pipeline-mcp

Use Pipeline — an AI-powered LinkedIn outreach platform — directly from Claude Code, Cursor, Codex, Claude Desktop, or any MCP-aware AI agent.

75 tools for campaigns, prospects, enrichment, research, signals, content, CRM, conversations, analytics, workflows, and composite automations (zero-to-outreach, build-campaign-from-table).

v2.1 is a thin proxy. All tools live on the server at pipeline.help/api/mcp-server. When Pipeline ships a feature, this client sees it immediately — no updates, no drift.

Install

Claude Code

Add to ~/.claude.json (or run claude mcp add):

{
  "mcpServers": {
    "pipeline": {
      "command": "npx",
      "args": ["-y", "pipeline-mcp", "--api-key", "pipeline_pk_YOUR_KEY"]
    }
  }
}

Cursor

Add to your Cursor MCP config:

{
  "mcpServers": {
    "pipeline": {
      "command": "npx",
      "args": ["-y", "pipeline-mcp", "--api-key", "pipeline_pk_YOUR_KEY"]
    }
  }
}

Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "pipeline": {
      "command": "npx",
      "args": ["-y", "pipeline-mcp", "--api-key", "pipeline_pk_YOUR_KEY"]
    }
  }
}

Codex CLI

codex mcp add pipeline npx -y pipeline-mcp --api-key pipeline_pk_YOUR_KEY

Any MCP-aware client

Run pipeline-mcp --api-key pipeline_pk_YOUR_KEY and point your client at its stdio. Or run as HTTP:

pipeline-mcp --http --port 3000 --api-key pipeline_pk_YOUR_KEY

Get an API key

1. Sign in at pipeline.help
2. Settings → API Keys → Create new key
3. Copy the key (shown only once). Format: pipeline_pk_...

Global install

npm i -g pipeline-mcp

Then reference pipeline-mcp directly in your MCP config (skip the npx -y prefix).

Configuration

| Flag | Env | Default | Purpose | |---|---|---|---| | --api-key <key> | PIPELINE_API_KEY | — | Required for stdio | | --base-url <url> | PIPELINE_BASE_URL | https://www.pipeline.help/api | Override for self-hosted / staging | | --http | — | off | Run as local HTTP proxy instead of stdio | | --port <n> | — | 3000 | Port for --http mode | | --version | — | — | Print version | | --help | — | — | Print help |

Tokens vs latency

MCP is great for agentic flows where the AI explores and chains tools. For deterministic "just-do-it" operations, you'll burn fewer tokens with the companion CLI:

npm i -g @pipeline/cli
pipeline login
pipeline list-campaigns --status active

Same auth, same tool surface, zero AI in the loop. See the CLI README.

How it works

Claude Code / Cursor / Codex
        │  (stdio, MCP protocol)
        ▼
    pipeline-mcp (this package, ~250 LOC)
        │  (HTTPS, JSON-RPC 2.0)
        ▼
https://www.pipeline.help/api/mcp-server
        │
        ▼
    75 tools (campaigns, prospects, signals, CRM, …)

All schemas and handlers live on the server. This package is a thin layer of network plumbing. When Pipeline adds a tool, it's immediately callable — no npm update required.

License

MIT © Pipeline