ZOOQ - LinkedIn Data for AI Agents
Live LinkedIn data for AI agents: 44 tools for profiles, companies, jobs, posts, people search, job-change signals and email finding. Hosted remote server (streamable HTTP) - your agent never touches your own LinkedIn account. 300 free credits on signup, no card. Dockerfile in repo bridges stdio clients to the hosted endpoint via mcp-remote.
README
ZOOQ MCP — live LinkedIn data for AI agents
ZOOQ gives your AI agent real-time LinkedIn data — profiles, companies, jobs, posts, people search, job-change signals and email finding — as 44 clean MCP tools served from a hosted endpoint.
The important part: your agent never touches your LinkedIn account. Most LinkedIn MCP servers work by borrowing your logged-in session cookie, which puts your own account at ban risk and breaks every few weeks. ZOOQ runs on its own infrastructure. You paste one API key; your account stays out of it entirely.
- Endpoint:
https://zooq.dev/api/mcp(streamable HTTP) - Auth:
X-API-Keyheader — get a free key (300 credits, no card) - Pricing: credit-based, pay for what you call. Failed upstream calls are auto-refunded.
Install
Claude Code
claude mcp add --transport http zooq https://zooq.dev/api/mcp --header "X-API-Key: YOUR_ZOOQ_KEY"
Cursor / Cline / any MCP client (config JSON)
{
"mcpServers": {
"zooq": {
"url": "https://zooq.dev/api/mcp",
"headers": { "X-API-Key": "YOUR_ZOOQ_KEY" }
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector → URL https://zooq.dev/api/mcp, header X-API-Key: YOUR_ZOOQ_KEY.
Replace YOUR_ZOOQ_KEY with the key from zooq.dev/signup. That's the whole setup.
What your agent can do with it
| Category | Tools | Examples |
|---|---|---|
| Profiles (7) | full profile, enrich, employment history, similar people | profile_full, profile_enrich |
| Companies (11) | company info, employees data, insights, similar companies | companies_enrich, companies_employees_data |
| Search & signals (7) | people/company search, live search, job-change signals | search_people, search_job_changes |
| Jobs (6) | job search, details, hiring team | search_jobs, jobs_hiring_team |
| Posts & activity (5) | a person's posts, comments, likes | posts_all, posts_comments |
| Email finding (5) | find, verify, reverse lookup, domain prospects | email_find_by_profile, email_verify |
| Lookups (3) | skills, institutions taxonomy | g_title_skills_lookup |
Typical agent recipes:
- AI SDR —
search_people→profile_enrich→posts_all→ write a genuinely personalized opener →email_find_by_profile - Job-change trigger —
search_job_changeson your target accounts → congratulate/pitch the week they land - Account research —
companies_enrich+companies_employees_data+companies_jobs→ a briefing your agent writes itself
Why not a scraper or a cookie-based server?
| Cookie/scraper servers | ZOOQ | |
|---|---|---|
| Uses YOUR LinkedIn account | Yes — ban risk is yours | Never |
| Breaks when LinkedIn changes | Constantly | Our problem, not yours |
| Setup | Browser profiles, cookies, captchas | One API key |
| Cost | "Free" until your account isn't | 300 free credits, then pay-per-call |
Rate limits & good citizenship
Responses carry _meta.credits_remaining and _meta.hourly_cap_remaining — agents should pace themselves.
Default cap: 10,000 credits/hour. Errors are structured (-32005 = hourly cap, back off).
Links
- Site & docs: zooq.dev
- Free key: zooq.dev/signup
- Pricing: zooq.dev/pricing
- Built by Amir Baldiga — GTM engineer; ZOOQ powers his own outbound agents.
License
MIT (this repository — the metadata and docs). The ZOOQ API itself is a commercial service.
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.
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.
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.
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.