mu
OfficialProvides web search via the Brave Search API, enabling agents to search the web and fetch clean page text.
Allows interaction with the agent from Discord via commands like /agent, /news, /markets, /weather, and more.
Allows sign-in with Google OAuth, providing authentication for the web app.
Can use local Ollama models as the AI provider for the agent, enabling private and offline operation.
Can use OpenAI or any OpenAI-compatible endpoint as the AI provider for the agent.
Aggregates news from RSS feeds, providing tools to list, read, and search articles across configured feeds.
Allows interaction with the agent from Telegram via commands like /agent, /ask, /news, and more.
Supports passkey/WebAuthn authentication for passwordless sign-in.
Provides video search and listing from curated YouTube channels, without ads or recommendations.
Click on "Install 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., "@muwhat's the weather in San Francisco?"
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.
Mu
Tools for agents.
Overview
Mu is an open-source runtime for agents, tools and services.
It includes Micro, a personal assistant that has access to all the tools and services.
Related MCP server: hidrix-tools
How it works
Mu is a monolothic codebase: the runtime, services, archive, inbox and agent system all in one host. Services operate as building blocks for agents — mail, chat, news, video, search, markets, weather and more. Data gets archived locally so it stays searchable and becomes contextual memory. Services and the archive become tools for Micro and any other agents you create.
Micro is the first agent and the one you use for everything. It answers by default and can be reached from the web, email, SMS, WhatsApp or the CLI.
Mu comes with a unified inbox for mail, chat, SMS, WhatsApp, notes, tasks and agent activity, bringing communication and agent work into one place.
Features
What's included:
Micro - The default personal assistant and the front door to the system.
Clients - Use Micro via Web, SMS, email, WhatsApp and more. Requires setup.
Services - 30+ services including news, mail, markets and video, accessible via API, CLI or the Web.
Agents - Micro answers by default; define your own by name, prompt and tools, then chat via the web.
Inbox - A single place to keep track of chats, notes, tasks, etc. Assign tasks to agents or reply directly.
Agents
Mu is the runtime. Micro is the first agent and the one people meet first.
Micro is the default personal assistant. General purpose, with the services above as its tools, so it can answer from what is true now rather than only from what a model remembers: the news this morning, the price this minute, your own mail.
Code is the second, and is not finished. It builds things on a machine of its own — writes the files, runs them, hosts the result — and what it makes outlives the conversation.
Your own agents are the same shape: a name, an instruction, and the tools they may reach. Each has an address, so agent+yours@ reaches it from anywhere that can send mail, the same way agent@ reaches Micro.
Install
Quick install guide for self hosting (let us know if it's broken).
curl -fsSL https://raw.githubusercontent.com/micro/mu/main/install.sh | sh
mu --serveOpen http://localhost:8080. The first account you create is the admin.
Quite a few things need API keys, but here's some must haves.
For | Set | Notes |
AI models |
| free if you run Ollama locally |
Web search |
| Brave has a free tier |
Video |
| free quota |
Follow setup in CLI
mu setup # pick an AI provider, paste a key
mu --serveEverything else — mail, Google sign-in, Stripe for payments, etc — is optional.
The binary is a client, and by default it calls https://micro.mu — the hosted Mu instance where Micro runs publicly. Running your own? Point it there:
mu login https://your.host # saves the address and a token
mu config get # says which instance is in use, and whyWithout that, mu news list on the machine you just installed calls the hosted instance rather than the one you are running. MU_URL and --url override per shell and per command.
Other ways to run it:
# Docker
git clone https://github.com/micro/mu && cd mu
docker compose up
# From source
git clone https://github.com/micro/mu
cd mu && go install
mu --serveSee the installation guide.
CLI
Every service is a mu subcommand
mu news list # latest headlines
mu news search "ai safety" # search news
mu web search "claude code" # search the web
mu markets list --category stocks # live prices
mu weather forecast --lat 51.5 --lon -0.12
mu docs list --collection notes # your own documents
mu x402 # paying per call: config, and your key
mu help # full tool listEvery tool is a command: the service, then the method. The underscore form works too, so mu news list and mu news_list are the same call.
To authenticate
mu login # opens /token in your browser, paste the PAT back
mu config set token xxx # or set it directly
export MU_TOKEN=xxx # or use the environmentRun mu --help for the list — it reads the same catalogue the agent does.
To talk to Micro instead, use mu ask — it runs on the instance, so it needs your token and no model key of your own:
mu ask "what is in my inbox?"
mu ask --agent research "anything new this week?"mu agent is the other direction and easy to reach for by mistake: it runs the agent here, on your machine, with your own model key, renting tools from an instance over x402 and paying per call. Same word in English, opposite ways round.
API
Every service has a HTTP endpoint, at /api/v1/<service>/<method>.
curl https://micro.mu/api/v1/ # the catalogue
curl "https://micro.mu/api/v1/news/list?limit=5" # arguments in the query
curl -X POST https://micro.mu/api/v1/news/list \
-H 'Content-Type: application/json' -d '{"limit":5}'Authenticate with a token from /token as Authorization: Bearer, or with an OAuth client. A priced endpoint answers 402 without one, which an x402 client pays per call with no account at all.
For Tools via MCP use /mcp. See /tools for more info.
Web
/- talk to Micro/home— an overview of everything going on./inbox— the place to see chats, mail, tasks, etc./agents— your agents, and where you make a new one./services—/news,/weather,/markets, etc.
Configuration
Some files are embedded in the binary, so editing means rebuilding:
home/cards.json— home screen cardsservice/news/feeds.json— RSS news feedsservice/chat/prompts.json— chat topicsservice/video/channels.json— YouTube channelsservice/places/locations.json— saved locations
See Install for every setting the code reads.
The rest lives in /admin/config on the server.
License
AGPL 3.0
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
Pocket Agent (aipocketagent.com) MCP server — read tools for personas, apps, and product info.
- UnifAPIOAuthcom.unifapi
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceMCP server giving AI agents real-time web search, page scraping, company intelligence, email discovery, local lead generation, and a persistent knowledge graph. Pay only for what you use, no subscriptions.24MIT
- AlicenseNot gradedqualityFmaintenanceMCP tool server that gives any AI agent the ability to search, scrape, and analyze content across the internet.42MIT
- FlicenseAqualityBmaintenanceA production-grade MCP server that provides a centralized microservice toolkit for LLM agents, enabling web search and extensible tool integration.1-
- AlicenseNot gradedqualityBmaintenanceMCP server that gives AI agents a durable identity, persistent browser, memory, and coordination tools, enabling them to maintain state across sessions and act on the live web.3MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/micro/mu'
If you have feedback or need assistance with the MCP directory API, please join our Discord server