Skip to main content
Glama
jongall45

Frontrun MCP Server

by jongall45

frontrun_convergence

Detect when multiple venture capital firms independently follow the same X account within a time window, signaling potential pre-funding interest. Adjust threshold and timeframe to filter signal strength.

Instructions

Detect convergence: entities followed by multiple tracked accounts independently within a time window. Higher threshold = stronger signal. This is the highest-signal endpoint — when 3+ VCs independently follow the same account, it strongly suggests pre-funding interest.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
thresholdNoMinimum number of tracked accounts that must have followed. Default: 2. Use 3+ for high-conviction signals.
sinceNoTime window: "48h", "7d", "14d", "30d", or ISO date. Default: "7d"

Implementation Reference

  • Handler function for frontrun_convergence tool. Builds query parameters (threshold, since) and makes a GET request to the /v1/convergence API endpoint, returning JSON-formatted results.
      async ({ threshold, since }) => {
        const params = new URLSearchParams();
        if (threshold) params.set('threshold', String(threshold));
        if (since) params.set('since', since);
        const qs = params.toString();
        const result = await apiCall('GET', `/convergence${qs ? '?' + qs : ''}`);
        return { content: [{ type: 'text', text: JSON.stringify(result, null, 2) }] };
      }
    );
  • Zod schema defining two optional input parameters: threshold (number) for minimum tracked accounts, and since (string) for the time window.
    {
      threshold: z.number().optional().describe('Minimum number of tracked accounts that must have followed. Default: 2. Use 3+ for high-conviction signals.'),
      since: z.string().optional().describe('Time window: "48h", "7d", "14d", "30d", or ISO date. Default: "7d"'),
    },
  • index.js:161-177 (registration)
    Complete tool registration for frontrun_convergence using MCP server.tool() method. Registers the tool name, description, input schema, and handler function.
    // --- GET /v1/convergence ---
    server.tool(
      'frontrun_convergence',
      'Detect convergence: entities followed by multiple tracked accounts independently within a time window. Higher threshold = stronger signal. This is the highest-signal endpoint — when 3+ VCs independently follow the same account, it strongly suggests pre-funding interest.',
      {
        threshold: z.number().optional().describe('Minimum number of tracked accounts that must have followed. Default: 2. Use 3+ for high-conviction signals.'),
        since: z.string().optional().describe('Time window: "48h", "7d", "14d", "30d", or ISO date. Default: "7d"'),
      },
      async ({ threshold, since }) => {
        const params = new URLSearchParams();
        if (threshold) params.set('threshold', String(threshold));
        if (since) params.set('since', since);
        const qs = params.toString();
        const result = await apiCall('GET', `/convergence${qs ? '?' + qs : ''}`);
        return { content: [{ type: 'text', text: JSON.stringify(result, null, 2) }] };
      }
    );
  • Helper function apiCall that handles all HTTP requests to the Frontrun API. Includes authentication headers, timeout handling (60s), and error handling for rate limits, auth failures, and insufficient balance.
    async function apiCall(method, path, body = null) {
      const url = `${API_URL}/v1${path}`;
      const options = {
        method,
        headers: {
          'X-API-Key': API_KEY,
          'Content-Type': 'application/json',
        },
      };
      if (body) {
        options.body = JSON.stringify(body);
      }
    
      const controller = new AbortController();
      const timeout = setTimeout(() => controller.abort(), 60000);
      options.signal = controller.signal;
    
      let response;
      try {
        response = await fetch(url, options);
      } catch (err) {
        clearTimeout(timeout);
        if (err.name === 'AbortError') return { error: 'Request timed out (60s). Try a narrower query.' };
        return { error: `Network error: ${err.message}` };
      }
      clearTimeout(timeout);
    
      if (response.status === 429) {
        const retry = response.headers.get('Retry-After') || '60';
        return { error: `Rate limited. Retry in ${retry}s.` };
      }
      if (response.status === 401) {
        return { error: 'Invalid API key. Check FRONTRUN_API_KEY.' };
      }
      if (response.status === 402) {
        const data = await response.json();
        return { error: 'Insufficient balance', ...data };
      }
      if (!response.ok) {
        const text = await response.text();
        return { error: `HTTP ${response.status}: ${text.slice(0, 500)}` };
      }
    
      return response.json();
    }

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/jongall45/frontrun-mcp-server'

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