mcp
Model Context Protocol server management and tool integration
What this skill does
# MCP - Complete API Reference
Manage Model Context Protocol (MCP) servers, external tools, and AI integrations.
---
## Chat Commands
### Server Management
```
/mcp list List configured MCP servers
/mcp status Check server connection status
/mcp add <name> <command> Add new MCP server
/mcp remove <name> Remove MCP server
/mcp restart <name> Restart server
```
### Tool Interaction
```
/mcp tools List available tools
/mcp tools <server> Tools from specific server
/mcp call <server> <tool> [args] Call a tool directly
/mcp resources <server> List server resources
```
### Configuration
```
/mcp config <server> View server config
/mcp config <server> set <key> <value> Update config
/mcp logs <server> View server logs
```
---
## TypeScript API Reference
### Create MCP Client
```typescript
import { createMCPClient } from 'clodds/mcp';
const mcp = createMCPClient({
// Transport
transport: 'stdio', // 'stdio' | 'sse'
// Server command
command: 'npx',
args: ['-y', '@modelcontextprotocol/server-filesystem'],
// Options
timeout: 30000,
retries: 3,
});
```
### Connect to Server
```typescript
// Connect
await mcp.connect();
// Check status
const status = mcp.getStatus();
console.log(`Connected: ${status.connected}`);
console.log(`Server: ${status.serverInfo?.name}`);
console.log(`Version: ${status.serverInfo?.version}`);
// Disconnect
await mcp.disconnect();
```
### List Tools
```typescript
// Get available tools
const tools = await mcp.listTools();
for (const tool of tools) {
console.log(`${tool.name}: ${tool.description}`);
console.log(` Input schema: ${JSON.stringify(tool.inputSchema)}`);
}
```
### Call Tool
```typescript
// Call a tool
const result = await mcp.callTool({
name: 'read_file',
arguments: {
path: '/path/to/file.txt',
},
});
console.log(`Result: ${JSON.stringify(result)}`);
```
### List Resources
```typescript
// Get available resources
const resources = await mcp.listResources();
for (const resource of resources) {
console.log(`${resource.uri}: ${resource.name}`);
console.log(` Type: ${resource.mimeType}`);
}
// Read a resource
const content = await mcp.readResource('file:///path/to/file.txt');
console.log(content);
```
### List Prompts
```typescript
// Get available prompts
const prompts = await mcp.listPrompts();
for (const prompt of prompts) {
console.log(`${prompt.name}: ${prompt.description}`);
}
// Get prompt content
const prompt = await mcp.getPrompt('code-review', {
code: 'function add(a, b) { return a + b; }',
});
console.log(prompt.messages);
```
### MCP Registry
```typescript
import { createMCPRegistry } from 'clodds/mcp';
const registry = createMCPRegistry({
configPath: './mcp-servers.json',
});
// Add server
registry.addServer({
name: 'filesystem',
command: 'npx',
args: ['-y', '@modelcontextprotocol/server-filesystem', '/home/user'],
env: {},
});
// List servers
const servers = registry.listServers();
// Get server
const server = registry.getServer('filesystem');
// Remove server
registry.removeServer('filesystem');
// Start all servers
await registry.startAll();
// Stop all servers
await registry.stopAll();
```
---
## Popular MCP Servers
| Server | Purpose | Install |
|--------|---------|---------|
| **filesystem** | File operations | `@modelcontextprotocol/server-filesystem` |
| **github** | GitHub API | `@modelcontextprotocol/server-github` |
| **postgres** | Database queries | `@modelcontextprotocol/server-postgres` |
| **brave-search** | Web search | `@modelcontextprotocol/server-brave-search` |
| **puppeteer** | Browser automation | `@modelcontextprotocol/server-puppeteer` |
---
## Server Configuration
```json
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/home/user"],
"env": {}
},
"github": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_TOKEN": "ghp_..."
}
}
}
}
```
---
## CLI Commands
```bash
# List MCP servers
clodds mcp list
# Add MCP server
clodds mcp add filesystem "npx -y @modelcontextprotocol/server-filesystem /home"
# Test server connection
clodds mcp test filesystem
# Remove server
clodds mcp remove filesystem
```
---
## Best Practices
1. **Use official servers** — Start with well-tested MCP servers
2. **Limit file access** — Restrict filesystem server to specific directories
3. **Secure credentials** — Use env vars for tokens, not command args
4. **Monitor logs** — Check server logs for errors
5. **Timeout handling** — Set appropriate timeouts for slow operations
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.