mcp-transport-websocket-setup
Configure WebSocket transport for bidirectional MCP communication with connection management and reconnection handling.
What this skill does
# MCP Transport WebSocket Setup
Configure WebSocket transport for bidirectional MCP communication.
## Capabilities
- Configure WebSocket transport for MCP
- Implement connection lifecycle management
- Set up reconnection with backoff
- Handle message framing
- Implement heartbeat/ping-pong
- Configure secure WebSocket (WSS)
## Usage
Invoke this skill when you need to:
- Set up bidirectional MCP communication
- Implement WebSocket-based MCP transport
- Configure connection management
- Enable real-time bidirectional messaging
## Inputs
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| language | string | Yes | Target language |
| server | boolean | No | Generate server code (default: true) |
| client | boolean | No | Generate client code (default: false) |
| secure | boolean | No | Use WSS (default: true) |
## Generated Patterns
### TypeScript WebSocket Server
```typescript
import { WebSocketServer, WebSocket } from 'ws';
import { Server } from '@modelcontextprotocol/sdk/server/index.js';
interface Connection {
ws: WebSocket;
server: Server;
lastPing: number;
}
const connections = new Map<string, Connection>();
const wss = new WebSocketServer({
port: parseInt(process.env.WS_PORT || '8080'),
path: '/mcp',
});
// Heartbeat interval
const HEARTBEAT_INTERVAL = 30000;
wss.on('connection', (ws, req) => {
const connectionId = crypto.randomUUID();
console.log(`New connection: ${connectionId}`);
// Create MCP server for this connection
const server = new Server(
{ name: 'my-mcp-server', version: '1.0.0' },
{ capabilities: { tools: {}, resources: {} } }
);
// Register handlers
registerToolHandlers(server);
// Store connection
connections.set(connectionId, {
ws,
server,
lastPing: Date.now(),
});
// Handle messages
ws.on('message', async (data) => {
try {
const message = JSON.parse(data.toString());
await handleMessage(connectionId, message);
} catch (error) {
console.error('Failed to process message:', error);
ws.send(JSON.stringify({
jsonrpc: '2.0',
error: { code: -32700, message: 'Parse error' },
}));
}
});
// Handle close
ws.on('close', () => {
console.log(`Connection closed: ${connectionId}`);
connections.delete(connectionId);
});
// Handle errors
ws.on('error', (error) => {
console.error(`Connection error: ${connectionId}`, error);
});
// Respond to pings
ws.on('pong', () => {
const conn = connections.get(connectionId);
if (conn) conn.lastPing = Date.now();
});
});
// Heartbeat check
setInterval(() => {
const now = Date.now();
connections.forEach((conn, id) => {
if (now - conn.lastPing > HEARTBEAT_INTERVAL * 2) {
console.log(`Terminating stale connection: ${id}`);
conn.ws.terminate();
connections.delete(id);
} else {
conn.ws.ping();
}
});
}, HEARTBEAT_INTERVAL);
async function handleMessage(connectionId: string, message: any) {
const conn = connections.get(connectionId);
if (!conn) return;
// Process MCP message and send response
// Implementation depends on message type
}
console.log(`WebSocket MCP Server running on port ${process.env.WS_PORT || 8080}`);
```
### TypeScript WebSocket Client
```typescript
import WebSocket from 'ws';
interface MCPClientOptions {
url: string;
reconnect?: boolean;
maxRetries?: number;
}
class MCPWebSocketClient {
private ws: WebSocket | null = null;
private reconnectAttempts = 0;
private maxRetries: number;
private reconnectDelay = 1000;
constructor(private options: MCPClientOptions) {
this.maxRetries = options.maxRetries ?? 5;
}
async connect(): Promise<void> {
return new Promise((resolve, reject) => {
this.ws = new WebSocket(this.options.url);
this.ws.on('open', () => {
console.log('Connected to MCP server');
this.reconnectAttempts = 0;
this.reconnectDelay = 1000;
resolve();
});
this.ws.on('message', (data) => {
const message = JSON.parse(data.toString());
this.handleMessage(message);
});
this.ws.on('close', () => {
console.log('Disconnected from MCP server');
if (this.options.reconnect) {
this.attemptReconnect();
}
});
this.ws.on('error', (error) => {
console.error('WebSocket error:', error);
reject(error);
});
});
}
private attemptReconnect() {
if (this.reconnectAttempts >= this.maxRetries) {
console.error('Max reconnection attempts reached');
return;
}
this.reconnectAttempts++;
const delay = this.reconnectDelay * Math.pow(2, this.reconnectAttempts - 1);
console.log(`Reconnecting in ${delay}ms (attempt ${this.reconnectAttempts})`);
setTimeout(() => {
this.connect().catch(() => {
// Will trigger another reconnect attempt
});
}, delay);
}
async send(message: any): Promise<void> {
if (!this.ws || this.ws.readyState !== WebSocket.OPEN) {
throw new Error('Not connected');
}
this.ws.send(JSON.stringify(message));
}
private handleMessage(message: any) {
// Handle incoming MCP messages
console.log('Received:', message);
}
close() {
this.options.reconnect = false;
this.ws?.close();
}
}
```
## Workflow
1. **Configure server** - WebSocket server setup
2. **Add handlers** - Message processing
3. **Implement heartbeat** - Connection health
4. **Add reconnection** - Client reconnection
5. **Configure security** - WSS setup
6. **Add monitoring** - Connection metrics
## Target Processes
- mcp-transport-layer
- mcp-server-bootstrap
- mcp-client-implementation
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($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.