Centralized management and registration of MCP servers for AI agent tooling.

Install

mkdir -p .claude/skills/mcpmu && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/19453" && unzip -o skill.zip -d .claude/skills/mcpmu && rm skill.zip

Installs to .claude/skills/mcpmu

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Install, set up, and manage MCP servers using the mcpmu CLI. Use when the user wants to install mcpmu, register it as an MCP server in Claude Code, add/remove/list MCP servers, manage namespaces, set tool permissions, or expose servers via serve mode.
251 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Register and manage multiple MCP servers
  • Group servers into namespaces
  • Configure tool-level permissions
  • Expose multiple servers as a single endpoint
  • Monitor server logs via TUI

How it works

mcpmu acts as a multiplexer that aggregates multiple MCP server configurations into a single endpoint, allowing agents to interact with them through one interface.

Inputs & outputs

You give it
MCP server command or URL
You get back
Unified MCP endpoint configuration

When to use mcpmu

  • Install and register MCP servers
  • Manage namespaces for MCP tools
  • Expose local servers to AI agents
  • Remove unused MCP configurations

About this skill

mcpmu — MCP Server Manager

mcpmu is a multiplexing MCP server manager. You configure MCP servers once in mcpmu, then expose them as a single unified MCP endpoint to any agent (Claude Code, Codex, Cursor, Windsurf, etc.).

Installing mcpmu

First check if mcpmu is already installed:

which mcpmu

If not installed, install via Homebrew (preferred) or Go:

Homebrew (macOS/Linux):

brew tap Bigsy/tap && brew install mcpmu

From source (requires Go):

go install github.com/Bigsy/mcpmu/cmd/mcpmu@latest

Registering mcpmu as an MCP Server in Claude Code

After installing mcpmu, register it so Claude Code can use all mcpmu-managed servers through a single endpoint:

Default (all servers, default namespace):

claude mcp add mcpmu -- mcpmu serve --stdio

Specific namespace:

claude mcp add work -- mcpmu serve --stdio --namespace work

With management tools (lets Claude add/remove servers via MCP):

claude mcp add mcpmu -- mcpmu serve --stdio --expose-manager-tools

You can verify the registration:

claude mcp list

To remove mcpmu from Claude Code:

claude mcp remove mcpmu

Scoped registration

Claude Code supports different scopes for MCP server registration:

claude mcp add mcpmu --scope user -- mcpmu serve --stdio       # available in all projects
claude mcp add mcpmu --scope project -- mcpmu serve --stdio    # this project only

Full Setup Walkthrough

To go from zero to a working mcpmu setup in Claude Code:

  1. Install mcpmu: brew tap Bigsy/tap && brew install mcpmu
  2. Add some MCP servers: mcpmu add context7 -- npx -y @upstash/context7-mcp
  3. Optionally create a namespace: mcpmu namespace add work --description "Work tools"
  4. Assign servers to it: mcpmu namespace assign work context7
  5. Register with Claude Code: claude mcp add mcpmu -- mcpmu serve --stdio
  6. Restart Claude Code — all mcpmu-managed tools are now available

Adding Servers

Stdio servers (local processes)

mcpmu add <name> -- <command> [args...]

Examples:

mcpmu add context7 -- npx -y @upstash/context7-mcp
mcpmu add filesystem -- npx -y @modelcontextprotocol/server-filesystem /tmp
mcpmu add my-server --env FOO=bar --cwd /path -- ./server --flag
mcpmu add auto-server --autostart -- ./server  # start on app launch

HTTP servers (remote endpoints)

mcpmu add <name> <url> [flags]

Examples:

mcpmu add atlassian https://mcp.atlassian.com/mcp --scopes read,write
mcpmu add figma https://mcp.figma.com/mcp --bearer-env FIGMA_TOKEN

OAuth login (for HTTP servers that need it)

mcpmu mcp login <server>
mcpmu mcp login atlassian --scopes read,write
mcpmu mcp logout <server>

Listing and Managing Servers

mcpmu list              # human-readable list
mcpmu list --json       # JSON output
mcpmu remove <name>     # remove (prompts for confirmation)
mcpmu remove <name> --yes  # skip confirmation
mcpmu rename <old> <new>   # rename (updates namespace/permission refs)

Namespaces

Namespaces group servers into profiles — e.g. work, personal, minimal. The namespace subcommand can also be shortened to ns.

mcpmu namespace add <name> --description "desc"
mcpmu namespace list [--json]
mcpmu namespace remove <name> [--yes]
mcpmu namespace assign <namespace> <server>
mcpmu namespace unassign <namespace> <server>
mcpmu namespace default <name>
mcpmu namespace rename <old> <new>
mcpmu namespace set-deny-default <namespace> <true|false>

Common namespace patterns

Create separate profiles:

mcpmu namespace add work --description "Work servers"
mcpmu namespace add personal --description "Personal projects"
mcpmu namespace assign work atlassian
mcpmu namespace assign work context7
mcpmu namespace assign personal context7

Create a minimal namespace that denies all tools by default, then allowlist:

mcpmu namespace add minimal --description "Lean toolset"
mcpmu namespace set-deny-default minimal true
mcpmu permission set minimal context7 resolve allow

Tool Permissions

Control which tools each server exposes per namespace:

mcpmu permission list <namespace> [--json]
mcpmu permission set <namespace> <server> <tool> <allow|deny>
mcpmu permission unset <namespace> <server> <tool>

Examples:

mcpmu permission set work atlassian jira_search allow
mcpmu permission set work atlassian confluence_delete deny

Serve Mode

Expose managed servers as a single MCP endpoint:

mcpmu serve --stdio                          # default namespace
mcpmu serve --stdio --namespace work         # specific namespace
mcpmu serve --stdio -n work --eager          # pre-start all servers
mcpmu serve --stdio --expose-manager-tools   # include mcpmu.* management tools
mcpmu serve --stdio --log-level debug        # verbose logging

Flags:

  • -n, --namespace — namespace to expose
  • --eager — pre-start all servers (default: lazy/on-demand)
  • --expose-manager-tools — include mcpmu.* tools in tools/list
  • -l, --log-level — debug, info, warn, error

Connecting mcpmu to Other Agents

For Claude Code registration, see "Registering mcpmu as an MCP Server in Claude Code" above.

For other agents:

Codex:

codex mcp add mcpmu -- mcpmu serve --stdio

Any MCP config JSON (Cursor, Windsurf, etc.):

{
  "mcpmu": {
    "command": "mcpmu",
    "args": ["serve", "--stdio"]
  }
}

For a namespace-specific entry:

{
  "work": {
    "command": "mcpmu",
    "args": ["serve", "--stdio", "--namespace", "work"]
  }
}

Interactive TUI

Run mcpmu with no arguments to open the terminal UI for visual server management, log monitoring, and namespace switching.

Config

Config lives at ~/.config/mcpmu/config.json. All commands support --config / -c to use a custom config path.

Shell Completions

# zsh (Homebrew)
mcpmu completion zsh > "$(brew --prefix)/share/zsh/site-functions/_mcpmu"

# bash
mcpmu completion bash > /etc/bash_completion.d/mcpmu

# fish
mcpmu completion fish > ~/.config/fish/completions/mcpmu.fish

When not to use it

  • Directly connecting to single-server endpoints without multiplexing needs

Prerequisites

mcpmu CLIGo (for source installation)

Limitations

  • Requires mcpmu CLI installation
  • Config file located at ~/.config/mcpmu/config.json

How it compares

It centralizes management of multiple MCP servers into a single unified endpoint rather than configuring each server individually in the agent.

Compared to similar skills

mcpmu side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
mcpmu (this skill)04moReviewIntermediate
telegram-bot-builder1066moReviewIntermediate
mcp-integration218moReviewIntermediate
n8n-workflow-patterns161moNo flagsAdvanced

Try saying

Example prompts that trigger this skill in your AI assistant.

More by diegosouzapw

View all by diegosouzapw

helm-chart-scaffolding-v2

diegosouzapw

Helm Chart Scaffolding workflow skill. Use this skill when the user needs Comprehensive guidance for creating, organizing, and managing Helm charts for packaging and deploying Kubernetes applications and the operator should preserve the upstream workflow, copied support files, and provenance before

00

cc-skill-coding-standards-v2

diegosouzapw

Coding Standards & Best Practices workflow skill. Use this skill when the user needs Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development and the operator should preserve the upstream workflow, copied support files, and provenance before

00

worktree-setup

diegosouzapw

Automatically invoked after `git worktree add` to create data/shared symlink and data/local directory. Required before starting work in any new worktree.

00

parsehub-automation

diegosouzapw

Automate Parsehub tasks via Rube MCP (Composio). Always search tools first for current schemas.

00

signalwire-agents-sdk

diegosouzapw

Expert assistance for building SignalWire AI Agents in Python. Automatically activates when working with AgentBase, SWAIG functions, skills, SWML, voice configuration, DataMap, or any signalwire_agents code. Provides patterns, best practices, and complete working examples.

00

agent-sales-engineer

diegosouzapw

Expert sales engineer specializing in technical pre-sales, solution architecture, and proof of concepts. Masters technical demonstrations, competitive positioning, and translating complex technology into business value for prospects and customers.

00

You might also like

telegram-bot-builder

davila7

Expert in building Telegram bots that solve real problems - from simple automation to complex AI-powered bots. Covers bot architecture, the Telegram Bot API, user experience, monetization strategies, and scaling bots to thousands of users. Use when: telegram bot, bot api, telegram automation, chat bot telegram, tg bot.

106130

mcp-integration

anthropics

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

21123

n8n-workflow-patterns

czlonkowski

Proven workflow architectural patterns from real n8n workflows. Use when building new workflows, designing workflow structure, choosing workflow patterns, planning workflow architecture, or asking about webhook processing, HTTP API integration, database operations, AI agent workflows, or scheduled tasks.

16115

n8n-code-javascript

czlonkowski

Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with $helpers, working with dates using DateTime, troubleshooting Code node errors, or choosing between Code node modes.

7122

n8n-expression-syntax

czlonkowski

Validate n8n expression syntax and fix common errors. Use when writing n8n expressions, using {{}} syntax, accessing $json/$node variables, troubleshooting expression errors, or working with webhook data in workflows.

6111

n8n-node-configuration

czlonkowski

Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node_essentials and get_node_info, or learning common configuration patterns by node type.

7108

Search skills

Search the agent skills registry