NoLag MCP
Realtime coordination for AI agents: manage apps, rooms, actors, publish, and dispatch tasks. Visit https://nolag.app and setup your account.
README
NoLag MCP Server
A hosted Model Context Protocol (MCP) server for NoLag. Connect Claude Desktop, Cursor, or any MCP-compatible client and let an AI agent manage your realtime infrastructure directly: create apps, rooms, and actors, publish messages, dispatch agent tasks, and manage access scopes, all through natural language.
- Homepage: https://nolag.app
- Full setup guide: https://nolag.app/docs/agents/mcp-setup
- Get an API key: https://portal.nolag.app (Settings → API Keys)
What is NoLag?
NoLag is realtime messaging infrastructure and the coordination layer for AI agents: pub/sub over WebSocket with presence, rooms, and quality-of-service delivery, high level SDKs for chat, notifications, and dashboards, and agent patterns to dispatch work, share state, observe decisions, and gate actions. SDKs for JavaScript, Go, and Python. This MCP server exposes a set of tools so an AI client can operate that infrastructure for you.
Endpoints
The server is remote (hosted). It supports two transports:
- SSE:
GET https://api.nolag.app/mcp/sse - Streamable HTTP:
POST https://api.nolag.app/mcp
Authentication uses a project-level API key (format nl_live_yourKeyId.yourSecret),
created in the Portal.
Connect
Claude Desktop / Claude Code
Add this to your MCP configuration (claude_desktop_config.json, or .mcp.json
in your project root for Claude Code):
{
"mcpServers": {
"nolag": {
"command": "npx",
"args": [
"mcp-remote",
"https://api.nolag.app/mcp/sse?token=nl_live_yourKeyId.yourSecret"
]
}
}
}
mcp-remote bridges the SSE transport to stdio and installs automatically via
npx on first run. Replace the token with your API key.
Cursor
Add the same block to .cursor/mcp.json.
Custom HTTP client
curl -X POST https://api.nolag.app/mcp \
-H "Authorization: Bearer nl_live_yourKeyId.yourSecret" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":"1","method":"initialize","params":{}}'
Run it locally (stdio)
Prefer a local stdio server over the hosted endpoint? This repo ships a thin
bridge that forwards to https://api.nolag.app/mcp. Listing tools needs no key;
tool execution uses your key from NOLAG_API_KEY.
{
"mcpServers": {
"nolag": {
"command": "npx",
"args": ["-y", "@nolag/mcp"],
"env": { "NOLAG_API_KEY": "nl_live_yourKeyId.yourSecret" }
}
}
}
Or with Docker:
docker build -t nolag-mcp .
docker run -i -e NOLAG_API_KEY=nl_live_yourKeyId.yourSecret nolag-mcp
Tools
The server exposes tools across NoLag's resources:
- Apps — create, list, update, and delete apps.
- Rooms — create, list, update, and delete rooms.
- Actors — create, list, update, and delete client identities and access tokens.
- Topics and messaging — publish messages to topics.
- Agents — dispatch tasks and coordinate multi-agent work.
- Access scopes — manage tenant isolation.
To verify your connection, ask your client to "list my NoLag apps" or "create an agent actor".
Links
- Docs: https://nolag.app/docs
- MCP setup guide: https://nolag.app/docs/agents/mcp-setup
- AI agents guide: https://nolag.app/docs/agents
- Portal: https://portal.nolag.app
License
MIT. See LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.