stack/packages/harness/tests/mcp-server.test.mjs

import { test } from "node:test";
import assert from "node:assert/strict";
import { spawn } from "node:child_process";
import { writeFileSync } from "node:fs";
import { join } from "node:path";
import { createInterface } from "node:readline";
import { SOURCES } from "../src/bundle.mjs";
import { REPLY_CAP, typedTools } from "../src/tools.mjs";
import { fakeToolSocket, resolvedFor, scratch } from "./helpers.mjs";

// The server over stdio: send(message) resolves with the reply to its id.
function serve(t, toolsFile, socket) {
  const child = spawn(process.execPath, [SOURCES.mcpServer, toolsFile, socket], { stdio: ["pipe", "pipe", "pipe"] });
  t.after(() => child.kill());
  const waiting = new Map();
  const orphans = [];
  createInterface({ input: child.stdout }).on("line", (line) => {
    const m = JSON.parse(line);
    const w = waiting.get(m.id);
    if (w) {
      waiting.delete(m.id);
      w(m);
    } else orphans.push(m);
  });
  let next = 1;
  return {
    orphans,
    send(method, params) {
      const id = next++;
      return new Promise((resolve) => {
        waiting.set(id, resolve);
        child.stdin.write(JSON.stringify({ jsonrpc: "2.0", id, method, params }) + "\n");
      });
    },
    raw: (text) => child.stdin.write(text),
  };
}

async function setup(t) {
  const dir = scratch(t);
  const tools = typedTools({ resolved: resolvedFor(t, "pm"), tracker: true });
  const toolsFile = join(dir, "tools.json");
  writeFileSync(toolsFile, JSON.stringify(tools));
  const sock = await fakeToolSocket(t, dir, (tool, args) => {
    if (tool === "launch") throw new Error("capacity-full");
    // trail answers a string `size` characters long once JSON-encoded, for the reply cap.
    if (tool === "trail" && /^size:/.test(args.subject)) return "x".repeat(Number(args.subject.slice(5)) - 2);
    return { tool, args };
  });
  return { dir, tools, sock, server: serve(t, toolsFile, sock.path) };
}

test("initialize, ping and tools/list", async (t) => {
  const { tools, server } = await setup(t);
  const init = await server.send("initialize", { protocolVersion: "2025-03-26", capabilities: {}, clientInfo: { name: "x", version: "0" } });
  assert.deepEqual(init.result, { protocolVersion: "2025-03-26", capabilities: { tools: {} }, serverInfo: { name: "mosaic", version: "1" } });
  assert.deepEqual((await server.send("ping")).result, {});
  const list = (await server.send("tools/list")).result.tools;
  assert.deepEqual(list.map((x) => x.name), tools.map((x) => x.name));
  const launch = list.find((x) => x.name === "launch");
  assert.deepEqual(launch.inputSchema, tools.find((x) => x.name === "launch").parameters);
});

test("tools/call goes through the tool socket; a refusal is an isError result", async (t) => {
  const { sock, server } = await setup(t);
  const ok = (await server.send("tools/call", { name: "list_agents", arguments: { scope: "all" } })).result;
  assert.equal(ok.isError, undefined);
  assert.deepEqual(JSON.parse(ok.content[0].text), { tool: "list_agents", args: { scope: "all" } });
  const refused = (await server.send("tools/call", { name: "launch", arguments: { instance: "coder" } })).result;
  assert.equal(refused.isError, true);
  assert.equal(refused.content[0].text, "refused: capacity-full");
  assert.deepEqual(sock.calls.map((c) => c.tool), ["list_agents", "launch"]);
});

test("replies are compact JSON; over the cap a tool error names the size and the cap", async (t) => {
  const { sock, server } = await setup(t);
  const call = async (name, args) => (await server.send("tools/call", { name, arguments: args })).result;
  const ok = await call("get_task", { task_ref: "vikunja:3/7" });
  assert.equal(ok.content[0].text, '{"tool":"get_task","args":{"task_ref":"vikunja:3/7"}}');
  // list_tasks with no arguments asks the broker for open tasks.
  assert.equal((await call("list_tasks", {})).content[0].text, '{"tool":"list_tasks","args":{"done":false}}');
  const fits = await call("trail", { subject: `size:${REPLY_CAP}` });
  assert.equal(fits.isError, undefined);
  assert.equal(fits.content[0].text.length, REPLY_CAP);
  const over = await call("trail", { subject: `size:${REPLY_CAP + 1}` });
  assert.equal(over.isError, true);
  assert.deepEqual(over.content, [{
    type: "text",
    text: `reply too large: ${REPLY_CAP + 1} characters, over the ${REPLY_CAP}-character cap. Narrow the query: a filter, a smaller limit, or get_task for one task.`,
  }]);
  assert.deepEqual(sock.calls.map((c) => c.tool), ["get_task", "list_tasks", "trail", "trail"]);
});

test("unknown tools and methods are JSON-RPC errors and never reach the socket", async (t) => {
  const { sock, server } = await setup(t);
  const unknown = await server.send("tools/call", { name: "resolve_decision", arguments: {} });
  assert.equal(unknown.error.code, -32602);
  assert.equal((await server.send("resources/list")).error.code, -32601);
  server.raw("not json\n");
  // A notification gets no reply; the next request still answers.
  server.raw(JSON.stringify({ jsonrpc: "2.0", method: "notifications/initialized" }) + "\n");
  assert.deepEqual((await server.send("ping")).result, {});
  assert.deepEqual(server.orphans, [{ jsonrpc: "2.0", id: null, error: { code: -32700, message: "parse error" } }]);
  assert.equal(sock.calls.length, 0);
});

test("a missing argument is a usage error", async (t) => {
  const child = spawn(process.execPath, [SOURCES.mcpServer], { stdio: "pipe" });
  const code = await new Promise((r) => child.on("exit", r));
  assert.equal(code, 2);
});