Server data from the Official MCP Registry
Your AI fetches and reads full job descriptions across seven ATS platforms, no copy-paste.
Your AI fetches and reads full job descriptions across seven ATS platforms, no copy-paste.
Valid MCP server (1 strong, 1 medium validity signals). No known CVEs in dependencies. ⚠️ Package registry links to a different repository than scanned source. Imported from the Official MCP Registry. 1 finding(s) downgraded by scanner intelligence.
10 files analyzed · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-prpmdev-jd-intel-mcp": {
"args": [
"-y",
"jd-intel-mcp"
],
"command": "npx"
}
}
}From the project's GitHub README.
Stop pasting job descriptions into AI assistants. Let your AI fetch them directly.
Full text. Clean structure. Across seven major ATS. No copy-paste. No context loss.
Your AI assistant already knows a lot about you. Your resume is in its memory. Your target roles, your past projects, your background. Ready to help the moment you feed it a job description.
So you copy-paste.
A JD from one company. Another from the next. A half-dozen more from your target list. Half have broken HTML. Salary info dies in translation. Links get stripped. And for every role, the dance starts over.
You could wait for the job boards to ship their own MCPs. They'll get there eventually. On their timeline. Filtered through their priorities, not yours. Tied to their query abstractions.
jd-intel skips that wait. Raw JDs, fetched directly by your AI, on your terms. One level below the curated layer.
Try asking your AI:
"Find AI/ML engineering jobs posted this week." "What product designer roles are open at fintechs right now?" "Pull the staff PM roles posted in the last 7 days."
Done.
Because scraping breaks where jd-intel doesn't:
The toolkit fetches. Your AI thinks.
Works with MCP-aware AI clients: Claude Desktop, Claude Code, Cursor, Windsurf, VS Code. ChatGPT, Gemini, and other non-MCP clients don't support this yet. They use different tool-calling systems. (We wish they did. The protocol works the same way regardless of which AI you talk to.)
The simplest path. No Node.js, no terminal: Claude Desktop runs the server on its own bundled runtime.
Shortcuts: drag the .mcpb onto the Settings window, or double-click it when your system opens .mcpb files with Claude Desktop. The extension is open source and unsigned, so Claude Desktop shows an "unverified" notice. Choose Install Anyway.
Prefer the terminal, or on an older Claude Desktop? Install Node.js 18+, run npx jd-intel-mcp install, then reopen Claude Desktop. Or edit the config file directly, see Manual install.
One-file .mcpb install is a Claude Desktop feature; these clients run the same server via npx and need Node.js 18+.
Claude Code
claude mcp add jd-intel -- npx -y jd-intel-mcp
Cursor (Settings, then Tools & MCP, then New MCP Server, or edit ~/.cursor/mcp.json):
{
"mcpServers": {
"jd-intel": { "command": "npx", "args": ["-y", "jd-intel-mcp"] }
}
}
Windsurf (Settings, then Tools, then Windsurf Settings, then Add Server, or View Raw Config to edit mcp_config.json). Use the same mcpServers block as Cursor, then press refresh.
VS Code (Copilot agent mode): run the MCP: Add Server command, or create .vscode/mcp.json. The key is servers and the type is stdio:
{
"servers": {
"jd-intel": { "type": "stdio", "command": "npx", "args": ["-y", "jd-intel-mcp"] }
}
}
Start a new chat and ask: "What fintech companies are in your jd-intel registry?" If it lists companies, you're set. Then try the real thing: "Find senior PM roles open right now that I'd be a fit for."
Tools not appearing?
npx clear-npx-cache, then restart.node --version is 18 or newer for the npx paths. The one-click .mcpb does not need Node.npm install jd-intel
import { fetchJobs } from 'jd-intel';
const jobs = await fetchJobs({
company: '<your-target-company>',
titleFilter: 'designer',
postedWithinDays: 14,
limit: 50,
});
CLI usage: npx jd-intel fetch <company-slug> --title-filter "engineer" --posted-within-days 14. Full filter reference below.
Node.js 18+. No API keys. No configuration.
If npx jd-intel-mcp install fails, edit the config directly.
Config file location:
~/Library/Application Support/Claude/claude_desktop_config.json%APPDATA%\Claude\claude_desktop_config.json{
"mcpServers": {
"jd-intel": {
"command": "npx",
"args": ["-y", "jd-intel-mcp"]
}
}
}
Restart Claude Desktop.
.mcpb): install a newer .mcpb over the current one, or manage it in Settings, then Extensions. Remove and reinstall to reset.npx -y jd-intel-mcp picks up new versions from npm's cache (within ~24h). Force it now with npx clear-npx-cache, then restart the client.npm install jd-intel@latest (force latest) or npm update jd-intel (respect semver).The company registry refreshes on its own: jd-intel fetches the current list at startup and falls back to the bundled copy offline, so new companies show up without reinstalling.
| Tool | Purpose |
|---|---|
fetch_jobs | Get open roles at a company with filters for role type, topic, location, and recency |
search_registry | Find companies by name or sector |
detect_ats | Identify which ATS platform a company uses |
Plus one Resource: registry://jd-intel/all. Full company registry, grouped by ATS. Fetched lazily for broad catalog surveys.
Every job normalizes to one schema, across every platform:
{
"id": "a1b2c3d4e5f6",
"company": "Example Co",
"title": "Senior Software Engineer, Platform",
"department": "Engineering",
"location": "Remote - US",
"locationType": "remote",
"salary": { "min": 180000, "max": 240000, "currency": "USD" },
"description": "Design and build the API surface our customers integrate against...",
"url": "https://boards.example.com/jobs/12345",
"postedAt": "2026-04-10T14:30:00Z"
}
No custom parsing per company.
| Field | Description |
|---|---|
title | Full job title |
company | Normalized company name |
department | Team or department (when provided) |
location | City, state, country, or remote |
locationType | remote, hybrid, or onsite |
salary | Min-max range with currency (when available) |
description | Full JD in clean markdown |
url | Direct link to the posting |
postedAt | Publication date (when provided) |
| Platform | Status | Typical use |
|---|---|---|
| Greenhouse | Shipped | Most widely used ATS in tech |
| Ashby | Shipped | Growing fast with startups |
| Lever | Shipped | Common at mid-stage companies |
| SmartRecruiters | Shipped | Enterprise and mid-market |
| Teamtailor | Shipped | European startups and scale-ups |
| Recruitee | Shipped | Dutch / EU SMBs and scale-ups |
| Workday | Shipped | Large enterprises (registry-keyed) |
| Personio | Planned | German / EU mid-market |
Adding a new ATS is a single adapter file. See Contributing.
| Flag | What it matches | Use for |
|---|---|---|
--title-filter | Title only | Role identity (PM, engineer, designer) |
--filter | Title + department + description | Topic or scope (integrations, growth) |
--posted-within-days | Recent postings | Recency cuts |
--location-include | Location contains any keyword | Region targeting |
--location-exclude | Location contains no keyword | Drop geographic noise |
--limit | First N results | Cap output size |
All filters AND together. Deep dive on patterns and gotchas: docs/filters.md.
Shipped
Next
Planned
Add a company to the registry: submit a PR to the appropriate file in registry/.
Add an ATS adapter: new file in src/adapters/. One adapter, one file. Follow the pattern of the existing adapters.
Request a company: open an issue. Tell me who's missing.
Prashant R. PM who builds. I try out and build what really matters below the AI hype.
MIT
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.