Advertise
MCP.so
Sign In

PubNub MCP Server for Cursor IDE

@stephenlb

Repository

Basic information

Category

Developer Tools

Transports

stdio

Author

stephenlb

About PubNub MCP Server for Cursor IDE

PubNub MCP Model Context Protocol Server for use in Cursor, Claude Desktop, Claude Code and OpenAI Codex and more!

PubNub MCP Server for Cursor IDE config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "pubnub-mcp-server-stephenlb": {
      "command": "npx",
      "args": [
        "-y",
        "@pubnub/mcp"
      ]
    }
  }
}

PubNub MCP Server for Cursor IDE tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is PubNub Model Context Protocol (MCP) Server for Cursor IDE?

The PubNub Model Context Protocol (MCP) Server for Cursor IDE is a CLI-based MCP server that exposes PubNub SDK documentation and PubNub Functions resources to LLM-powered tools, enabling prompt-driven access to PubNub capabilities.

How to use PubNub Model Context Protocol (MCP) Server for Cursor IDE?

Install via npx -y @pubnub/mcp (requires Node.js >= 18). Configure in Cursor IDE by adding a mcp.json entry with command: "npx", args: ["-y", "@pubnub/mcp"], and optional PubNub keys as environment variables. Invoke resources like pubnub://docs/javascript or tools like publish_pubnub_message from the chat interface.

Key features of PubNub Model Context Protocol (MCP) Server for Cursor IDE

  • Fetches formatted PubNub JavaScript, Python, and Java SDK documentation
  • Accesses PubNub Functions documentation from a static Markdown file
  • Publishes messages to PubNub channels
  • Lists available PubNub Functions
  • Retrieves message history and presence information
  • Works with Cursor IDE, Claude Code, and Claude Desktop

Use cases of PubNub Model Context Protocol (MCP) Server for Cursor IDE

  • Query PubNub SDK docs directly from an LLM chat (e.g., "Show me JavaScript SDK docs for subscribe()")
  • Publish messages to PubNub channels using natural language prompts
  • List available PubNub Functions resources
  • Fetch Python or Java SDK documentation for specific methods

Frequently asked questions

1

What are the runtime requirements?

Node.js >= 18 and npm are required.

2

Do I need a PubNub account and API keys?

A PubNub account and API keys are optional for live actions like publishing messages; the server can still serve static documentation without them.

3

How do I configure the server in Cursor IDE?

Add a `mcp.json` entry (global at `~/.cursor/mcp.json` or project-level `.cursor/mcp.json`) with the command `npx`, args `["-y", "@pubnub/mcp"]`, and optionally set environment variables for `PUBNUB_SUBSCRIBE_KEY` and `PUBNUB_PUBLISH_KEY`.

4

What transport protocol does the server use?

The server communicates over STDIN/STDOUT using JSON-RPC v2.0.

5

What documentation resources are available?

Resources include PubNub JavaScript, Python, and Java SDK docs, plus a static Markdown file for PubNub Functions.

Comments

More Developer Tools MCP servers

OpenMark

OpenMark AI

OpenMark is a remote MCP server available at https://openmark.ai. Benchmark your own prompt on 100+ models with real API calls.

Modelglass

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

1

Routebase

Routebase

Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.

ArtiBot Cloud MCP - Zhijiangyun 智匠云

bofob

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation

1

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

3
Advertise