A2A INTEGRATION · MCP-NATIVE

Use GitDealFlow A2A with Mastra

TypeScript agent framework with first-class MCP support. TypeScript builders shipping agents alongside their Next.js or Hono apps.

Crunchbase API: $20K/yr. GitDealFlow A2A: free, no signup.

Mastra has native MCP via MCPClient as of v0.4. Add our package once and every Mastra agent in the project can call all five skills. The A2A endpoint is the cleaner fallback when you want to call the agent without MCP overhead from a serverless edge handler.

Install

npm install @mastra/core @mastra/mcp

MCP via @mastra/mcp

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcp = new MCPClient({
  servers: {
    gitdealflow: {
      command: "npx",
      args: ["@gitdealflow/mcp-signal@latest"],
    },
  },
});

const tools = await mcp.getTools();

export const scoutAgent = new Agent({
  name: "VC Scout",
  model: openai("gpt-4o-mini"),
  instructions: "Use the gitdealflow tools to surface live engineering signals.",
  tools,
});

Direct A2A fetch tool

import { createTool } from "@mastra/core/tools";
import { z } from "zod";

export const gitdealflowA2A = createTool({
  id: "gitdealflow-a2a",
  description: "Call GitDealFlow's A2A endpoint for VC signals.",
  inputSchema: z.object({
    skill: z.enum([
      "get_trending_startups",
      "search_startups_by_sector",
      "get_startup_signal",
      "get_signals_summary",
      "get_methodology",
    ]),
    args: z.record(z.string(), z.any()).optional(),
  }),
  execute: async ({ context }) => {
    const r = await fetch("https://signals.gitdealflow.com/api/a2a", {
      method: "POST",
      headers: { "Content-Type": "application/json" },
      body: JSON.stringify({
        jsonrpc: "2.0", id: 1, method: "message/send",
        params: { message: { role: "user", parts: [
          { kind: "data", data: { skill: context.skill, args: context.args ?? {} } },
        ]}},
      }),
    });
    return (await r.json()).result.artifacts[0].parts[0].data;
  },
});

What you can ask

Inside a Mastra workflow: chain trending → memo-writer → email-sender steps.
Inside a Hono route: surface 'is this startup tracked?' for logged-in users.
Inside a cron job: write a Monday digest to the team's Slack.
Inside a multi-step agent: scout → analyst → verifier with shared context.

Gotchas

Mastra MCPClient holds long-lived stdio processes — call `await mcp.disconnect()` in serverless teardown to avoid orphaned children.
If your edge runtime can't spawn child processes, use the A2A fallback tool — it's pure fetch, edge-safe.

References

Try it without setup

The interactive playground lets you send live JSON-RPC requests against the A2A endpoint with no install, no auth. Pick a skill, hit send, see the response.

Full launch story: I made my VC deal flow callable by Claude.

Other framework integrations

MCP via @mastra/mcp

import { MCPClient } from "@mastra/mcp"; import { Agent } from "@mastra/core/agent"; import { openai } from "@ai-sdk/openai"; const mcp = new MCPClient({ servers: { gitdealflow: { command: "npx", args: ["@gitdealflow/mcp-signal@latest"], }, }, }); const tools = await mcp.getTools(); export const scoutAgent = new Agent({ name: "VC Scout", model: openai("gpt-4o-mini"), instructions: "Use the gitdealflow tools to surface live engineering signals.", tools, });

Direct A2A fetch tool

import { createTool } from "@mastra/core/tools"; import { z } from "zod"; export const gitdealflowA2A = createTool({ id: "gitdealflow-a2a", description: "Call GitDealFlow's A2A endpoint for VC signals.", inputSchema: z.object({ skill: z.enum([ "get_trending_startups", "search_startups_by_sector", "get_startup_signal", "get_signals_summary", "get_methodology", ]), args: z.record(z.string(), z.any()).optional(), }), execute: async ({ context }) => { const r = await fetch("https://signals.gitdealflow.com/api/a2a", { method: "POST", headers: { "Content-Type": "application/json" }, body: JSON.stringify({ jsonrpc: "2.0", id: 1, method: "message/send", params: { message: { role: "user", parts: [ { kind: "data", data: { skill: context.skill, args: context.args ?? {} } }, ]}}, }), }); return (await r.json()).result.artifacts[0].parts[0].data; }, });