LinkedIn MCP Zero
You can use it as an MCP server for live public LinkedIn and job-market research, local resume matching, alerts/exports, and optional authenticated LinkedIn browsing via CDP.
Search and filter LinkedIn jobs, multi-board jobs, advanced searches, job details, company jobs/profiles, salary data, hiring trends, and industry insights.
Compare 2–5 jobs and export selected job details to CSV, JSON, or XLSX.
Parse resumes locally (PDF/DOCX/text), generate resume insights, and rank jobs against a saved resume.
Save, list, and run recurring job alerts.
Use optional Chrome CDP browser tools for your profile, other profiles, people search, connections, inbox/conversations, feed, notifications, sidebar suggestions, company employees, and session checks.
Use a gated Voyager profile lookup and built-in help/status tools.
README-highlighted features include real-time zero-login scraping, hybrid BM25/vector RAG, ghost-job viability scoring, dynamic skill graph, privacy-first resume analysis, and stdio/HTTP deployment with security controls.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@LinkedIn MCP Zero search for remote data scientist jobs"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A high-performance, public-first Model Context Protocol (MCP) server for real-time LinkedIn talent intelligence, hybrid semantic RAG matching, ghost-job viability scoring, dynamic skill graphs, and privacy-first resume analysis.
Zero Login Required (33 Default Public/Local Tools) · 45 Catalog Tools · FastMCP 2.0 Native · Dual Stdio/HTTP Transports
⚡ Quickstart • 🎬 Live Demo • 🛠️ 45 Tools • 🏗️ Architecture • 📊 Benchmarks • 🚀 Deployment • 🛡️ Security • ❓ FAQ
🌟 What Sets LinkedIn MCP Zero Apart
Related MCP server: LinkedIn MCP
⚡ Quickstart & One-Command Setup
Option A: Automatic Client Configuration (Recommended)
LinkedIn MCP Zero can automatically configure your favorite AI development environment with a single command:
# 🖥️ Anthropic Claude Desktop (macOS / Windows / Linux)
uvx linkedin-mcp-zero --install-client claude-desktop
# ⚡ Cursor IDE (Project or Global)
uvx linkedin-mcp-zero --install-client cursor
# 💻 Claude Code CLI
uvx linkedin-mcp-zero --install-client claude-code
# 📝 VS Code (Cline / Roo Code / MCP Extension)
uvx linkedin-mcp-zero --install-client vscode
# 🔮 Google Antigravity IDE & Agent Framework
uvx linkedin-mcp-zero --install-client antigravityOption B: Verify System Health (--doctor)
Run the automated diagnostic suite to inspect your Python runtime, SQLite FTS5 support, and live network reachability:
uvx linkedin-mcp-zero --doctorOption C: Supported AI Tool Integrations & Configurations
Choose your preferred AI client environment below for copy-pasteable JSON configurations and instant setup:
1. Anthropic Claude Desktop
Configuration File Location:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonLinux:
~/.config/Claude/claude_desktop_config.json
{
"mcpServers": {
"linkedin-zero": {
"command": "uvx",
"args": [
"linkedin-mcp-zero"
]
}
}
}2. Cursor IDE
Configuration File Location:
Workspace:
.cursor/mcp.jsonGlobal:
~/.cursor/mcp.json
{
"mcpServers": {
"linkedin-zero": {
"command": "uvx",
"args": [
"linkedin-mcp-zero"
]
}
}
}3. Visual Studio Code (Cline / Roo Code / Continue)
Configuration File Location:
macOS:
~/Library/Application Support/Code/User/mcp.jsonLinux:
~/.config/Code/User/mcp.jsonWindows:
%APPDATA%\Code\User\mcp.json
{
"servers": {
"linkedin-zero": {
"command": "uvx",
"args": [
"linkedin-mcp-zero"
]
}
}
}4. Claude Code CLI
One-line terminal command:
claude mcp add linkedin-zero -- uvx linkedin-mcp-zero5. Google Antigravity IDE & Agent Framework
Configuration File Location:
Workspace:
.agents/mcp_config.jsonGlobal:
~/.gemini/antigravity-ide/mcp_config.jsonor~/.gemini/config/mcp_config.json
{
"mcpServers": {
"linkedin-zero": {
"command": "uvx",
"args": [
"linkedin-mcp-zero"
]
}
}
}6. Cloud Hosted / Remote Streamable-HTTP
For remote web apps, distributed teams, or hosted agents connecting over HTTP SSE:
{
"mcpServers": {
"linkedin-zero-remote": {
"url": "https://linkedin-mcp-zero.onrender.com/mcp",
"headers": {
"x-api-key": "your-secure-api-token"
}
}
}
}🎬 Animated Live Execution Demo
Here is a visual recording of LinkedIn MCP Zero executing a live zero-login query, performing FTS5 Porter BM25 indexing, calculating ghost-job viability, and dynamically updating the SQLite skill co-occurrence graph in real time:
=== REAL-TIME LINKEDIN INSPECTION ===
Query: "Staff AI Engineer" in "San Francisco, CA"
1. Live Public Network Retrieval:
[1] ID: 4475151136 | Staff Systems Engineer, Inference @ Anthropic (San Francisco, CA)
[2] ID: 4483675233 | Research Engineer, Model Optimization @ OpenAI (San Francisco, CA)
[3] ID: 4301398088 | Principal AI Platform Engineer @ Databricks (San Francisco, CA)
2. Live Job Detail & Dynamic Skill Extraction:
Title: Staff Systems Engineer, Inference Infrastructure
Company: Anthropic
Skills: ['Python', 'PyTorch', 'CUDA', 'Distributed Systems', 'Triton']
Desc: "Anthropic is building reliable, interpretable, and steerable AI systems..."
3. SQLite FTS5 BM25 Indexing:
BM25 Search for "PyTorch": Found Anthropic Staff Systems Engineer (Rank: -0.842)
4. Real-Time Viability & Saturation Analysis:
Status: ACTIVE_HIGH_PRIORITY
Viability Score: 0.98 / 1.0 (0 reposts, posted 4h ago, 28 applicants)
5. Dynamically Learned Graph Connections:
"PyTorch" dynamically linked to:
-> cuda (weight: 5.8)
-> distributed systems (weight: 3.2)
-> triton (weight: 1.0)
-> llm serving (weight: 2.1)🛠️ Complete Interactive Tool Matrix (45 Tools)
LinkedIn MCP Zero provides 45 synchronized production tools organized into distinct risk tiers.
🛡️ Zero-Login Guarantee: 33 core tools require zero credentials, zero sessions, and zero browser automation. Your personal LinkedIn account is never touched and remains 100% protected.
Tool Name | Alias | Risk Tier | Est. Tokens | Description |
| 🟢 Public | ~500 | Search public LinkedIn job postings by keyword, location, and filters | |
| 🟢 Public | ~800 | Multi-board meta-search across LinkedIn, Indeed, Glassdoor, RemoteOK, and ZipRecruiter | |
| 🟢 Public | ~400 | Fetch complete job description, salary range, metadata, and criteria from URL or ID | |
| 🟢 Public | ~400 | Retrieve all active job openings for a specific company identifier | |
| 🟢 Public | ~250 | Extract structured compensation numbers, currency, and pay periodicity from listings | |
| 🟢 Public | ~400 | Analyze regional hiring demand, role popularity, and posting volume trends | |
| 🟢 Public | ~500 | Sector-wide hiring momentum, top hiring companies, and demanded skillsets | |
| 🟢 Public | ~1200 | Deep-dive industry landscape analysis with real-time research and market synthesis | |
| 🟢 Public | ~600 | Filtered search by experience level, remote modality, job type, and posting freshness | |
| 🟢 Public | ~800 | Side-by-side comparative analysis of 2 to 5 job postings across criteria | |
| 🟢 Public | ~1000 | Interactive career preference matching tailored to target roles and geographies |
Tool Name | Alias | Risk Tier | Est. Tokens | Description |
| 🟢 Public | ~300 | Extract organizational profile, employee counts, headquarters, and industry signals | |
| 🟢 Public | ~300 | Discover companies matching targeted keywords, industry sectors, and locations |
Tool Name | Alias | Risk Tier | Est. Tokens | Description |
| 🔒 Local | ~600 | Parse local PDF, DOCX, or text resume into structured skills, experience, and education | |
| 🔒 Local | ~500 | Identify candidate skill gaps, missing keywords, and strategic resume improvements | |
| 🔒 Local | ~800 | Universal multi-role ATS resume tailoring, keyword optimization, and real-time gap analysis | |
| 🔒 Local | ~800 | Deep resume critique leveraging client LLM reasoning for high-impact tailoring | |
| 🟢 Local/Pub | ~700 | Rank live job postings against candidate resume using Hybrid BM25 + Vector RRF | |
| 🟢 Local/Pub | ~900 | AI-driven semantic match reasoning providing qualitative candidate-job fit analysis | |
| 🟢 Local/Pub | ~800 | Generate tailored, high-converting cover letters mapped to actual job requirements |
Tool Name | Alias | Risk Tier | Est. Tokens | Description |
| 🟢 Public | ~350 | Ghost job detector: Evaluates repost history, applicant saturation, and hiring probability | |
| 🔒 Local | ~200 | Dynamic Skill Graph: Query live technology co-occurrence networks learned in SQLite | |
| 🟢 Local/Pub | ~600 | Benchmark compensation offers against live scraped market distributions | |
| 🔒 Local | ~200 | Real-time breakdown of tool invocation counts, error rates, and token consumption |
Tool Name | Alias | Risk Tier | Est. Tokens | Description |
| 🔒 Local | ~150 | Save recurring search criteria with frequency settings | |
| 🔒 Local | ~200 | List all active recurring job alerts | |
| 🟢 Public | ~500 | Poll live postings for matches against all saved alert queries | |
| 🔒 Local | ~200 | Export scraped listings to CSV, JSON, or XLSX with formula injection protection | |
| 🔒 Local | ~100 | Human-in-the-loop user approval for saving exports to filesystem | |
| 🔒 Local | ~150 | Inspect SQLite FTS5 database stats, cache hits, and circuit breaker status | |
| 🔒 Local | ~100 | Interactive parameter documentation and schema inspector for all tools | |
| 🔒 Local | ~100 | Cumulative session tokens and tool invocation statistics | |
| 🔒 Local | ~50 | Reset local telemetry metrics |
⚠️ Account Risk & Platform Policy Disclosure:
Unlike the 33 default tools which use public TLS impersonation with zero credentials and zero account risk, these 11 browser tools interact directly with an active, logged-in Chrome browser session via Chrome DevTools Protocol (--remote-debugging-port=9222) or Patchright.
Platform Risk: Programmatic scraping of authenticated LinkedIn sessions violates LinkedIn's User Agreement. Over-use or automated scanning may trigger CAPTCHA checkpoints or account restrictions.
Best Practice: If you choose to enable browser mode with
--enable-browser, use a secondary or test account, keep request rates conservative, and never run bulk automation on your primary personal account.Stay Zero-Risk: For job hunting, salary benchmarking, ATS resume tailoring, and talent research, the 33 default public/local tools provide 100% of the capability with zero account risk.
Requires Chrome with remote debugging (google-chrome --remote-debugging-port=9222) and --with-extra browser.
Tool Name | Alias | Risk Tier | Est. Tokens | Description |
| ⚠️ Browser | ~500 | Read personal authenticated profile summary, headline, and experience | |
| ⚠️ Browser | ~500 | Read public or 1st-degree connection profile page details | |
| ⚠️ Browser | ~600 | People search executed through active authenticated Chrome session | |
| ⚠️ Browser | ~600 | Read connection roster names, titles, and connection timestamps | |
| ⚠️ Browser | ~500 | List recent conversation summaries and unread thread counts | |
| ⚠️ Browser | ~600 | Read conversation transcript messages (SSRF domain guarded) | |
| ⚠️ Browser | ~600 | Read authenticated LinkedIn home feed posts and updates | |
| ⚠️ Browser | ~400 | Read incoming network notifications and interaction alerts | |
| ⚠️ Browser | ~400 | Extract "People Also Viewed" sidebar profile recommendations | |
| ⚠️ Browser | ~500 | Browse authenticated company employee roster directory | |
| ⚠️ Browser | ~100 | Verify Chrome DevTools Protocol connectivity and login state |
Tool Name | Alias | Risk Tier | Est. Tokens | Description |
| ⛔ Disabled by Default | ~500 | Query internal LinkedIn Voyager API via |
🏗️ System Flow & Hybrid RAG Architecture
1. High-Level System Flow
flowchart TD
classDef client fill:#1e1e38,stroke:#8B5CF6,stroke-width:2px,color:#fff;
classDef server fill:#0f172a,stroke:#0A66C2,stroke-width:2px,color:#fff;
classDef engine fill:#064e3b,stroke:#10B981,stroke-width:2px,color:#fff;
classDef rag fill:#312e81,stroke:#6366F1,stroke-width:2px,color:#fff;
classDef ext fill:#18181b,stroke:#71717a,stroke-width:1.5px,color:#fff;
subgraph ClientLayer["🤖 AI Clients & Orchestrators"]
C1["Claude Desktop"]:::client
C2["Cursor IDE"]:::client
C3["Claude Code CLI"]:::client
C4["Remote Agent via Streamable-HTTP"]:::client
end
subgraph CoreServer["⚡ LinkedIn MCP Zero (FastMCP 2.0 Engine)"]
direction TB
MW["Security & Rate Limiting Middleware<br/>(RFC 6585 · Single-Flight Coalescer · OAuth 2.1)"]:::server
Router{"45-Tool Router"}:::server
subgraph ScrapeEngine["Live Guest Scraping Engine"]
CF["curl_cffi Chrome 124 TLS Impersonator"]:::engine
HP["JSON-LD & DOM Extractors"]:::engine
JIT["Cryptographic Jitter (secrets)"]:::engine
end
subgraph RAGEngine["Hybrid Retrieval & Knowledge Engine"]
FTS["SQLite FTS5 Full-Text Index<br/>(Unicode61 Porter Stemming)"]:::rag
VEC["Dense Semantic Vector Store<br/>(Cosine Similarity)"]:::rag
RRF["Reciprocal Rank Fusion (RRF)<br/>Score = 1 / (60 + Rank_BM25) + 1 / (60 + Rank_Vec)"]:::rag
DSG["Dynamic In-Process Skill Graph<br/>(Real-Time Edge Weight Co-occurrence)"]:::rag
end
subgraph Intelligence["Decision & Viability Intelligence"]
GHOST["Ghost Job & Saturation Detector<br/>(analyze_job_viability)"]:::server
RESUME["Privacy-First Resume Parser<br/>(PDF / DOCX / Text)"]:::server
LLM_BRIDGE["LLM Sampling Bridge<br/>(Client-Side or Provider API)"]:::server
end
end
subgraph ExternalWeb["🌍 Production Web"]
LI["LinkedIn Public Gateway<br/>(Guest Search Endpoints)"]:::ext
MB["Multi-Board Engines<br/>(Indeed, Glassdoor, RemoteOK)"]:::ext
end
ClientLayer <==>|Stdio / Streamable-HTTP| MW
MW --> Router
Router --> ScrapeEngine
Router --> RAGEngine
Router --> Intelligence
ScrapeEngine <==>|Direct HTTPS TLS| LI
ScrapeEngine <==>|Direct HTTPS| MB
HP --> FTS
HP --> DSG
RESUME --> DSG
FTS & VEC --> RRF2. End-to-End Execution Sequence
sequenceDiagram
autonumber
actor User as AI Client (Claude / Cursor / Agent)
participant MW as Security Middleware & Coalescer
participant FastMCP as FastMCP 2.0 Router
participant Engine as Live Scraping Engine (curl_cffi)
participant Web as LinkedIn Public Gateway
participant SQLite as SQLite FTS5 & Skill Graph
participant RRF as Hybrid RRF Ranker
User->>MW: Call tool: search_jobs("Staff AI Engineer", "SF")
MW->>FastMCP: Deduplicated Request Passed (Single-Flight Protected)
FastMCP->>Engine: Dispatch Scraping Task
Engine->>Web: TLS Chrome 124 Impersonated GET Request
Web-->>Engine: 200 OK (Live HTML & JSON-LD Postings)
Engine->>SQLite: Index Postings into FTS5 & Learn Skill Co-occurrences
FastMCP->>RRF: Query FTS5 BM25 + Vector Similarity
RRF-->>FastMCP: Reciprocal Rank Fused Scores (k=60)
FastMCP-->>User: Structured Clean JSON Payload (<600 tokens)3. Concrete Architectural Implementation Layers
LinkedIn MCP Zero is structured into 5 decoupled, production-hardened subsystems:
Layer 1: Unified Transport & Gateway
Implementation:
src/linkedin_mcp_zero/server/app.py&src/linkedin_mcp_zero/server/middleware.pyFastMCP 2.0 Native: Supports both local process IPC (
stdio) for desktop AI clients and asynchronous network daemon (streamable-http) for cloud containers.Security Middleware: Sliding-window rate limiting emitting RFC 6585
Retry-After: 60headers, token verification, and OAuth 2.1 metadata endpoint.
Layer 2: Zero-Login Scraping & Impersonation Engine
Implementation:
src/linkedin_mcp_zero/engines/public_api.py&src/linkedin_mcp_zero/engines/multi_board.pyBrowser-Grade TLS: Uses
curl_cffitargeting public LinkedIn guest endpoints (/jobs-guest/jobs/api/seeMoreJobPostings/search) with Chrome 124 JA3/JA4 TLS fingerprinting.Single-Flight Coalescing: Duplicate parallel requests for identical queries share the same in-flight task to eliminate thundering herds and IP rate limits.
Anti-Fingerprinting: Cryptographic randomness via Python
secretsfor headers, User-Agent rotations, and network jitter.
Layer 3: Hybrid RAG & Reciprocal Rank Fusion (RRF)
Implementation:
src/linkedin_mcp_zero/storage/db.py&src/linkedin_mcp_zero/storage/vector_db.pySQLite FTS5 Full-Text: Embedded full-text virtual table with Unicode61 Porter tokenization delivering instant BM25 lexical rank.
Dense Cosine Vectors: Lightweight in-process vector store computing semantic embedding similarity.
RRF Score Fusion: Fuses lexical BM25 and dense semantic scores using Reciprocal Rank Fusion ($k=60$): $$\text{Score}{\text{RRF}}(d) = \sum{m \in {\text{BM25}, \text{Vector}}} \frac{1}{60 + \text{Rank}_m(d)}$$
Layer 4: Real-Time Dynamic Skill Graph
Implementation:
src/linkedin_mcp_zero/config/skills.py&src/linkedin_mcp_zero/storage/db.pyContinuous In-Process Learning: 200+ canonical technical skill nodes. When live postings or candidate resumes are analyzed, co-occurring technologies dynamically update edge weights in SQLite: $$\text{Weight}{A \leftrightarrow B} \leftarrow \text{Weight}{A \leftrightarrow B} + 1.0$$
Allows instant query expansion and technology ecosystem exploration via
expand_skill_cluster.
Layer 5: Decision Intelligence & Viability Scoring
Implementation:
src/linkedin_mcp_zero/engines/matching.py&src/linkedin_mcp_zero/engines/resume.pyGhost-Job Viability Engine (
analyze_job_viability): Algorithmic detection evaluating posting age, applicant pool volume, repost frequencies, and hiring velocity.Local In-Memory Resume Parsing: Extracts structured skills, experience, and education from PDF, DOCX, and TXT with zero cloud data transmission.
Model-Agnostic LLM Bridge (
src/linkedin_mcp_zero/utils/llm.py): Supports client-side sampling (Claude, Cursor, Gemini) with optional direct OpenAI and Anthropic provider execution.
📊 Feature Comparison Matrix
Feature | stickerdaniel (2.3k★) | Standard Scraping MCPs | LinkedIn MCP Zero v0.4.7 |
Total Synchronized Tools | ~10 tools | 2–5 tools | ✅ 45 Production Tools |
Zero-Login Public Search | ❌ None (Requires credentials) | ⚠️ 0–2 tools | ✅ 33 Working Tools (No Login) |
Data Authenticity | ⚠️ Static/Cached | ❌ Frequent synthetic mocks | ✅ 100% Real-Time Live Network |
Ghost Job & Saturation Analysis | ❌ None | ❌ None | ✅ Algorithmic ( |
Dynamic Skill Graph Learning | ❌ None | ❌ None | ✅ Live SQLite Co-occurrence Learning |
Hybrid BM25 + Vector RRF RAG | ❌ None | ❌ None | ✅ SQLite FTS5 + Dense Vector RRF ($k=60$) |
Multi-Job Board Federation | ❌ LinkedIn only | ❌ Single source | ✅ 5 Major Job Boards Integrated |
Local Resume Parsing (PDF/DOCX) | ❌ None | ❌ None | ✅ Zero-Leakage In-Memory Parsing |
Transport Protocol Support | Stdio only | Stdio only | ✅ Stdio + Streamable HTTP (FastMCP 2.0) |
Single-Flight Request Coalescing | ❌ None | ❌ None | ✅ Prevents Duplicate Network Hits |
Spreadsheet Formula Neutralization | ❌ Unescaped CSV | ❌ Unescaped CSV | ✅ Escapes |
One-Click Diagnostic CLI | ❌ None | ❌ None | ✅ Built-in |
🚀 Production Deployment & Cloud Hosting
LinkedIn MCP Zero can be executed locally as a stdio child process or hosted online as a high-performance cloud service via Streamable HTTP / SSE mode.
HTTP / Cloud Endpoints
Service Status & Discovery:
GET /(Public JSON status and tool count)Health & Diagnostic Probe:
GET /health(Liveness & readiness probe for cloud balancers)MCP 2.0 Streaming SSE:
GET /sseorPOST /sse(Streamable MCP endpoint for remote AI agents)OAuth 2.1 Discovery:
GET /.well-known/oauth-protected-resource(RFC 9728 metadata)
Cloud Provider Quickstart
1. Render (1-Click or Blueprint)
Deploy automatically using render.yaml:
Click Deploy to Render above or connect your GitHub repository in the Render Dashboard.
Render automatically provisions the Docker container, configures the
/healthcheck, and sets an auto-generatedLINKEDIN_MCP_API_KEY.
2. Railway (1-Command CLI)
Deploy using the Railway CLI and railway.json:
npm i -g @railway/cli
railway login
railway init
railway up3. Fly.io (Global Edge Deployment)
Deploy across worldwide regions using fly.toml:
fly launch --no-deploy
fly secrets set LINKEDIN_MCP_API_KEY="your-secure-key"
fly deploy4. Pre-built Docker Container (GitHub Container Registry)
Run the pre-built, hardened multi-arch image directly:
docker run -d -p 8000:8000 \
-e LINKEDIN_MCP_API_KEY="your-secure-token" \
-e RATE_LIMIT_PER_MINUTE=120 \
--name linkedin-mcp-zero \
ghcr.io/santhakumar-k-2004/linkedin-mcp-zero:latest5. Kubernetes Cluster
Deploy to any Kubernetes cluster (GKE, EKS, AKS, or local Minikube/k3s):
kubectl apply -f deploy/k8s.yaml🌐 Connecting Remote AI Clients to Hosted Server
Once hosted online (e.g. https://your-service.onrender.com), connect your favorite AI client using the remote SSE transport:
🖥️ Claude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"linkedin-remote": {
"url": "https://your-service.onrender.com/sse",
"headers": {
"x-api-key": "your-secure-token"
}
}
}
}⚡ Cursor IDE (.cursor/mcp.json)
{
"mcpServers": {
"linkedin-remote": {
"url": "https://your-service.onrender.com/sse",
"headers": {
"x-api-key": "your-secure-token"
}
}
}
}🔮 Google Antigravity IDE (.agents/mcp_config.json)
{
"mcpServers": {
"linkedin-remote": {
"url": "https://your-service.onrender.com/sse",
"headers": {
"x-api-key": "your-secure-token"
}
}
}
}📝 VS Code
{
"servers": {
"linkedin-remote": {
"url": "https://your-service.onrender.com/sse",
"headers": {
"x-api-key": "your-secure-token"
}
}
}
}🔍 Verification & Health Checking
Verify your remote deployment is live and healthy:
# Liveness probe
curl -f https://your-service.onrender.com/health
# Discovery endpoint
curl -H "x-api-key: your-secure-token" https://your-service.onrender.com/🔒 Security & Privacy Model
LinkedIn MCP Zero is architected around strict defense-in-depth principles:
Zero-Login by Default: 33 of 45 tools require no authentication, no credentials, and no cookies. Your account cannot be banned or restricted because it is never used.
Privacy-First Local Resume Parsing: PDF, DOCX, and text resume extraction (
analyze_resume,match_jobs_to_resume) runs completely in local memory on your device using native parsers. Candidate PII, resumes, and contacts are never sent to external analytics or telemetry services.Transparent Client LLM Reasoning: Qualitative reasoning tools (
tailor_resume,smart_match_jobs,generate_cover_letter,get_resume_insights_advanced) pass parsed candidate details strictly to your configured AI client (Claude, Cursor, Gemini, or local Ollama) as part of your prompt context. You retain 100% control over the prompt context.Spreadsheet Formula Injection Neutralization: All CSV/XLSX export routines prefix any cell starting with
=,+,-,@, or tab characters with'to mitigate CVE-style CSV macro execution.SSRF Domain Protection: Internal browser scrapers strictly enforce LinkedIn and recognized multi-board hostname validation to prevent unauthorized network pivot attempts.
Cryptographic Randomness: All jitter delays, user-agent rotations, and temporary identifiers use Python's cryptographically secure
secretsmodule instead of predictable pseudo-random seeds.Single-Flight Request Coalescing: Duplicate parallel requests for the same LinkedIn job or company URL are coalesced into a single flight, preventing thundering-herd rate limiting.
RFC 6585 Rate Limiting: Intelligent sliding-window rate limiters emit standard
Retry-After: 60headers and thread-safe circuit breakers when upstream rate limits are approached.
💻 Local Development & Testing
# Clone repository
git clone https://github.com/SanthaKumar-K-2004/linkedin-mcp-zero.git
cd linkedin-mcp-zero
# Install with development extras
uv sync --extra dev
# Run comprehensive test suite (125 unit tests)
uv run pytest tests/ -v
# Code quality and formatting checks
uv run ruff check .
uv run ruff format --check .
# Strict static type analysis
uv run mypy src/
# Automated security vulnerability scan
uv run bandit -r src/ -x tests -ll
# Build distributable wheel and source packages
uv build❓ Frequently Asked Questions
📄 License & Community
Licensed under the Apache License, Version 2.0. See the LICENSE file for complete details.
Educational & Research Notice: LinkedIn MCP Zero is developed for research, market analytics, and educational workflow automation. Please adhere to applicable platform terms of service and use responsibly.
Available Tools
33 toolsanalyze_job_viabilityBRead-onlyIdempotent
Assess hiring viability, applicant saturation, and ghost-job probability based on public signals.
Inputs: job_id_or_url (required). Returns: object
analyze_resumeARead-onlyIdempotent
Parse resume PDF/DOCX/text locally into structured skills, experience, and contact info without external calls.
Inputs: path (required). Returns: object
analyze_salary_offerCRead-onlyIdempotent
AI-powered salary analysis using real market data and client's LLM.
Inputs: job_id (required). Returns: object
check_saved_alertsARead-onlyIdempotent
Run saved alerts against live LinkedIn search and report newly discovered matches.
Inputs: ids. Returns: result
compare_jobsARead-onlyIdempotent
Compare 2-5 public LinkedIn jobs on requirements, skills, seniority, and viability.
Inputs: ids (required). Returns: object
confirm_exportBIdempotent
Export jobs with interactive user confirmation dialog.
Inputs: fmt (required), ids (required). Returns: object
deep_industry_analysisCRead-onlyIdempotent
Full industry analysis with real-time progress updates across active job postings.
Inputs: industry (required). Returns: object
expand_skill_clusterARead-onlyIdempotent
Explore technology ecosystems and related skills via in-process knowledge graph.
Inputs: skill (required). Returns: object
export_jobsBIdempotent
Export public job details to a local CSV, JSON, or Excel file.
Inputs: ids (required), fmt, filename. Returns: object
generate_cover_letterBRead-onlyIdempotent
Generate a tailored, compelling cover letter (max 200 words) using the client's LLM.
Inputs: job_id (required), resume_id (required). Returns: object
get_company_jobsARead-onlyIdempotent
Get real-time public job listings for a specific hiring company.
Inputs: co (required), loc, limit. Returns: result
get_company_profileBRead-onlyIdempotent
Get public company profile signals including headcount trends and hiring velocity.
Inputs: co (required). Returns: object
get_engine_statusCRead-onlyIdempotent
Show available engines.
Inputs: no named parameters. Returns: object
get_helpCRead-onlyIdempotent
Show tool documentation.
Inputs: tool. Returns: object
get_industry_insightsBRead-onlyIdempotent
Get public market insights and hiring demand for an industry vertical.
Inputs: ind (required). Returns: object
get_job_detailsARead-onlyIdempotent
Get full public LinkedIn job details including full description, salary, skills, and applicant count.
Inputs: id (required). Returns: object
get_job_salaryBRead-onlyIdempotent
Extract structured salary and compensation data from public job details.
Inputs: id (required). Returns: object
get_job_trendsARead-onlyIdempotent
Get hiring trends, demand velocity, and top demanded skills by role/location.
Inputs: kw (required), loc. Returns: object
get_resume_insightsBRead-onlyIdempotent
Get resume skill gaps, strengths, and suggestions with optional client LLM reasoning.
Inputs: id (required). Returns: object
get_resume_insights_advancedCRead-onlyIdempotent
Get advanced AI-powered insights on a resume using LLM reasoning.
Inputs: id (required). Returns: object
get_saved_alertsARead-onlyIdempotent
List all saved job alerts and their last check timestamps.
Inputs: no named parameters. Returns: result
get_tool_usage_summaryBRead-onlyIdempotent
Show local aggregate MCP usage by tool.
Inputs: no named parameters. Returns: object
get_usage_statsBRead-onlyIdempotent
Show recent local MCP usage and token estimates.
Inputs: limit. Returns: object
match_jobs_to_resumeBRead-onlyIdempotent
Rank public jobs against a saved resume using TF-IDF and cosine skill similarity with optional LLM reasoning.
Inputs: id (required), kw, loc, limit, +1 more. Returns: object
personalized_job_huntBRead-onlyIdempotent
Interactive job search that asks you what matters most via MCP elicitation.
Inputs: kw (required). Returns: object
reset_usage_statsCDestructive
Reset local usage metrics.
Inputs: confirm. Returns: object
save_job_alertBIdempotent
Save a recurring public job search alert to local database.
Inputs: kw (required), name (required), loc, freq. Returns: object
search_companiesCRead-onlyIdempotent
Search hiring companies from public job market signals.
Inputs: kw (required), limit. Returns: result
search_jobsARead-onlyIdempotent
Search real-time public LinkedIn job listings without authentication.
Returns deduplicated jobs with:
id: LinkedIn numerical job ID
t: Job title
co: Hiring organization name
loc: Job location
posted: Exact ISO date (YYYY-MM-DD)
age: Relative age (e.g. '2d', '1w')
benefits: Benefits badge (e.g. 'Actively Hiring')
sal: Salary range if published
relevance: Match percentage against search keyword (0-100%)
Inputs: kw (required), age, exp, loc, +3 more. Returns: result
search_jobs_advancedBRead-onlyIdempotent
Advanced public LinkedIn job search with company filtering, date sorting, and relevance scoring.
Inputs: kw (required), co, age, exp, +5 more. Returns: result
search_jobs_multiARead-onlyIdempotent
Search multiple public job boards (LinkedIn, Indeed, Glassdoor, ZipRecruiter) simultaneously.
Inputs: kw (required), age, loc, limit. Returns: result
smart_match_jobsBRead-onlyIdempotent
AI-powered job matching using the client's LLM for deep reasoning and fit explanation.
Inputs: resume_id (required). Returns: object
tailor_resumeCRead-onlyIdempotent
Universal multi-role ATS resume tailoring, keyword optimization, and real-time gap analysis across 9 industry disciplines.
Inputs: path (required), target_job, target_role. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 33 tools
Several clusters contain near-duplicates whose boundaries require careful reading: search_jobs vs search_jobs_advanced vs search_jobs_multi, get_resume_insights vs get_resume_insights_advanced, and get_industry_insights vs deep_industry_analysis. The descriptions do differentiate them (filters, multi-board, progress updates), so an agent can disambiguate, but misselection risk remains real. Utility tools (get_engine_status, get_help, get_usage_stats, get_tool_usage_summary) also blur into each other.
The dominant pattern is snake_case verb_noun (search_jobs, get_job_details, generate_cover_letter, save_job_alert), applied across most of the 33 tools. A handful deviate from verb-first form — personalized_job_hunt, deep_industry_analysis, confirm_export — and the advanced/basic suffixing is inconsistent, but overall the convention is predictable and readable.
33 tools is heavy for a job-search server and includes marginal entries like get_help, get_engine_status, reset_usage_stats, and two separate usage-summary tools. The core workflow (search, detail, resume, match, export) could be expressed in roughly half the surface. The volume increases selection cost more than it adds capability.
Coverage is broad: search (basic/advanced/multi-board), job and company detail, salary, trends, alerts, resume parsing/tailoring/matching, comparison, export, and viability analysis form a coherent lifecycle. Gaps are minor — no bookmarking of individual jobs or application tracking — but these are reasonable given the public, unauthenticated scope.
Maintenance
Related MCP Connectors
Hosted LinkedIn MCP server on your own account: 35 tools for search, profiles, inbox, posts, pages.
LinkedIn MCP with 47 tools: post, comment, DM and run comment-to-DM automations inside your limits.
Research saved LinkedIn contacts, review monitored public activity, and prepare engagement campaigns. Four product/setup tools work anonymously. Company tools require OAuth or a scoped API key: explicitly sign in and refresh tools. Paid actions require a credit budget. MCP cannot post comments or start extension delivery. Setup and examples: https://opencomment.ai/mcp
LinkedIn MCP for Claude, ChatGPT, Grok, Hermes: triage inbox, comment, find people, live profiles
Related MCP Servers
- AlicenseAqualityCmaintenanceSelf-hosted, ban-safe MCP server for LinkedIn that provides 22 tools for profiles, search, jobs, posts, connections, and messages. Integrates with any MCP-compatible client like Claude Desktop.581MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for programmable LinkedIn automation via Playwright, offering 20 tools for profile management, messaging, feed interaction, and job searching through real browser automation.18 npmMIT
- AlicenseAqualityDmaintenanceMCP server for safe LinkedIn automation: official-API posting, comments, and likes plus guest-endpoint job search and a local application tracker.16MIT
- AlicenseNot gradedqualityDmaintenanceLive 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.MIT