RocketReach Local MCP
Provides local MCP access to RocketReach's REST API, enabling person and company search, profile lookups, and account management without OAuth.
README
RocketReach Local MCP
A local Model Context Protocol server for RocketReach that uses the REST API and an API key. It replaces the official OAuth MCP when that endpoint is flaky or rate-limited.
Setup
1. Install dependencies
pip install -r requirements.txt
2. Add your API key
Store your key in your user config folder (recommended):
Windows
mkdir $env:USERPROFILE\.rocketreach
Set-Content $env:USERPROFILE\.rocketreach\api_key "YOUR_API_KEY"
macOS / Linux
mkdir -p ~/.rocketreach
echo "YOUR_API_KEY" > ~/.rocketreach/api_key
chmod 600 ~/.rocketreach/api_key
Alternative locations (checked in order):
| Priority | Location |
|---|---|
| 1 | ~/.rocketreach/api_key — plain text file |
| 2 | ~/.rocketreach/.env — ROCKETREACH_API_KEY=... |
| 3 | Project .env — ROCKETREACH_API_KEY=... |
| 4 | ROCKETREACH_API_KEY environment variable |
Get your key from RocketReach Account → API.
3. Connect in Cursor
Add to %USERPROFILE%\.cursor\mcp.json:
{
"mcpServers": {
"rocketreach": {
"command": "python",
"args": ["C:\\path\\to\\RocketReach MCP\\server.py"],
"cwd": "C:\\path\\to\\RocketReach MCP"
}
}
}
Reload MCP servers in Cursor (Settings → MCP → refresh).
Tools
| Tool | Description | Credits |
|---|---|---|
ping |
Liveness check | No |
account |
Plan, credits, rate limits | No |
person_search |
Search 700M+ profiles | No |
company_search |
Search companies | No |
person_lookup |
Emails/phones for a person | Yes |
company_lookup |
Full company profile | Yes |
check_person_status |
Poll async person lookups | No |
Usage examples
In Cursor chat
Check my RocketReach account credits
Find VPs of Engineering at SaaS companies in New York
Look up person id 531625233
CLI tests
# Test REST client (account + sample search)
python test.py --local
# Credits and rate limits only
python test.py --usage
# Official MCP OAuth smoke test (optional)
python test.py --smoke
Python client
from rocketreach_mcp.client import RocketReachClient
client = RocketReachClient()
print(client.account())
results = client.person_search(
{"current_title": ["VP Engineering"], "location": ["New York"]},
page_size=5,
)
print(results["pagination"], len(results["profiles"]))
MCP server (stdio)
python server.py
Person search query examples
{"name": ["Jane Doe"]}
{"current_title": ["Software Engineer"], "current_employer": ["Google"]}
{"location": ["\"San Francisco\"::~50mi"], "management_levels": ["director", "vp"]}
{"skills": ["python", "machine learning"]}
Use quotes inside values for exact match: "\"IBM\"".
Company search query examples
{"domain": ["stripe.com"]}
{"industry": ["Software"], "employees": ["100-500"]}
{"techstack": ["Salesforce"]}
Person lookup
Provide one identifier:
id— RocketReach profile ID from searchemaillinkedin_urlname+current_employernpi_number
If status is progress, call check_person_status with the profile ID.
Project layout
RocketReach MCP/
├── server.py # MCP server entrypoint
├── rocketreach_mcp/
│ ├── client.py # REST API client
│ └── config.py # ~/.rocketreach credential loading
├── test.py # CLI tests
├── requirements.txt
└── README.md
Notes
- Search endpoints do not consume credits; lookups do.
- The client retries on HTTP 429 using
Retry-Afteror backoff. - Keep
~/.rocketreach/api_keyout of git; it is user-local only.
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.