handshake-mcp
Enables AI assistants to search and apply for jobs on Handshake, track applications, and research employers using your browser session.
README
handshake-mcp
An MCP server that gives AI assistants like Claude access to Handshake — search jobs, apply, track applications, and research employers through your own browser session.
Disclaimer: This project is independent and unaffiliated with Handshake. Automated access may violate Handshake's Terms of Service. Use for personal productivity only.
Tools
| Tool | Description |
|---|---|
hs_search_jobs |
Search by keyword, location, or job type |
hs_get_job |
Full description, requirements, salary, deadline |
hs_apply |
Submit an application, attach resume/cover letter |
hs_save_job / hs_unsave_job / hs_get_saved_jobs |
Bookmark management |
hs_get_applications / hs_withdraw_application |
Application tracking |
hs_search_employers / hs_get_employer |
Company research |
hs_get_profile |
Your Handshake student profile |
hs_get_documents |
Uploaded resumes and cover letters |
Quick start
With uvx (recommended)
# First-time login
uvx handshake-mcp --login
# Add to Claude Code (~/.claude/.mcp.json)
{
"mcpServers": {
"handshake": {
"command": "uvx",
"args": ["handshake-mcp"]
}
}
}
From source
git clone https://github.com/shahparam11/handshake-mcp-server.git
cd handshake-mcp
uv sync
# First-time login
uv run handshake-mcp --login
Add to ~/.claude/.mcp.json:
{
"mcpServers": {
"handshake": {
"command": "uv",
"args": ["run", "--project", "/path/to/handshake-mcp", "handshake-mcp"]
}
}
}
Restart Claude Code. The hs_* tools are now available.
With Docker
docker build -t handshake-mcp .
# Login (mounts session storage)
docker run -it -v ~/.handshake-mcp:/root/.handshake-mcp handshake-mcp --login
# Run as MCP server
docker run -i -v ~/.handshake-mcp:/root/.handshake-mcp handshake-mcp
CLI
handshake-mcp --login # authenticate via browser
handshake-mcp --status # check session validity
handshake-mcp --logout # clear saved session
handshake-mcp --version # print version
How it works
On --login, a Patchright Chromium browser opens. After you log in, the full browser profile (cookies, localStorage, IndexedDB) is saved to ~/.handshake-mcp/. Subsequent tool calls use these cookies via an httpx client against Handshake's internal REST API at app.joinhandshake.com/api/v1/.
CSRF protection uses the double-submit cookie pattern — the CSRF-TOKEN cookie value is reflected back as the X-CSRF-Token request header.
Note: Handshake's internal API is undocumented. If a tool returns 404, open browser DevTools on Handshake → Network tab, find the matching request path, and update the relevant
handshake_mcp/tools/*.pyfile.
Session refresh
handshake-mcp --login
Project layout
handshake_mcp/
├── cli_main.py # Entry point — --login/--logout/--status/server
├── server.py # FastMCP server factory
├── auth.py # Patchright login + profile/cookie storage
├── client.py # Authenticated httpx client
├── exceptions.py # CredentialsNotFoundError, SessionExpiredError
└── tools/
├── jobs.py # hs_search_jobs, hs_get_job, hs_apply, hs_save/unsave/get_saved_jobs
├── employers.py # hs_search_employers, hs_get_employer
├── applications.py # hs_get_applications, hs_withdraw_application
└── profile.py # hs_get_profile, hs_get_documents
Development
uv sync --group dev
uv run pytest --cov
uv run ruff check .
License
MIT — see LICENSE.
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.