domains_type,
      };
      if (options.calendar_invitees_domains) {
        params['calendar_invitees_domains[]'] = options.calendar_invitees_domains;
      }
      if (options.recorded_by) {
        params['recorded_by[]'] = options.recorded_by;
      }
      if (options.teams) {
        params['teams[]'] = options.teams;
      }
      return this._get('/meetings', params);
    }
    
    async getTranscript(recordingId: number): Promise<Record<string, unknown>> {
  • src/server.ts:250-345 (registration)
    The 'list_meetings' tool is registered in src/server.ts, including its schema and handler function.
    server.registerTool(
      'list_meetings',
      {
        description:
          'List meetings with optional filtering and pagination. All timestamps are UTC. Use get_summary or get_transcript for detailed content.',
        inputSchema: {
          page: z
            .number()
            .int()
            .min(1)
            .default(1)
            .describe('Page number (starts at 1). Any page can be requested directly.'),
          page_size: z
            .number()
            .int()
            .min(1)
            .default(DEFAULT_PAGE_SIZE)
            .describe('Number of meetings per page (default 10).'),
          participants: z
            .array(z.string())
            .optional()
            .describe(
              'Filter by participant email addresses (calendar invitees and recorder). Use with participants_match to control matching logic.'
            ),
          participants_match: z
            .enum(['any', 'all'])
            .default('any')
            .describe(
              "How to match participants: 'any' returns meetings with at least one match, 'all' returns only meetings where every listed participant is present."
            ),
          created_after: z
            .string()
            .optional()
            .describe('ISO timestamp to filter meetings created after this date.'),
          created_before: z
            .string()
            .optional()
            .describe('ISO timestamp to filter meetings created before this date.'),
          meeting_type: z
            .enum(['internal', 'external'])
            .optional()
            .describe("Filter by 'internal' or 'external'."),
          calendar_invitees_domains: z
            .array(z.string())
            .optional()
            .describe('Filter by invitee email domains (e.g. ["acme.com"]).'),
          calendar_invitees_domains_type: z
            .enum(['all', 'only_internal', 'one_or_more_external'])
            .optional()
            .describe("Filter invitee type: 'all', 'only_internal', or 'one_or_more_external'."),
          recorded_by: z.array(z.string()).optional().describe('Filter by recorder email addresses.'),
          teams: z.array(z.string()).optional().describe('Filter by team names.'),
        },
      },
      async args => {
        const client = getClient();
        const apiKwargs: Record<string, unknown> = {
          created_after: args.created_after,
          created_before: args.created_before,
          meeting_type: args.meeting_type,
          calendar_invitees_domains: args.calendar_invitees_domains,
          calendar_invitees_domains_type: args.calendar_invitees_domains_type,
          recorded_by: args.recorded_by,
          teams: args.teams,
        };
        const key = cacheKey('list_meetings', {
          ...apiKwargs,
          participants: args.participants,
          participants_match: args.participants_match,
        });
    
        let cached = _itemsCache.get(key);
        const isExpired = cached !== undefined && Date.now() - cached.fetchedAt > CACHE_TTL_MS;
        if (!cached || isExpired) {
          try {
            const result = await fetchAll(
              opts => client.listMeetings(opts as Record<string, unknown>),
              apiKwargs
            );
            let { items } = result;
            if (args.participants && args.participants.length > 0) {
              items = filterByParticipants(
                items,
                args.participants,
                args.participants_match === 'all'
              );
            }
            const entry = { items, truncated: result.truncated, fetchedAt: Date.now() };
            _itemsCache.set(key, entry);
            cached = entry;
          } catch (err) {
            const msg = err instanceof Error ? err.message : String(err);
            return { content: [{ type: 'text', text: `Error fetching meetings: ${msg}` }] };
          }
        }
Behavior3/5

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 adds useful context: 'All timestamps are UTC' clarifies timezone handling, and the mention of pagination and filtering hints at the tool's scope. However, it doesn't disclose critical behavioral traits like rate limits, authentication requirements, error handling, or what the output format looks like (since there's no output schema).

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 extremely concise and well-structured with just two sentences. The first sentence states the core purpose and key features (filtering, pagination, UTC timestamps), and the second provides clear alternative guidance. Every word earns its place with zero waste or redundancy.

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

Completeness3/5

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

Given the complexity (11 parameters, no annotations, no output schema), the description is somewhat incomplete. It adequately covers the basic purpose and provides alternative tool guidance, but lacks details about output format, error conditions, or behavioral constraints that would be helpful for an AI agent. The high schema coverage helps, but the absence of output schema means the description should ideally hint at return values.

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

Parameters3/5

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 11 parameters thoroughly. The description adds minimal parameter semantics beyond what's in the schema—it mentions 'optional filtering and pagination' which aligns with parameters like 'page' and 'page_size', but doesn't provide additional context about parameter interactions or usage patterns. Baseline 3 is appropriate when schema does the heavy lifting.

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

Purpose4/5

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

The description clearly states the tool's purpose: 'List meetings with optional filtering and pagination.' It specifies the verb ('List') and resource ('meetings'), and mentions filtering/pagination capabilities. However, it doesn't explicitly differentiate from sibling tools like 'list_teams' or 'list_team_members' beyond mentioning alternatives for detailed content.

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

Usage Guidelines4/5

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

The description provides clear usage guidance by stating 'Use get_summary or get_transcript for detailed content,' which helps distinguish when to use this tool versus alternatives for meeting content. It also implies this tool is for listing with filtering, not for detailed content retrieval. However, it doesn't explicitly state when NOT to use this tool or compare it to all sibling tools.

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