Agent-MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Agent-MCPStandup time — what should I work on today?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Homework — Host, Two Transports, and a Skill
This project satisfies the local parts of the assignment without extra frameworks:
a CLI agent using Ollama
qwen3.5:4b;an MCP host that loads config, merges tools, and routes calls;
a stdio todo server with 3 tools, 1 resource, and 1 prompt;
the same server over authenticated local Streamable HTTP;
progressive skill loading through
use_skill;persistence, validation, recoverable MCP errors, and integration tests.
Public hosting is intentionally not performed. See PUBLIC_HTTP.md for the exact deployment steps.
Requirements
Node.js 20+
Ollama
qwen3.5:4b:ollama pull qwen3.5:4b
Related MCP server: Personal OS MCP
Install and verify
npm install
npm test
npm run checkRun everything locally
Use the same local key in both terminals. It is not committed.
Terminal 1 — start the authenticated HTTP server:
export MCP_KEY="$(openssl rand -hex 32)"
echo "$MCP_KEY" # copy this value for terminal 2
npm run server:httpTerminal 2 — ensure Ollama is running, then start the agent:
export MCP_KEY="paste-the-same-value"
ollama serve # omit if Ollama is already runningIn another terminal, run:
export MCP_KEY="paste-the-same-value"
npm run agentTry these requests:
Add "finish MCP homework" using the stdio todo server.
Add "record the demo" using the HTTP todo server.
Standup time — what should I work on today?The last request should trigger use_skill("daily-plan"), then call both MCP servers and return Today, Later, and Blockers.
Test with MCP Inspector
Stdio:
npx @modelcontextprotocol/inspector node src/servers/stdio.jsHTTP:
export MCP_KEY="a-local-test-key"
npm run server:http
npx @modelcontextprotocol/inspectorIn Inspector, select Streamable HTTP, use http://127.0.0.1:3000/mcp, and add header Authorization: Bearer a-local-test-key. Verify:
add_task,list_tasks, andcomplete_taskare listed and callable.todo://listcan be read.plan_my_daycan be loaded.Completing an unknown ID returns
isError: true.
Project map
config.json agent/model/server configuration
skills/daily-plan/SKILL.md on-demand workflow
src/agent/ MCP host, Ollama loop, and skill loader
src/todo/ shared todo domain and MCP capabilities
src/servers/stdio.js stdio entry point
src/servers/http.js Streamable HTTP entry point
test/ unit and protocol integration testsGrading evidence
Requirement | Evidence |
Agent host |
|
stdio server |
|
Local HTTP |
|
Skill in agent |
|
Error handling | Zod validation, |
Tests |
|
Demo and submission checklist
YouTube video demo:
Show
npm testpassing.Show the stdio server in Inspector: tools, resource, and prompt.
Show the HTTP server returning 401 without the key, then connecting with it.
In the agent, add one task through each server.
Ask “Standup time” and show automatic skill loading plus calls to both servers.
Briefly open
config.jsonandSKILL.mdand explain the routing.
Submit the YouTube link and source code on Moodle. If you later deploy, also submit the public /mcp URL and a temporary grader key.
This server cannot be deployed
Maintenance
Related MCP Connectors
Persistent memory, hybrid search and a goal graph for AI agents, over stdio or remote HTTP.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
- mcpOAuthnet.todoist
Official Todoist MCP server for AI assistants to manage tasks, projects, and workflows.
Local-first task manager: create, edit, and complete tasks, projects, and checklists via MCP.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceA local-stdio MCP server for a single personal Todoist account with env-gated read-only mode and prompt-injection mitigations.221 npmMIT
- FlicenseAqualityBmaintenanceMCP server for Personal OS API that enables managing tasks, notes, projects, collections, reviews, and more through typed tools over stdio.66-
- FlicenseNot gradedqualityBmaintenanceA Model Context Protocol server that provides todo management via stdio, local HTTP, and public HTTPS transports, enabling agents to add, list, and complete tasks, and includes a daily standup skill.-
- AlicenseNot gradedqualityCmaintenanceA demo MCP server exposing an in-memory todo list via tools (add_task, list_tasks, complete_task), a resource, and a prompt, over both stdio and HTTP transports.1 npmISC