mcp

Simple example of MCP server with dynamic tools creation from Pipedrive openapi specification

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

Command

claude mcp add --transport stdio schipiga-mcp-server node server.js \
  --env OPENAI_API_KEY="your-openai-api-key" \
  --env PIPEDRIVE_API_KEY="your-pipedrive-api-key"

How to use

This MCP server (schipiga-mcp-server) provides a Node.js-based MCP endpoint that coordinates tool usage through a set of example scripts. The repository's README indicates Node.js is used to run both the server and the client examples, including direct tool invocation and agent-driven tool calls. You can trigger tool calls either directly or via agent workflows that leverage OpenAI and other tools. Use cases demonstrated by the examples include invoking specific tools directly, as well as running agent-based scripts such as beeai, LangChain, and LlamaIndex agents to orchestrate multi-step tasks.

To use it, first install dependencies and set up authentication tokens as described in the examples section. Start the MCP server using the Node.js entry (server.js) and then run the example scripts under the examples directory to exercise direct tool calls or agent-based tool orchestration. Be sure to export required API keys (PIPEDRIVE_API_KEY and OPENAI_API_KEY) before running the examples so that the tools can authenticate and perform their tasks. The examples demonstrate both single-tool invocations and more complex agent-driven workflows that chain together multiple tools to accomplish goals.

How to install

Prerequisites:

Node.js and npm installed on your system (recommended via Node Version Manager - nvm).
A Git client to clone the repository.

Installation steps:

Clone the repository: git clone https://github.com/slug to your local machine
Switch to the appropriate Node version (if using nvm): nvm use
Install dependencies: npm install
Set up required environment variables (example shown): export PIPEDRIVE_API_KEY=your-pipedrive-api-key export OPENAI_API_KEY=your-openai-api-key
Start the MCP server (used in this project as a Node server): node server.js
Run the example scripts to test tool calls and agent workflows, for example: node examples/toolcall-direct.js node examples/beeai-agent.js node examples/langchain-agent.js node examples/llamaindex-agent.js

Additional notes

Tips:

Ensure your Node.js version matches the project's requirements (use nvm to manage versions).
Keep your API keys in environment variables rather than hard-coding them.
If you encounter module resolution issues, re-run npm install or check for conflicting Node.js versions.
The examples directory contains scripts for direct tool calls as well as agent-based workflows; use them to validate both simple and complex tool orchestration.
The MCP server expects an environment configuration; adapt the env block in mcp_config to your deployment environment if running in a container or CI.
For production deployments, consider securing API keys and restricting access to the MCP endpoint.

Related MCP Servers

zen

1.1k

Selfhosted notes app. Single golang binary, notes stored as markdown within SQLite, full-text search, very low resource usage

MCP -Deepseek_R1

A Model Context Protocol (MCP) server implementation connecting Claude Desktop with DeepSeek's language models (R1/V3)

mcp-fhir

A Model Context Protocol implementation for FHIR

mcp

Inkdrop Model Context Protocol Server

mcp-appium-gestures

This is a Model Context Protocol (MCP) server providing resources and tools for Appium mobile gestures using Actions API..

dubco -npm

The (Unofficial) dubco-mcp-server enables AI assistants to manage Dub.co short links via the Model Context Protocol. It provides three MCP tools: create_link for generating new short URLs, update_link for modifying existing links, and delete_link for removing short links.