Skip to main content
ClaudeWave
ES, Spanish
Skill2.9k estrellas del repoactualizado 6d ago

mcp-servers

# mcp-servers MCP Server Management provides built-in tools to add, remove, configure, and troubleshoot Model Context Protocol servers that extend an agent's capabilities through external tools. Use this skill when users need to connect external data sources or applications, manage server lifecycle operations like restart or removal, or diagnose connectivity and configuration issues with MCP servers running over stdio, SSE, or HTTP transports.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/moltis-org/moltis /tmp/mcp-servers && cp -r /tmp/mcp-servers/crates/skills/src/assets/devops/mcp-servers ~/.claude/skills/mcp-servers
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# MCP Server Management

Manage MCP (Model Context Protocol) servers that provide external tools to the agent.
MCP servers extend the agent's capabilities by exposing tools over stdio, SSE, or streamable-HTTP transports.

## Agent Tools

The agent has built-in tools for MCP management — no sandbox, network, or CLI needed:

- `mcp_list` — list all configured servers with status
- `mcp_add` — add a new server (params: `name`, `command`, `args`, `transport`, `url`, `env`, `display_name`)
- `mcp_remove` — remove a server (params: `name`)
- `mcp_status` — detailed status for a server (params: `name`)
- `mcp_restart` — restart a running server (params: `name`)

These are the preferred way to manage MCP servers from skills. Use them directly.

## RPC Methods

For advanced use or direct API access, the full RPC namespace is documented below.

## Listing Servers

```json
// RPC: mcp.list
```

Returns all configured servers with their connection status, transport type, and enabled state.

## Adding a Server

### Stdio transport (local process)

```json
// RPC: mcp.add
{
  "name": "filesystem",
  "command": "npx",
  "args": ["-y", "@modelcontextprotocol/server-filesystem", "/home/user/documents"]
}
```

### SSE transport (remote)

```json
// RPC: mcp.add
{
  "name": "remote-tools",
  "transport": "sse",
  "url": "https://mcp.example.com/sse"
}
```

### Streamable HTTP transport

```json
// RPC: mcp.add
{
  "name": "api-tools",
  "transport": "streamable-http",
  "url": "https://mcp.example.com/mcp"
}
```

### With environment variables

```json
// RPC: mcp.add
{
  "name": "github",
  "command": "npx",
  "args": ["-y", "@modelcontextprotocol/server-github"],
  "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_..." }
}
```

### With custom display name

```json
// RPC: mcp.add
{
  "name": "gbrain",
  "command": "gbrain",
  "args": ["serve", "--mcp"],
  "display_name": "GBrain Knowledge Base"
}
```

Returns `{ "ok": true, "name": "<final_name>" }`. If a server with the same name already exists, a numeric suffix is appended automatically (e.g. `github-2`).

## Removing a Server

```json
// RPC: mcp.remove
{ "name": "filesystem" }
```

## Updating a Server

Partial update — omitted fields keep their current values.

```json
// RPC: mcp.update
{
  "name": "github",
  "args": ["-y", "@modelcontextprotocol/server-github", "--verbose"],
  "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_new_token" }
}
```

## Enable / Disable

Toggle a server without removing its configuration.

```json
// RPC: mcp.enable
{ "name": "filesystem" }

// RPC: mcp.disable
{ "name": "filesystem" }
```

## Restart

Force-restart a running server (useful after config changes).

```json
// RPC: mcp.restart
{ "name": "filesystem" }
```

## Server Status

Detailed status for a single server including connection state, uptime, and error info.

```json
// RPC: mcp.status
{ "name": "filesystem" }
```

## List Tools

Show which tools a specific MCP server exposes.

```json
// RPC: mcp.tools
{ "name": "filesystem" }
```

## Global Config

```json
// RPC: mcp.config.get

// RPC: mcp.config.update
{ "request_timeout_secs": 120 }
```

The global `request_timeout_secs` applies to all servers that don't set their own timeout.
Per-server timeouts can be set via `mcp.update` with `request_timeout_secs`.

## OAuth

For MCP servers that require OAuth authentication:

```json
// RPC: mcp.oauth.start
{ "name": "my-oauth-server" }

// RPC: mcp.oauth.complete
{ "name": "my-oauth-server", "code": "auth_code_here" }

// RPC: mcp.reauth
{ "name": "my-oauth-server" }
```

## Transport Types

| Transport | When to Use | Required Fields |
|-----------|-------------|----------------|
| `stdio` (default) | Local process, fast, no network | `command`, optional `args`, `env` |
| `sse` | Remote server, Server-Sent Events | `url` |
| `streamable-http` | Remote server, HTTP streaming | `url` |

## Common Patterns

### GBrain knowledge base

```json
// RPC: mcp.add
{
  "name": "gbrain",
  "command": "gbrain",
  "args": ["serve", "--mcp"],
  "display_name": "GBrain Knowledge Base"
}
```

Requires: `bun install -g gbrain && gbrain init`

### GitHub tools

```json
// RPC: mcp.add
{
  "name": "github",
  "command": "npx",
  "args": ["-y", "@modelcontextprotocol/server-github"],
  "env": { "GITHUB_PERSONAL_ACCESS_TOKEN": "ghp_..." }
}
```

### Filesystem access

```json
// RPC: mcp.add
{
  "name": "filesystem",
  "command": "npx",
  "args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/allowed/directory"]
}
```

### Memory / persistent storage

```json
// RPC: mcp.add
{
  "name": "memory",
  "command": "npx",
  "args": ["-y", "@modelcontextprotocol/server-memory"]
}
```

## Troubleshooting

1. **Server won't connect?** Check `mcp.status` for error details. For stdio servers, verify the command is in PATH.
2. **Tools not appearing?** Use `mcp.tools` to see what the server exposes. Try `mcp.restart` to force reconnection.
3. **Timeout errors?** Increase `request_timeout_secs` via `mcp.config.update` or per-server via `mcp.update`.
4. **OAuth errors?** Run `mcp.reauth` to restart the OAuth flow.
5. **Environment variables?** Sensitive values (API keys, tokens) go in the `env` field of the server config.
1passwordSkill

Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.

apple-notesSkill

Manage Apple Notes via the memo CLI on macOS (create, view, search, edit).

apple-remindersSkill

Manage Apple Reminders via remindctl CLI (list, add, complete, delete).

architecture-diagramSkill

Generate dark-themed SVG diagrams of software systems and cloud infrastructure as standalone HTML files with inline SVG graphics. Semantic component colors (cyan=frontend, emerald=backend, violet=database, amber=cloud/AWS, rose=security, orange=message bus), JetBrains Mono font, grid background. Best suited for software architecture, cloud/VPC topology, microservice maps, service-mesh diagrams, database + API layer diagrams, security groups, message buses — anything that fits a tech-infra deck with a dark aesthetic. If a more specialized diagramming skill exists for the subject (scientific, educational, hand-drawn, animated, etc.), prefer that — otherwise this skill can also serve as a general-purpose SVG diagram fallback. Based on Cocoon AI's architecture-diagram-generator (MIT).

arxivSkill

Search and retrieve academic papers from arXiv using their free REST API. No API key needed. Search by keyword, author, category, or ID. Combine with web_extract or the ocr-and-documents skill to read full paper content.

ascii-artSkill

Generate ASCII art using pyfiglet (571 fonts), cowsay, boxes, toilet, image-to-ascii, remote APIs (asciified, ascii.co.uk), and LLM fallback. No API keys required.

ascii-videoSkill

Production pipeline for ASCII art video — any format. Converts video/audio/images/generative input into colored ASCII character video output (MP4, GIF, image sequence). Covers: video-to-ASCII conversion, audio-reactive music visualizers, generative ASCII art animations, hybrid video+audio reactive, text/lyrics overlays, real-time terminal rendering. Use when users request: ASCII video, text art video, terminal-style video, character art animation, retro text visualization, audio visualizer in ASCII, converting video to ASCII art, matrix-style effects, or any animated ASCII output.

audiocraft-audio-generationSkill

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.