linkedin-mcp-server
MCP ServerFreeOpen-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI assistant access to profiles, companies, jobs, and messages.
Capabilities8 decomposed
linkedin profile data retrieval via mcp protocol
Medium confidenceExposes LinkedIn profile information (name, headline, location, connections, experience, education) through the Model Context Protocol as structured tool calls that Claude and other MCP-compatible AI assistants can invoke. Uses the linkedin-api Python library to authenticate and fetch profile data, then marshals responses into MCP tool result format for seamless LLM integration.
Implements LinkedIn data access as native MCP tools rather than REST endpoints, allowing Claude to directly invoke profile lookups within conversation context without intermediate API wrappers. Uses linkedin-api library's session-based authentication to maintain persistent LinkedIn connections across multiple tool calls.
Tighter Claude integration than generic LinkedIn API wrappers because it speaks MCP natively, eliminating serialization overhead and enabling Claude to reason about profile data inline during multi-step tasks.
company information lookup and enrichment
Medium confidenceRetrieves company metadata from LinkedIn (company name, industry, size, location, description, follower count) through MCP tool calls, enabling AI assistants to enrich company context during research or recruitment workflows. Fetches data via linkedin-api's company endpoint and structures results as MCP tool outputs for LLM consumption.
Exposes company lookup as a discrete MCP tool callable by Claude, allowing multi-step workflows where company research feeds into candidate evaluation or job matching without context switching between tools.
More integrated than calling LinkedIn's official API directly because it's pre-wrapped as an MCP tool; Claude can invoke it conversationally without managing authentication or response parsing.
job search and listing retrieval
Medium confidenceSearches LinkedIn job postings by keyword, location, and filters (job title, company, experience level) and returns structured job listings through MCP tools. Uses linkedin-api's job search endpoint to query LinkedIn's job database and marshals results into MCP tool format for Claude to process and reason about.
Wraps LinkedIn job search as an MCP tool, allowing Claude to perform multi-step job research workflows (search → filter → summarize → match to candidates) within a single conversation without context switching.
More conversational than LinkedIn's native job search UI because Claude can reason about results, apply custom filters, and cross-reference with candidate profiles in the same interaction.
direct messaging and conversation retrieval
Medium confidenceFetches LinkedIn direct messages and conversation history through MCP tools, allowing AI assistants to read and analyze message threads. Uses linkedin-api's messaging endpoints to retrieve conversation metadata and message content, then structures results as MCP tool outputs for LLM analysis and response generation.
Exposes LinkedIn messaging as an MCP tool, enabling Claude to access and analyze message threads directly within conversation context, supporting use cases like message summarization and recruiter outreach detection without leaving the LLM interface.
More integrated than checking LinkedIn messages manually because Claude can automatically summarize, categorize, and flag important conversations, reducing context-switching overhead.
mcp protocol server implementation and tool registration
Medium confidenceImplements a fully functional MCP server that registers LinkedIn data access functions as callable tools, handles MCP protocol handshakes, manages request/response serialization, and maintains session state across multiple tool invocations. Built on the MCP Python SDK, it exposes LinkedIn operations as standardized MCP tools that any MCP-compatible client (Claude Desktop, Cline, etc.) can discover and invoke.
Implements a complete MCP server lifecycle (initialization, tool registration, request handling, session management) using the MCP Python SDK, allowing LinkedIn to be exposed as a first-class tool ecosystem rather than a one-off integration.
More standardized than custom REST wrappers because it follows the MCP specification, enabling interoperability with any MCP-compatible client and reducing integration friction for developers adopting MCP-based architectures.
session-based linkedin authentication and credential management
Medium confidenceManages LinkedIn authentication using email/password credentials or session cookies, maintains authenticated sessions across multiple API calls, and handles session expiration/re-authentication. Uses linkedin-api's session management to persist authentication state, reducing the need to re-authenticate for each tool invocation while handling LinkedIn's anti-bot protections.
Uses linkedin-api's session-based authentication model rather than token-based APIs, allowing persistent connections across multiple tool calls while managing LinkedIn's strict anti-bot detection by maintaining realistic session behavior.
More resilient than stateless authentication because it reuses authenticated sessions, reducing authentication overhead and lowering the risk of triggering LinkedIn's bot-detection thresholds on each API call.
error handling and linkedin api failure recovery
Medium confidenceImplements error handling for LinkedIn API failures (authentication errors, rate limits, network timeouts, invalid requests) and maps them to meaningful MCP error responses. Catches linkedin-api exceptions and translates them into structured error messages that Claude and other MCP clients can interpret and act upon.
Maps linkedin-api exceptions to MCP error protocol, allowing Claude and other MCP clients to receive structured error information and adjust their behavior (e.g., retry, escalate, or inform the user) based on error type.
More informative than generic API errors because it translates LinkedIn-specific failures into MCP-compliant error responses, enabling intelligent error handling in AI workflows.
tool schema definition and discovery for mcp clients
Medium confidenceDefines JSON schemas for each LinkedIn tool (profile lookup, company search, job search, messaging) that describe input parameters, output structure, and tool metadata. Exposes these schemas via MCP's tool discovery mechanism, allowing Claude and other MCP clients to understand what tools are available, what parameters they accept, and what data they return.
Implements MCP tool schema definitions that allow Claude to understand LinkedIn tool capabilities at runtime, enabling Claude to invoke tools with correct parameters without explicit instruction or documentation lookup.
More discoverable than hardcoded tool lists because MCP clients can automatically parse tool schemas and present available tools to users, reducing onboarding friction.
Capabilities are decomposed by AI analysis. Each maps to specific user intents and improves with match feedback.
Related Artifactssharing capabilities
Artifacts that share capabilities with linkedin-mcp-server, ranked by overlap. Discovered automatically through the match graph.
Coresignal
** - Access comprehensive B2B data on companies, employees, and job postings for your LLMs and AI workflows.
linkedin-mcp-server
Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI assistant access to profiles, companies, jobs, and messages.
adzuna-mcp
MCP server: adzuna-mcp
sg-company-lookup-mcp
MCP server: sg-company-lookup-mcp
ContactOut MCP
ContactOut MCP unlocks instant access to verified professional emails and phone numbers, helping you reach prospects, candidates, and partners with ease. All you need is your ContactOut API key to get started.
Career Site Jobs
** - A MCP server to retrieve up-to-date jobs from company career sites.
Best For
- ✓AI agent builders integrating LinkedIn data into Claude workflows
- ✓Recruitment automation teams building candidate research pipelines
- ✓Solo developers prototyping MCP-based LinkedIn assistants
- ✓Recruitment platforms automating company context enrichment
- ✓AI agents building company research reports
- ✓Job board integrations needing company metadata
- ✓Job board builders integrating LinkedIn job data into AI workflows
- ✓Recruitment automation platforms matching candidates to opportunities
Known Limitations
- ⚠Requires valid LinkedIn credentials (email/password or session cookies) — no OAuth support
- ⚠LinkedIn actively blocks scraping; authentication may fail if LinkedIn detects bot-like behavior
- ⚠Rate-limited by LinkedIn's server-side protections; bulk profile fetches will trigger blocks
- ⚠Profile data freshness depends on LinkedIn's caching; real-time updates not guaranteed
- ⚠Cannot access private profile sections or restricted data (e.g., salary, detailed contact info)
- ⚠Company data availability depends on LinkedIn's public company pages; private companies may have limited data
Requirements
Input / Output
UnfragileRank
UnfragileRank is computed from adoption signals, documentation quality, ecosystem connectivity, match graph feedback, and freshness. No artifact can pay for a higher rank.
Repository Details
Last commit: May 3, 2026
About
Open-source MCP server for LinkedIn. Give Claude and any MCP-compatible AI assistant access to profiles, companies, jobs, and messages.
Categories
Alternatives to linkedin-mcp-server
Are you the builder of linkedin-mcp-server?
Claim this artifact to get a verified badge, access match analytics, see which intents users search for, and manage your listing.
Get the weekly brief
New tools, rising stars, and what's actually worth your time. No spam.
Data Sources
Looking for something else?
Search →