Skip to main content
Glama
matthewbergvinson

Fathom MCP Server

get_action_items

Extract action items from Fathom meeting recordings to track tasks and follow-ups. Specify a recording ID or check recent meetings for pending items.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
recording_idNoGet action items from a specific meeting
include_completedNoInclude completed action items (default: true)
limitNoNumber of recent meetings to check if no recording_id (default: 10)

Implementation Reference

  • Main handler function: Fetches meetings using Fathom client (specific recording or recent), extracts and filters action items (by completion status), formats into markdown sections using formatActionItems and formatDate.
    async ({ recording_id, include_completed, limit }) => {
      const meetingLimit = limit || 10;
      console.error(recording_id ? `Getting action items for ${recording_id}...` : `Getting action items from recent meetings...`);
    
      if (recording_id) {
        const response = await fathom.listMeetings({ include_action_items: true });
        const meeting = response.items.find(m => m.recording_id === recording_id);
    
        if (!meeting) {
          return {
            content: [{ type: 'text', text: `Meeting with recording ID ${recording_id} not found.` }],
            isError: true,
          };
        }
    
        let items = meeting.action_items || [];
        if (include_completed === false) {
          items = items.filter(i => !i.completed);
        }
    
        const title = meeting.title || meeting.meeting_title || `Meeting ${meeting.recording_id}`;
        const markdown = `## Action Items from: ${title}\n\n${formatActionItems(items)}`;
        
        return {
          content: [{ type: 'text', text: markdown }],
        };
      } else {
        const response = await fathom.listMeetings({ include_action_items: true });
        const meetings = response.items.slice(0, meetingLimit);
    
        const sections: string[] = [];
        for (const meeting of meetings) {
          let items = meeting.action_items || [];
          if (items.length === 0) continue;
    
          if (include_completed === false) {
            items = items.filter(i => !i.completed);
          }
          if (items.length === 0) continue;
    
          const title = meeting.title || meeting.meeting_title || `Meeting ${meeting.recording_id}`;
          const date = formatDate(meeting.recording_start_time);
          sections.push(`### ${title}\n_${date}_\n\n${formatActionItems(items)}`);
        }
    
        const markdown = sections.length > 0
          ? `# Action Items from Recent Meetings\n\n${sections.join('\n\n')}`
          : 'No action items found in recent meetings.';
    
        return {
          content: [{ type: 'text', text: markdown }],
        };
      }
    }
  • Zod schema defining input parameters for the tool.
    {
      recording_id: z.number().optional().describe('Get action items from a specific meeting'),
      include_completed: z.boolean().optional().describe('Include completed action items (default: true)'),
      limit: z.number().optional().describe('Number of recent meetings to check if no recording_id (default: 10)'),
    },
  • src/index.ts:267-327 (registration)
    Registers the 'get_action_items' tool on the MCP server with schema and handler function.
      'get_action_items',
      {
        recording_id: z.number().optional().describe('Get action items from a specific meeting'),
        include_completed: z.boolean().optional().describe('Include completed action items (default: true)'),
        limit: z.number().optional().describe('Number of recent meetings to check if no recording_id (default: 10)'),
      },
      async ({ recording_id, include_completed, limit }) => {
        const meetingLimit = limit || 10;
        console.error(recording_id ? `Getting action items for ${recording_id}...` : `Getting action items from recent meetings...`);
    
        if (recording_id) {
          const response = await fathom.listMeetings({ include_action_items: true });
          const meeting = response.items.find(m => m.recording_id === recording_id);
    
          if (!meeting) {
            return {
              content: [{ type: 'text', text: `Meeting with recording ID ${recording_id} not found.` }],
              isError: true,
            };
          }
    
          let items = meeting.action_items || [];
          if (include_completed === false) {
            items = items.filter(i => !i.completed);
          }
    
          const title = meeting.title || meeting.meeting_title || `Meeting ${meeting.recording_id}`;
          const markdown = `## Action Items from: ${title}\n\n${formatActionItems(items)}`;
          
          return {
            content: [{ type: 'text', text: markdown }],
          };
        } else {
          const response = await fathom.listMeetings({ include_action_items: true });
          const meetings = response.items.slice(0, meetingLimit);
    
          const sections: string[] = [];
          for (const meeting of meetings) {
            let items = meeting.action_items || [];
            if (items.length === 0) continue;
    
            if (include_completed === false) {
              items = items.filter(i => !i.completed);
            }
            if (items.length === 0) continue;
    
            const title = meeting.title || meeting.meeting_title || `Meeting ${meeting.recording_id}`;
            const date = formatDate(meeting.recording_start_time);
            sections.push(`### ${title}\n_${date}_\n\n${formatActionItems(items)}`);
          }
    
          const markdown = sections.length > 0
            ? `# Action Items from Recent Meetings\n\n${sections.join('\n\n')}`
            : 'No action items found in recent meetings.';
    
          return {
            content: [{ type: 'text', text: markdown }],
          };
        }
      }
    );
  • Helper function to format action items into markdown list with completion status, assignee, and timestamp.
    export function formatActionItems(actionItems: ActionItem[] | null | undefined): string {
      if (!actionItems || actionItems.length === 0) {
        return '_No action items_';
      }
    
      return actionItems.map(item => {
        const status = item.completed ? '[x]' : '[ ]';
        const assignee = item.assignee ? ` _(assigned to ${item.assignee.name})_` : '';
        const timestamp = item.recording_timestamp ? ` at ${item.recording_timestamp}` : '';
        return `- ${status} ${item.description}${assignee}${timestamp}`;
      }).join('\n');
    }
Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

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

Completeness1/5

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

Tool has no description.

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

Parameters1/5

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

Tool has no description.

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

Purpose1/5

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

Tool has no description.

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

Usage Guidelines1/5

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

Tool has no description.

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/matthewbergvinson/fathom-mcp'

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