MCP Server for LinkedIn
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TIMEOUT | No | Browser timeout for page operations in milliseconds. Example: 10000. | 5000 |
| CHROME_PATH | No | Path to Chrome/Chromium executable for custom installations. | |
| PROXY_BYPASS | No | Comma-separated list of hosts to bypass the proxy, e.g., localhost,127.0.0.1,::1. | |
| PROXY_SERVER | No | Proxy server URL, e.g., http://host:port. Accepts scheme://host:port or combined with credentials. | |
| TOOL_TIMEOUT | No | Per-tool MCP execution timeout in seconds. Increase for heavy scrapes or cold-start Chromium. | 180.0 |
| PROXY_PASSWORD | No | Password for proxy authentication. | |
| PROXY_USERNAME | No | Username for proxy authentication. | |
| UV_HTTP_TIMEOUT | No | Timeout for HTTP requests made by uv during package installation. Set to 300 to avoid timeouts on slow connections. | |
| LOGIN_INLINE_WAIT | No | How long to wait inline for a tool call to resume after login completes, in seconds. | 25 |
| LINKEDIN_MCP_CONTAINER | No | Override runtime container detection. Use 'false' if the server is not actually in a container. | |
| AUTO_IMPORT_FROM_BROWSER | No | Whether to auto-import a LinkedIn session from a locally logged-in browser on first use. Set to 'false' to disable. | true |
| FASTMCP_HTTP_ALLOWED_HOSTS | No | JSON array of allowed HTTP hosts for streamable HTTP transport, e.g., '["mcp.example"]'. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_person_profileA | Get a specific person's LinkedIn profile. |
| search_peopleA | Search for people on LinkedIn. |
| connect_with_personA | Send a LinkedIn connection request or accept an incoming one. The tool is annotated with destructiveHint so MCP clients will prompt for user confirmation before execution. |
| get_sidebar_profilesA | Get profile links from sidebar recommendation sections on a LinkedIn profile page. Extracts profiles from "More profiles for you", "Explore premium profiles", and "People you may know" sidebar sections. Follows "Show all" links to return the full list from each section. Sections that redirect to linkedin.com/premium are skipped. |
| get_my_profileA | Get the authenticated user's own LinkedIn profile. Navigates to /in/me/ and resolves the redirect to obtain the real username before scraping, so the url field in the result is the actual profile URL (e.g. linkedin.com/in/johndoe/) rather than /in/me/. |
| get_company_profileA | Get a specific company's LinkedIn profile. |
| get_company_postsA | Get recent posts from a company's LinkedIn feed. |
| search_companiesB | Search for companies on LinkedIn. |
| get_company_employeesA | List employees at a company from the LinkedIn /people/ page, including the demographics aggregate that this view exposes: where employees live, where they studied, and a function breakdown (Engineering, Sales, Operations, etc.). The demographics are unique to this tool. For filtered search by network degree (1st/2nd/3rd) or location, prefer search_people with current_company set to the company URN id. That path also returns more result pages than the /people/ tab. The optional keywords filter narrows results by name, title, or skill. company_name must be the exact LinkedIn URL slug (the path segment after /company/), not the display name. LinkedIn assigns unique slugs and the display name often does not match. For example, the AI lab Anthropic lives at /company/anthropicresearch/, not /company/anthropic/. If you are unsure of the slug, call search_companies first and pick the slug from the returned references. |
| get_job_detailsA | Get job details for a specific job posting on LinkedIn. |
| search_jobsA | Search for jobs on LinkedIn. Returns job_ids that can be passed to get_job_details for full info. |
| get_saved_jobsA | List job postings saved by the authenticated LinkedIn user. Returns job_ids that can be passed to get_job_details for full info. |
| get_inboxA | List recent conversations from the LinkedIn messaging inbox. |
| get_conversationA | Read a specific messaging conversation. Provide either linkedin_username or thread_id to identify the conversation. When looked up by linkedin_username, resolution searches the messaging inbox for the participant's display name and click-visits every matching row to capture its thread ID — LinkedIn's sidebar has no anchor hrefs or thread-id attributes, so this is the only available path. Each visit selects the row in the LinkedIn UI and may mark it as read. Pass thread_id directly to skip this enumeration. |
| search_conversationsC | Search messages by keyword. |
| send_messageA | Send a message to a LinkedIn user. The recipient must be directly messageable from the profile page. This is a write operation when confirm_send is True. |
| get_feedA | Get posts from the authenticated user's LinkedIn feed. |
| search_postsA | Search LinkedIn posts/content globally by keyword (the "Posts" tab). Use this to catch informal hiring posts ("we're hiring", "Buscamos ...", "estamos contratando", "join our team") that often appear before a formal job listing exists. This is global content search, distinct from get_feed (your own home feed) and get_company_posts (one company's page). |
| close_sessionA | Close the current browser session and clean up resources. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 19 tools
Each tool targets a distinct resource and action: search_* tools are separated by entity (companies, jobs, people, conversations, posts), and get_* tools are separated by specific content (feed, company posts, job details, profiles, conversation). Even potentially similar tools like get_feed, get_company_posts, and search_posts have clear contextual differences described.
All 19 tool names follow a consistent lowercase_with_underscores verb_noun pattern: get_*, search_*, send_*, connect_*, close_*. There is no mixing of styles or vague verbs, making the toolset predictable and easy to navigate.
With 19 tools, the server is slightly above the typical 3-15 range but each tool addresses a real LinkedIn feature area (feed, jobs, messaging, people, companies, posts). No tools are redundant, and the count reflects the multi-domain scope of LinkedIn, so it feels reasonable rather than bloated.
The server covers core LinkedIn workflows: reading feed (own, company, global search), searching and retrieving profiles/companies/employees, job search and details, messaging (inbox, conversation, search, send), and connection requests. Minor gaps exist (e.g., no ability to post or like), but for a read/messaging/connection automation server, the surface is nearly complete.