Pearch
About
Best people search engine that reduces the time spent on talent discovery.
Details
- Author
- Pearch-ai
- Downloads
- 275
- Categories
- Developer Tools, Search, Other
Jump to
- Natural language candidate queries
- Highest precision people search results
- Backed by scientific evaluation methods
- Seamless integration with any ATS
- Trusted by recruiters as top-quality sourcing tool
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
PearchCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install via Smithery (npx -y @smithery/cli install @Pearch-ai/mcp_pearch --client claude) or manually with Python 3.7+ and FastMCP. Set the PEARCH_API_KEY environment variable, then run fastmcp install pearch_mcp.py for standard use or fastmcp dev pearch_mcp.py for local development.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"pearch": {
"Pearch.ai": {
"command": "uv",
"args": [
"run",
"--with",
"fastmcp",
"fastmcp",
"run",
"your_path/pearch_mcp.py"
],
"env": {
"PEARCH_API_KEY": "your_token"
}
}
}
}
}McpServers
{
"Pearch.ai": {
"command": "uv",
"args": [
"run",
"--with",
"fastmcp",
"fastmcp",
"run",
"your_path/pearch_mcp.py"
],
"env": {
"PEARCH_API_KEY": "your_token"
}
}
}- Find candidates by natural-language description— Search for people usingsearch_people, e.g. by skills, location, experience, or role.
- Discover B2B companies and contacts— Usesearch_company_leadsto find companies matching criteria and key contacts within them.
- Test without an API key— Start immediately withtest_mcp_keyfor masked sample results before upgrading to a full key.
Evaluating AI Recruitment Sourcing Tools by Human Preference
- search_people— natural-language search for people (e.g. “software engineers in California with 5+ years Python”); returns candidates with optional insights and profile scoring.
- search_company_leads— find companies and leads/contacts within them (B2B); e.g. “AI startups in SF, 50–200 employees” + “CTOs and engineering managers”.
- Test key by default— works out of the box withtest_mcp_key(masked/sample results); set your own key for full results.
- Python 3.10+
- uv(recommended; Linux/macOS:curl -LsSf https://astral.sh/uv/install.sh | sh) or pip
- FastMCP— install withpip install fastmcporuv add fastmcp
Usetest_mcp_keyformasked (sample) results— no sign-up required.
Forfull, unmasked results, get an API key from thePearch.ai Dashboardand set it asPEARCH_API_KEYin your MCP config (see Installation below).
Clone the repo, then follow the steps for your client:
git clone https://github.com/Pearch-ai/mcp_pearch cd mcp_pearch
fastmcp install claude-desktop pearch_mcp.py --env PEARCH_API_KEY=test_mcp_key
Replacetest_mcp_keywith your dashboard key for full results.
If you seebad interpreter: No such file or directory(e.g. with conda), run:
python -m fastmcp install claude-desktop pearch_mcp.py --env PEARCH_API_KEY=test_mcp_key
Manual:edit~/.claude/claude_desktop_config.jsonand add undermcpServers. Replace/path/to/mcp_pearchwith your actual path.
"Pearch.ai": { "command": "uv", "args": ["run", "--with", "fastmcp", "fastmcp", "run", "/path/to/mcp_pearch/pearch_mcp.py"], "env": { "PEARCH_API_KEY": "test_mcp_key" } }
"Pearch.ai": { "command": "python", "args": ["/path/to/mcp_pearch/pearch_mcp.py"], "env": { "PEARCH_API_KEY": "test_mcp_key" } }
Ensurefastmcpis installed:pip install fastmcp.
fastmcp install cursor pearch_mcp.py --env PEARCH_API_KEY=test_mcp_key
Replacetest_mcp_keywith your dashboard key for full results.
Manual:add to~/.cursor/mcp.json(or project.cursor/mcp.json):
{ "mcpServers": { "Pearch.ai": { "command": "uv", "args": ["run", "--with", "fastmcp", "fastmcp", "run", "/absolute/path/to/pearch_mcp.py"], "env": { "PEARCH_API_KEY": "test_mcp_key" } } } }
Replace/absolute/path/to/pearch_mcp.pywith the real path. Usetest_mcp_keyfor masked results, or your dashboard key for full results.
fastmcp install mcp-json pearch_mcp.py --name "Pearch.ai"
Then paste the output intomcpServersin~/.cursor/mcp.json.
- VS Code:add the samemcpServersblock to.vscode/mcp.jsonin your workspace.
- Other MCP clients:use the samecommand/args/envformat in the client’s MCP config.
Generate a config snippet (defaults totest_mcp_key; add--env PEARCH_API_KEY=your-keyfor full results):
fastmcp install mcp-json pearch_mcp.py --name "Pearch.ai"
Paste the generated object into your client’smcpServers.
Base URL:PEARCH_API_URLor per-callbase_url(defaulthttps://api.pearch.ai).
The server exposes Streamable HTTP at/mcpwhen run with Uvicorn:
export PEARCH_API_URL='https://api.pearch.ai' # optional uvicorn pearch_mcp:app --host 0.0.0.0 --port 8000
Remote access uses thesame Pearch API keyasapi.pearch.ai(Authorization: Bearer). The server validates keys viaGET /v1/user. Demo keytest_mcp_keyis also accepted (masked results).
{ "mcpServers": { "Pearch.ai": { "url": "https://mcp.pearch.ai/mcp", "headers": { "Authorization": "Bearer ${env:PEARCH_API_KEY}" } } } }
export PEARCH_API_KEY='test_mcp_key' # or your key for full results fastmcp dev inspector pearch_mcp.py
Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.
Job search engine with 500k+ listings across Austria, Germany and Switzerland (alleskralle.com).
Hosted MCP server for the APITube News API: search articles from 500,000+ sources in 60+ languages, filtered by sentiment, entities, topics and source quality.
Live Austin-area MLS listings in your AI assistant — active listings, property details, schools, taxes, and neighborhood data for the Austin metro. Free remote MCP server, no install.
Find and qualify expired, dropping, and auction domains using SEO metrics, backlink data, domain age, language, screenshots, and historical tech signals across 17 auction sources and 49+ ccTLDs.
Search for open source issues related to climate change and sustainability using the ClimateTriage API.
Australian development application and property intelligence queries for AI agents.
Research a person's public footprint from a name, phone, email, or username. Sourced public-web profiles for AI agents. Not a background check.
Search distressed auction properties for investors
Provides comprehensive enterprise information query and analysis, including business info, risk analysis, intellectual property, and operational insights.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
