mesh-tools/test/mcp.test.ts

/**
 * The MCP surface, driven the way a host drives it.
 *
 * **The claim worth checking is that it is the same thing the command line is.** An agent and a
 * person must see the same tools and get the same answers, or this becomes a second definition of what
 * a tool is — which is exactly what a thin adapter is supposed to avoid.
 *
 *   docker run -d --rm --name t -p 14232:4222 nats:2.10-alpine -js
 *   MESH_TEST_NATS=nats://127.0.0.1:14232 node --test --experimental-strip-types test/mcp.test.ts
 */
import assert from "node:assert/strict";
import { test } from "node:test";
import { spawn } from "node:child_process";

import { connectNats } from "../dist/broker-nats.js";

const url = process.env.MESH_TEST_NATS;

/** A module answering the catalogue's list and one tool, plus a credential file the client reads. */
async function aMeshAndACredential(t: { after: (fn: () => Promise<void> | void) => void }) {
  const catalogue = await connectNats({ url: url!, module: "mesh-catalog" });
  const shop = await connectNats({ url: url!, module: "shop" });
  await catalogue.handle("catalog_modules", async () => ({
    modules: [{ module: "shop" }, { module: "ghost" }],
  }));
  await shop.handle("tools", async () => ({
    module: "shop",
    tools: [{ name: "price", description: "what something costs", input: { of: { type: "string" } } }],
  }));
  await shop.handle("price", async (body: { of?: string }) => ({ of: body.of ?? "nothing", cost: 12 }));
  const controller = await connectNats({ url: url!, module: "mesh-controller" });
  await controller.handle("seat:mesh-controller.tools", async () => ({
    seats: [{ seat: "mesh-controller", scope: "mesh", tools: [{ name: "status", description: "what is wrong", input: {} }] }],
  }));
  await controller.handle("seat:mesh-controller.status", async () => ({ output: "all quiet", ok: true }));
  t.after(async () => {
    await catalogue.close();
    await shop.close();
    await controller.close();
  });

  const { mkdtemp, writeFile } = await import("node:fs/promises");
  const { join } = await import("node:path");
  const dir = await mkdtemp("/tmp/mesh-client-");
  const path = join(dir, "credential.json");
  await writeFile(
    path,
    JSON.stringify({ url, user: "person.ada", password: "x", person: "ada", invokes: ["shop.price"] }),
  );
  return path;
}

/** Drive `mesh mcp` over stdio and collect the replies, as a host would. */
function driving(credential: string, requests: unknown[]): Promise<Record<string, any>[]> {
  return new Promise((resolve, reject) => {
    const child = spawn(process.execPath, ["dist/mesh.js", "mcp", "--credential", credential], {
      stdio: ["pipe", "pipe", "pipe"],
    });
    let out = "";
    let err = "";
    child.stdout.on("data", (d) => (out += d.toString()));
    child.stderr.on("data", (d) => (err += d.toString()));
    child.on("error", reject);
    child.on("close", () => {
      const replies = out
        .split("\n")
        .filter((l) => l.trim() !== "")
        .map((l) => JSON.parse(l) as Record<string, any>);
      if (replies.length === 0 && err !== "") reject(new Error(err));
      else resolve(replies);
    });
    for (const r of requests) child.stdin.write(`${JSON.stringify(r)}\n`);
    child.stdin.end();
  });
}

test("a host initialises, lists the mesh's tools and calls one", async (t) => {
  if (!url) return t.skip("MESH_TEST_NATS unset");
  const credential = await aMeshAndACredential(t);

  const replies = await driving(credential, [
    { jsonrpc: "2.0", id: 1, method: "initialize", params: {} },
    { jsonrpc: "2.0", method: "notifications/initialized" },
    { jsonrpc: "2.0", id: 2, method: "tools/list" },
    { jsonrpc: "2.0", id: 3, method: "tools/call", params: { name: "shop.price", arguments: { of: "a hat" } } },
  ]);

  const byId = new Map(replies.map((r) => [r.id, r]));
  // A notification is answered with nothing, or a host waiting on ids sees a reply it cannot match.
  assert.equal(replies.length, 3, `expected three replies, got ${JSON.stringify(replies)}`);

  const hello = byId.get(1)!.result;
  assert.equal(hello.protocolVersion, "2025-03-26");
  assert.ok(hello.capabilities.tools, "a server offering no tools is not this one");
  assert.match(hello.instructions, /ada/, "the handshake says whose authority a call is made under");

  const listed = byId.get(2)!.result.tools;
  assert.deepEqual(listed.map((x: { name: string }) => x.name), ["mesh-controller.status", "shop.price"],
    "the modules' tools and the roles', named the way a person names them");
  const price = listed[1];
  assert.ok(price.inputSchema, "a tool with no schema is one an agent cannot call");
  // A module's bare property map arrives as a schema an agent can read, its words kept — and
  // `node`, the machine to ask when the module runs on several (novox/hq ADR 0159), beside them.
  assert.deepEqual(price.inputSchema.properties.of, { type: "string" });
  assert.equal(price.inputSchema.properties.node.type, "string", "a module's tool takes the machine to ask");
  assert.ok(!listed[0].inputSchema.properties?.node, "a seat's verb takes no machine; the seat's scope decides");
  // Silence is named: the module the catalogue holds and nothing answered for.
  assert.deepEqual(byId.get(2)!.result._meta.notAnswering, ["ghost"]);

  const called = byId.get(3)!.result;
  assert.ok(!called.isError, `the call failed: ${JSON.stringify(called)}`);
  // The module's own answer, unshaped. An adapter that summarised it would be deciding what matters
  // in somebody else's answer.
  assert.deepEqual(JSON.parse(called.content[0].text), { of: "a hat", cost: 12 });
});

test("a tool nobody serves comes back as an error the agent can act on", async (t) => {
  if (!url) return t.skip("MESH_TEST_NATS unset");
  const credential = await aMeshAndACredential(t);

  const replies = await driving(credential, [
    { jsonrpc: "2.0", id: 1, method: "tools/call", params: { name: "ghost.missing", arguments: {} } },
  ]);
  const result = replies[0].result;
  // isError, not a protocol failure: the call was well-formed and the mesh answered it — with an
  // absence. A JSON-RPC error would tell the agent its request was malformed, which it was not.
  assert.ok(result?.isError, `expected a tool error, got ${JSON.stringify(replies[0])}`);
  assert.match(result.content[0].text, /nothing serves ghost\.missing/);
});

test("a method this surface does not have is refused, and a notification is not", async (t) => {
  if (!url) return t.skip("MESH_TEST_NATS unset");
  const credential = await aMeshAndACredential(t);

  const replies = await driving(credential, [
    { jsonrpc: "2.0", id: 1, method: "resources/list" },
    { jsonrpc: "2.0", method: "notifications/cancelled" },
  ]);
  assert.equal(replies.length, 1, "a notification was answered");
  assert.equal(replies[0].error.code, -32601);
  assert.match(replies[0].error.message, /resources\/list/);
});

test("a host calls the mesh's own verb through the seat", async (t) => {
  if (!url) return t.skip("MESH_TEST_NATS unset");
  const credential = await aMeshAndACredential(t);
  const replies = await driving(credential, [
    { jsonrpc: "2.0", id: 1, method: "tools/call", params: { name: "mesh-controller.status", arguments: {} } },
  ]);
  const result = replies[0].result;
  assert.ok(!result.isError, JSON.stringify(replies[0]));
  assert.deepEqual(JSON.parse(result.content[0].text), { output: "all quiet", ok: true });
});