Skip to main content
Glama

PyPI Version GitHub Release Python Version FastMCP 2.0 Transports Tests Passing Security Audit Safe Mode Zero Login License

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

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 antigravity

Option 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 --doctor

Option 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

Claude Desktop

Configuration File Location:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

  • Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "linkedin-zero": {
      "command": "uvx",
      "args": [
        "linkedin-mcp-zero"
      ]
    }
  }
}

2. Cursor IDE

Cursor

Configuration File Location:

  • Workspace: .cursor/mcp.json

  • Global: ~/.cursor/mcp.json

{
  "mcpServers": {
    "linkedin-zero": {
      "command": "uvx",
      "args": [
        "linkedin-mcp-zero"
      ]
    }
  }
}

3. Visual Studio Code (Cline / Roo Code / Continue)

VS Code

Configuration File Location:

  • macOS: ~/Library/Application Support/Code/User/mcp.json

  • Linux: ~/.config/Code/User/mcp.json

  • Windows: %APPDATA%\Code\User\mcp.json

{
  "servers": {
    "linkedin-zero": {
      "command": "uvx",
      "args": [
        "linkedin-mcp-zero"
      ]
    }
  }
}

4. Claude Code CLI

Claude Code

One-line terminal command:

claude mcp add linkedin-zero -- uvx linkedin-mcp-zero

5. Google Antigravity IDE & Agent Framework

Google Antigravity

Configuration File Location:

  • Workspace: .agents/mcp_config.json

  • Global: ~/.gemini/antigravity-ide/mcp_config.json or ~/.gemini/config/mcp_config.json

{
  "mcpServers": {
    "linkedin-zero": {
      "command": "uvx",
      "args": [
        "linkedin-mcp-zero"
      ]
    }
  }
}

6. Cloud Hosted / Remote Streamable-HTTP

Cloud Hosted

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

search_jobs

sj

🟢 Public

~500

Search public LinkedIn job postings by keyword, location, and filters

search_jobs_multi

sjm

🟢 Public

~800

Multi-board meta-search across LinkedIn, Indeed, Glassdoor, RemoteOK, and ZipRecruiter

get_job_details

gj

🟢 Public

~400

Fetch complete job description, salary range, metadata, and criteria from URL or ID

get_company_jobs

gcj

🟢 Public

~400

Retrieve all active job openings for a specific company identifier

get_job_salary

gjs

🟢 Public

~250

Extract structured compensation numbers, currency, and pay periodicity from listings

get_job_trends

gjt

🟢 Public

~400

Analyze regional hiring demand, role popularity, and posting volume trends

get_industry_insights

gii

🟢 Public

~500

Sector-wide hiring momentum, top hiring companies, and demanded skillsets

deep_industry_analysis

dia

🟢 Public

~1200

Deep-dive industry landscape analysis with real-time research and market synthesis

search_jobs_advanced

sja

🟢 Public

~600

Filtered search by experience level, remote modality, job type, and posting freshness

compare_jobs

cj

🟢 Public

~800

Side-by-side comparative analysis of 2 to 5 job postings across criteria

personalized_job_hunt

pjh

🟢 Public

~1000

Interactive career preference matching tailored to target roles and geographies

Tool Name

Alias

Risk Tier

Est. Tokens

Description

get_company_profile

gcp

🟢 Public

~300

Extract organizational profile, employee counts, headquarters, and industry signals

search_companies

sc

🟢 Public

~300

Discover companies matching targeted keywords, industry sectors, and locations

Tool Name

Alias

Risk Tier

Est. Tokens

Description

analyze_resume

ar

🔒 Local

~600

Parse local PDF, DOCX, or text resume into structured skills, experience, and education

get_resume_insights

gri

🔒 Local

~500

Identify candidate skill gaps, missing keywords, and strategic resume improvements

tailor_resume

tr

🔒 Local

~800

Universal multi-role ATS resume tailoring, keyword optimization, and real-time gap analysis

get_resume_insights_advanced

ria

🔒 Local

~800

Deep resume critique leveraging client LLM reasoning for high-impact tailoring

match_jobs_to_resume

mjr

🟢 Local/Pub

~700

Rank live job postings against candidate resume using Hybrid BM25 + Vector RRF

smart_match_jobs

smj

🟢 Local/Pub

~900

AI-driven semantic match reasoning providing qualitative candidate-job fit analysis

generate_cover_letter

gcl

🟢 Local/Pub

~800

Generate tailored, high-converting cover letters mapped to actual job requirements

Tool Name

Alias

Risk Tier

Est. Tokens

Description

analyze_job_viability

ajv

🟢 Public

~350

Ghost job detector: Evaluates repost history, applicant saturation, and hiring probability

expand_skill_cluster

esc

🔒 Local

~200

Dynamic Skill Graph: Query live technology co-occurrence networks learned in SQLite

analyze_salary_offer

aso

🟢 Local/Pub

~600

Benchmark compensation offers against live scraped market distributions

get_tool_usage_summary

gtus

🔒 Local

~200

Real-time breakdown of tool invocation counts, error rates, and token consumption

Tool Name

Alias

Risk Tier

Est. Tokens

Description

save_job_alert

sja

🔒 Local

~150

Save recurring search criteria with frequency settings

get_saved_alerts

gsa

🔒 Local

~200

List all active recurring job alerts

check_saved_alerts

csa

🟢 Public

~500

Poll live postings for matches against all saved alert queries

export_jobs

ej

🔒 Local

~200

Export scraped listings to CSV, JSON, or XLSX with formula injection protection

confirm_export

ce

🔒 Local

~100

Human-in-the-loop user approval for saving exports to filesystem

get_engine_status

ges

🔒 Local

~150

Inspect SQLite FTS5 database stats, cache hits, and circuit breaker status

get_help

gh

🔒 Local

~100

Interactive parameter documentation and schema inspector for all tools

get_usage_stats

gus

🔒 Local

~100

Cumulative session tokens and tool invocation statistics

reset_usage_stats

rus

🔒 Local

~50

Reset local telemetry metrics

WARNING

⚠️ 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

get_my_profile

gmp

⚠️ Browser

~500

Read personal authenticated profile summary, headline, and experience

get_person_profile

gpp

⚠️ Browser

~500

Read public or 1st-degree connection profile page details

search_people

sp

⚠️ Browser

~600

People search executed through active authenticated Chrome session

get_my_connections

gmc

⚠️ Browser

~600

Read connection roster names, titles, and connection timestamps

get_inbox

gi

⚠️ Browser

~500

List recent conversation summaries and unread thread counts

get_conversation

gco

⚠️ Browser

~600

Read conversation transcript messages (SSRF domain guarded)

get_feed

gf

⚠️ Browser

~600

Read authenticated LinkedIn home feed posts and updates

get_notifications

gn

⚠️ Browser

~400

Read incoming network notifications and interaction alerts

get_sidebar_profiles

gsp

⚠️ Browser

~400

Extract "People Also Viewed" sidebar profile recommendations

get_company_employees

gce

⚠️ Browser

~500

Browse authenticated company employee roster directory

check_session

cs

⚠️ Browser

~100

Verify Chrome DevTools Protocol connectivity and login state

Tool Name

Alias

Risk Tier

Est. Tokens

Description

get_profile_voyager

gpv

⛔ Disabled by Default

~500

Query internal LinkedIn Voyager API via curl_cffi session (requires explicit VOYAGER_ENABLED=true opt-in)


🏗️ 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 --> RRF

2. 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.py

  • FastMCP 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: 60 headers, 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.py

  • Browser-Grade TLS: Uses curl_cffi targeting 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 secrets for 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.py

  • SQLite 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.py

  • Continuous 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.py

  • Ghost-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 (analyze_job_viability)

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 =, +, -, @ Formula Injection

One-Click Diagnostic CLI

❌ None

❌ None

✅ Built-in --doctor Diagnostic


🚀 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 /sse or POST /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 /health check, and sets an auto-generated LINKEDIN_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 up

3. 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 deploy

4. 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:latest

5. 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:

  1. 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.

  2. 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.

  3. 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.

  4. 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.

  5. SSRF Domain Protection: Internal browser scrapers strictly enforce LinkedIn and recognized multi-board hostname validation to prevent unauthorized network pivot attempts.

  6. Cryptographic Randomness: All jitter delays, user-agent rotations, and temporary identifiers use Python's cryptographically secure secrets module instead of predictable pseudo-random seeds.

  7. 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.

  8. RFC 6585 Rate Limiting: Intelligent sliding-window rate limiters emit standard Retry-After: 60 headers 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.

NOTE

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 tools
analyze_job_viabilityB
Read-onlyIdempotent

Assess hiring viability, applicant saturation, and ghost-job probability based on public signals.

Inputs: job_id_or_url (required). Returns: object

analyze_resumeA
Read-onlyIdempotent

Parse resume PDF/DOCX/text locally into structured skills, experience, and contact info without external calls.

Inputs: path (required). Returns: object

analyze_salary_offerC
Read-onlyIdempotent

AI-powered salary analysis using real market data and client's LLM.

Inputs: job_id (required). Returns: object

check_saved_alertsA
Read-onlyIdempotent

Run saved alerts against live LinkedIn search and report newly discovered matches.

Inputs: ids. Returns: result

compare_jobsA
Read-onlyIdempotent

Compare 2-5 public LinkedIn jobs on requirements, skills, seniority, and viability.

Inputs: ids (required). Returns: object

confirm_exportB
Idempotent

Export jobs with interactive user confirmation dialog.

Inputs: fmt (required), ids (required). Returns: object

deep_industry_analysisC
Read-onlyIdempotent

Full industry analysis with real-time progress updates across active job postings.

Inputs: industry (required). Returns: object

expand_skill_clusterA
Read-onlyIdempotent

Explore technology ecosystems and related skills via in-process knowledge graph.

Inputs: skill (required). Returns: object

export_jobsB
Idempotent

Export public job details to a local CSV, JSON, or Excel file.

Inputs: ids (required), fmt, filename. Returns: object

generate_cover_letterB
Read-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_jobsA
Read-onlyIdempotent

Get real-time public job listings for a specific hiring company.

Inputs: co (required), loc, limit. Returns: result

get_company_profileB
Read-onlyIdempotent

Get public company profile signals including headcount trends and hiring velocity.

Inputs: co (required). Returns: object

get_engine_statusC
Read-onlyIdempotent

Show available engines.

Inputs: no named parameters. Returns: object

get_helpC
Read-onlyIdempotent

Show tool documentation.

Inputs: tool. Returns: object

get_industry_insightsB
Read-onlyIdempotent

Get public market insights and hiring demand for an industry vertical.

Inputs: ind (required). Returns: object

get_job_detailsA
Read-onlyIdempotent

Get full public LinkedIn job details including full description, salary, skills, and applicant count.

Inputs: id (required). Returns: object

get_job_salaryB
Read-onlyIdempotent

Extract structured salary and compensation data from public job details.

Inputs: id (required). Returns: object

get_resume_insightsB
Read-onlyIdempotent

Get resume skill gaps, strengths, and suggestions with optional client LLM reasoning.

Inputs: id (required). Returns: object

get_resume_insights_advancedC
Read-onlyIdempotent

Get advanced AI-powered insights on a resume using LLM reasoning.

Inputs: id (required). Returns: object

get_saved_alertsA
Read-onlyIdempotent

List all saved job alerts and their last check timestamps.

Inputs: no named parameters. Returns: result

get_tool_usage_summaryB
Read-onlyIdempotent

Show local aggregate MCP usage by tool.

Inputs: no named parameters. Returns: object

get_usage_statsB
Read-onlyIdempotent

Show recent local MCP usage and token estimates.

Inputs: limit. Returns: object

match_jobs_to_resumeB
Read-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_huntB
Read-onlyIdempotent

Interactive job search that asks you what matters most via MCP elicitation.

Inputs: kw (required). Returns: object

reset_usage_statsC
Destructive

Reset local usage metrics.

Inputs: confirm. Returns: object

save_job_alertB
Idempotent

Save a recurring public job search alert to local database.

Inputs: kw (required), name (required), loc, freq. Returns: object

search_companiesC
Read-onlyIdempotent

Search hiring companies from public job market signals.

Inputs: kw (required), limit. Returns: result

search_jobsA
Read-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_advancedB
Read-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_multiA
Read-onlyIdempotent

Search multiple public job boards (LinkedIn, Indeed, Glassdoor, ZipRecruiter) simultaneously.

Inputs: kw (required), age, loc, limit. Returns: result

smart_match_jobsB
Read-onlyIdempotent

AI-powered job matching using the client's LLM for deep reasoning and fit explanation.

Inputs: resume_id (required). Returns: object

tailor_resumeC
Read-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

    B3/5.0

    Scored across 33 tools

    Disambiguation3/5

    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.

    Naming Consistency4/5

    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.

    Tool Count2/5

    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.

    Completeness4/5

    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

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Self-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.
      58
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server for programmable LinkedIn automation via Playwright, offering 20 tools for profile management, messaging, feed interaction, and job searching through real browser automation.
      18 npm
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      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.
      MIT