MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. Each candidate is checked by a language model from its name, description and topics, and only actual MCP servers are listed (not clients, SDKs, lists or skills). Package metadata comes from ecosyste.ms (CC BY-SA 4.0). A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Your own free job search API. Describe the job you want in plain words or upload your CV, and get the best matching jobs from career pages, job boards and the web. Web page and MCP server included.
MIT ★ 2 -
Tech jobs search API for Python and MCP: search AI jobs, startup jobs and remote tech jobs at 824 companies by title, place, seniority, salary and posted date. Python quick start, curl, and MCP setup for Claude, Cursor, VS Code and ChatGPT. Runs on Apify, $1.15 per 1,000 matching jobs.
MIT -
linkedin job scraper: Python + MCP quick-start for the LinkedIn Job Search API on Apify. Call it from Python (uv) or as an MCP tool in Claude and Cursor. Returns structured JSON for linkedin job scraper.
-
mcp-job-searchgithub.com/rajivdatta/mcp-job-searchupdated this year
MCP server that finds recent jobs from your LinkedIn profile and scores them against your resume (JSearch API), with HTML match reports.
MIT -
Free MCP server + 24/7 watcher + optional agent runner to find jobs (YC / a16z / big tech) from public ATS APIs. No API keys.
MIT ★ 1 -
Find internships from your terminal. Scan company job boards (Greenhouse, Lever, Ashby, SmartRecruiters, Workable, Recruitee), community lists, and company career sites for matching roles. Zero API keys, no telemetry, works with your AI over MCP.
MIT -
entra-mcpno update data
Verified AI & tech jobs from company ATSs (OpenAI, Anthropic, Stripe, SpaceX + 300 more). Search, fit-score resume matching, salary stats, companies hiring, apply links. Employers: post jobs and find candidates with an API key. Finds and ranks — you apply.
smithery -
Job listings API: search 2.5M+ open roles from 50,000+ company career sites by title, place, salary or remote, no company list. Daily new-jobs feed. curl, Python, MCP.
MIT -
Jobs API and hiring change feed across Greenhouse, Lever, Ashby, Workable, Teamtailor and SmartRecruiters. Give it a company domain — it finds the job board itself. MCP server + Apify Actor.
npm MIT -
JazzHR API example: search live job postings across every company hiring on JazzHR (applytojob.com) from Python or MCP. Employer directory, job index, and a new-jobs delta feed.
-
MCP server for public Lever job boards. Search a company's openings, read one in full. No API key.
npm MIT -
MCP server that gives AI agents job-search tools over Greenhouse, Lever and Ashby public APIs
MIT -
job-search-assistantgithub.com/MezaGabriel/job-search-assistantupdated this year
AI job-search copilot for Claude Desktop — MCP server that sources, scores, tailors CVs/covers, and preps interviews. Runs on your own Claude subscription, no API costs.
-
Personal job-search assistant for Claude Desktop: searches real job boards, has Claude score each job 0-100 for fit, and shows a ranked board with one-click triage. MCP App, runs locally, no API keys.
npm MIT ★ 5 -
MCP server that lets AI assistants search Swedish job ads via Arbetsförmedlingen's open JobTech API. Unofficial.
MIT -
MCP server for public Ashby job boards. Resolve a company to its board, search its openings and the pay it publishes. No API key.
npm MIT -
production-job-systemgithub.com/heyfinal/production-job-systemupdated this year
🤖 Enterprise Job Discovery System - AI-powered job search automation with MCP integration, real API connections, and intelligent matching algorithms
-
rvcj-mcp-serverupdated this year
MCP server for HireQL job search API - search 630+ remote vibe coding jobs
npm MIT -
An MCP server that lets Claude search and read live job postings from companies you choose, using the official Greenhouse, Lever, and Ashby job board APIs. No scraping, no API keys. Filters roles into career lanes (deployment, PM, new grad), handles partial failures, and caches responses to keep requests low.
MIT -
adzuna-mcpgithub.com/soss-lesig/adzuna-mcpupdated this year
Model Context Protocol server for the Adzuna job search API
npm MIT -
Live tech job search over public APIs and company ATS boards — for humans and for AI agents over MCP. No API key, no database.
npm MIT -
iflow-mcp_folathecoder-adzuna-mcpgithub.com/folarinakinloye/adzuna-mcpupdated this year
MCP server for Adzuna Job Search API - search jobs, analyze salaries, and research employers
pypi MIT -
MCP server for HeadHunter API integration with Claude Code. Search jobs, manage resumes, and apply to vacancies using AI.
MIT ★ 38 -
MCP server for reverse head-hunting: search job postings across ten ATS platforms at once. No API keys, no accounts.
0BSD -
A Model Context Protocol (MCP) server for searching and retrieving LinkedIn job postings via the RapidAPI LinkedIn Data API.
★ 1 -
@lightanchor/mcp-servergithub.com/light-anchor/light-anchorupdated this year
MCP server for Light Anchor Jobs API — lets AI agents create, search, and apply to jobs
npm MIT -
Open-source job search with original application links, a local REST API, and MCP tools
MIT -
amtgithub.com/fabkho/amtactive
Ein Amt für die Jobsuche — a CLI + MCP job-search clerk that crawls job APIs, ranks the results, and drafts your CV & cover letters.
MIT ★ 3 -
recruitdata-mcpgithub.com/ssaikrishna862/recruitdata-mcpupdated this year
RecruitData — live jobs & hiring data API for recruiting AI agents (MCP). Unified search across Foundit, Shine, RemoteOK, BuiltIn, WeWorkRemotely.
MIT -
MCP server exposing three job-search tools (semantic resume search, live company research, cover letter generation) over authenticated HTTP. Built with FastMCP and FastAPI, with API-key auth and rate limiting. Containerized with Docker and deployed on Azure Container Apps.
-
MCP server + CLI for searching Serbian job boards (Infostud, HelloWorld.rs) — no API keys needed
-
Unofficial read-only MCP server for Jobvision (jobvision.ir), the Iranian job portal: job search, ads, companies, advertised pay. No API key. For Claude, Cursor, Copilot.
pypi MIT -
Unofficial read-only MCP server for IranTalent (irantalent.com), the job portal: job search, ads, companies and employee reviews. No API key. For Claude, Cursor, Copilot.
pypi MIT -
Job search pipeline: 10 job boards + 6 ATS APIs, cross-source dedupe, weighted ranking, tracker, Claude Code skills
MIT -
Unofficial read-only MCP server for Jobinja (jobinja.ir), the Iranian job portal: job search, ad details, companies, top-50 scores. No API key. For Claude, Cursor, Copilot.
pypi MIT -
AI-powered job search platform: CV analysis, gap analysis, interview prep, cover letters, automated outreach. FastAPI + Claude API + MCP.
MIT ★ 2 -
joblens-mcpgithub.com/rohith-jpg/joblens-mcpupdated this year
MCP server giving Claude live job search and resume-match scoring via official APIs — no scraping, no platform login
MIT -
Job Search Dossier — a keyless job-search web app, REST API, and MCP server. Ranks roles (5 live sources, link-checked), drafts cover letters, and answers application Q&A.
MIT -
NextRole MCP server — résumé & job-search tools for AI agents (ATS check, CV scoring, role search, JD fetch, CV tailoring). Remote: https://nextrole.site/api/mcp
-
trawlgithub.com/nitish-hegde-vst-au4/trawlupdated this year
A local-first job-search dashboard. Polls five ATSes daily, discovers new sponsoring companies weekly. No accounts, no API keys, no telemetry.
MIT -
mcp-server-recruteistale
MCP server implementation for Recrutei job search API
npm ISC -
@techmap/mcp-serveractive
MCP server for Techmap's job postings data: search 8M+ new job postings per month from 185 sources in 250 countries via the Techmap Jobs API.
npm MIT -
findyet-mcpactive
Findyet MCP server: search jobs, get CV-based recommendations, track applications and tailor CVs with your Findyet API key.
npm MIT -
MCP server for the Get on Board public API — search LATAM tech jobs from any MCP client
MIT -
An agent-friendly job board you self-host. Its own listings, never scraped. Web, API, MCP, CLI, TUI, desktop and PWA on one engine, and instances find each other through an open directory.
npm MIT ★ 4 -
mcp-linkedin-scrapergithub.com/dppalukuri/mcp-linkedin-scraperupdated this year
MCP server for LinkedIn — profiles, jobs, companies. Session-based auth, job search works without login. Free, no API keys needed.
-
MCP server for Upwork's GraphQL API. Lets Claude and other MCP clients search jobs, manage proposals and saved jobs, track profile, contracts and time reports over OAuth 2.0 with built-in rate limiting. TypeScript, published on npm as @furkankoykiran/upwork-mcp.
npm MIT ★ 2 -
leadharbor-mcpactive
MCP server for the LeadHarbor APIs on RapidAPI: email verify (MX), website contact extractor, LinkedIn jobs search, YouTube data. Bring your own RapidAPI key.
npm MIT -
MCP server for HeadHunter job search API
npm MIT -
YouTube Extended Search — FlashDatano update data
# YouTube Extended Search — FlashData Search larger YouTube video result sets, with up to 700 requested results. Map recurring channels and topics from structured video records. Group a larger topic sample by channelId or channelUrl to see which creators appear repeatedly, retaining the underlying video IDs. [YouTube Extended Search API documentation and examples](https://flashdata.dev/docs/sources/youtube_search_extended?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_search_extended-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Extended Search listing](https://smithery.ai/servers/flashdata/youtube-extended-search) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_search_extended`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_search_extended` without submitting a data query. After approving your data-call budget, try: > Search for 100 battery recycling videos, group the observed results by channel, and retain video IDs for later review. This server exposes `youtube_search_extended`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call max_results accepts 1–700, default 20. This is the extended-search product with its own higher rate, not repeated standard search or a guarantee of 700 returned records. The same supported filters are available. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_search_extended", "arguments": { "query": "battery recycling", "max_results": 100 } } ``` ## Work with the output Read results[0].results and group by channelId or channelUrl. Keep the original video IDs and count observed results per channel; retain channel labels for review. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_search_extended", "status": "done", "results": [ { "results": [ { "videoId": "dQw4w9WgXcQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 }, { "videoId": "aqz-KE-bpKQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 } ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The request limit is 700, not a promise of 700 returned videos or pagination. Extended search has its own rate, higher than standard search. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
Local-first YouTube research MCP server: search, metadata, transcripts with FTS search, media, frames and batch jobs via yt-dlp. No API key.
MIT -
OpenWeb Ninja MCPno update data
Official MCP server for OpenWeb Ninja: 40+ real-time web data and SERP APIs (Google Maps, Amazon, jobs, Zillow, Trustpilot, web search, news, finance) exposed as MCP tools. Requires an OpenWeb Ninja API key.
smithery -
Self-hosted search and research infrastructure for AI agents. Query web and specialist sources through MCP, run durable research jobs, and monitor results with replayable change events. SearXNG-compatible HTTP API.
MIT ★ 14 -
seek-mcpgithub.com/IntrepidShape/seek-mcpupdated this year
Zero-dependency Bun MCP server for Australian job search. Hand-rolled JSON-RPC over stdio, no SDK. SEEK has no public search API, so it reads Adzuna's AU index.
MIT -
Candidate Hub MCPno update data
**CandidateHub** gives AI agents a complete job-search toolkit backed by [aicandidatehub.com](https://www.aicandidatehub.com) — 18 tools covering the whole application lifecycle. ## What your agent can do - **Jobs** — import postings from any URL, search saved jobs, track applications end-to-end - **CVs & cover letters** — generate job-tailored CVs and cover letters from your profile - **Fit & pay** — analyze job fit against your profile; benchmark compensation for any role - **Profile** — import your résumé once; every tool builds on it ## Setup (2 minutes) 1. [Create a free account](https://www.aicandidatehub.com/login?utm_source=mcp&utm_medium=ai-agent&utm_campaign=smithery) 2. Mint a Personal Access Token at **Account → MCP Tokens** 3. Paste it as `candidatehub_token` when installing _Runs locally over stdio. Starts and lists tools without a token; API-backed tools need one._
smithery -
yokozuna-mcpgithub.com/mbe24/yokozuna-mcpupdated this year
MCP server for Sumo Logic log triage — search, facet, error-digest, cross-reference, and monitor logs from preview and production deployments via the Search Job API, with token-economical output for coding agents.
npm Apache-2.0 -
@verticalint-michael/enrich-layer-mcpupdated this year
MCP server for Enrich Layer API — 25 tools for company, person, contact, school, job, and search enrichment
npm MIT -
@kooperativa_team/mcp-serveractive
MCP server for the Kooperativa API — enrich and search professional profiles and companies, track hiring signals and job changes, and manage webhook monitors, directly from your AI assistant.
npm MIT -
MCP server for the Kooperativa API. Enrich and search professional profiles and companies, track hiring signals and job changes, and manage webhook monitors, from any MCP-compatible AI assistant.
MIT ★ 1 -
LinkedIn for AI assistants (MCP) — profiles, people/job/company search, feed & messaging as structured JSON, plus gated writes (connect/message/post/react/comment) via LinkedIn's API instead of DOM-clicking. Stealth-browser engine, 24 tools, built-in safety layer. Claude · Cursor · any MCP client.
npm MIT ★ 12