PacedLoop MCP Server
Enables interaction with the hosted PacedLoop API to manage workflows and monitor process runs. It provides tools for workflow CRUD operations, run execution management, and access to detailed performance analytics within MCP-capable clients.
README
pacedloop-mcp-server
Standalone MCP server for the hosted PacedLoop API.
This package is for users who want PacedLoop tools inside an MCP-capable client without running the full PacedLoop app locally.
What users need
- a PacedLoop account
- a PacedLoop API token
- Node.js 18+ installed locally
Hosted default:
https://www.pacedloop.com
What it exposes
- workflow CRUD
- run list, detail, start, advance, and repair
- analytics overview
- step analytics
- recent-run analytics
Quick start
- Clone this repository.
- Install dependencies:
npm install
- Set environment variables:
export PACEDLOOP_BASE_URL=https://www.pacedloop.com
export PACEDLOOP_API_TOKEN=your_pacedloop_token
PowerShell:
$env:PACEDLOOP_BASE_URL="https://www.pacedloop.com"
$env:PACEDLOOP_API_TOKEN="your_pacedloop_token"
- Start the server:
npm start
OpenClaw / NemoClaw setup
Use this process definition in your MCP client configuration:
Command:
npm
Args:
start
Working directory:
/path/to/pacedloop-mcp-server
Environment:
PACEDLOOP_BASE_URL=https://www.pacedloop.com
PACEDLOOP_API_TOKEN=your_pacedloop_token
If your MCP client supports launching a script directly, use:
Command:
node
Args:
/path/to/pacedloop-mcp-server/bin/pacedloop-mcp-server.mjs
Example OpenClaw-style config
OpenClaw/NemoClaw config shapes can vary by version, but this is the command block you want to represent:
{
"command": "npm",
"args": ["start"],
"cwd": "/path/to/pacedloop-mcp-server",
"env": {
"PACEDLOOP_BASE_URL": "https://www.pacedloop.com",
"PACEDLOOP_API_TOKEN": "your_pacedloop_token"
}
}
If your OpenClaw build expects direct script execution, use:
{
"command": "node",
"args": ["/path/to/pacedloop-mcp-server/bin/pacedloop-mcp-server.mjs"],
"env": {
"PACEDLOOP_BASE_URL": "https://www.pacedloop.com",
"PACEDLOOP_API_TOKEN": "your_pacedloop_token"
}
}
Publish as its own GitHub repo
From the parent directory:
cd pacedloop-mcp-server
git init
git add .
git commit -m "Initial standalone PacedLoop MCP server"
Then create a new GitHub repository and push:
git remote add origin git@github.com:YOUR_ORG_OR_USER/pacedloop-mcp-server.git
git branch -M main
git push -u origin main
Notes
- The server uses stdio and MCP JSON-RPC framing.
- The token is sent as a Bearer token to the PacedLoop API.
- Keep the API token on the local machine running the MCP client.
- This package is a thin adapter over the hosted PacedLoop backend, not a standalone workflow engine.
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.