LinkedIn MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BROWSERBASE_CDP_URL | Yes | Browserbase CDP WebSocket endpoint URL (e.g., wss://connect.browserbase.com?apiKey=YOUR_API_KEY&sessionId=SESSION_ID) |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_profileA | Get a LinkedIn user profile summary including name, headline, location, about section, experience, and education. Defaults to the currently logged-in user's profile. |
| search_jobsA | Search LinkedIn job listings by title, location, and/or company. Returns a list of matching jobs with title, company, location, and URL. |
| get_job_detailsB | Get the full details of a specific LinkedIn job posting including description, requirements, salary range (if available), and apply link. |
| get_connectionsC | List your LinkedIn connections with their name, headline, and profile URL. Optionally filter by name. |
| get_messagesC | Get recent LinkedIn messages and InMail conversations including sender, preview, and timestamp. |
| send_connection_requestB | Send a LinkedIn connection request to a user, with an optional personalised note (max 300 characters). |
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 6 tools
Each tool has a clearly distinct purpose targeting different LinkedIn resources: connections, job details, messages, profiles, job search, and connection requests. There is no overlap in functionality, making it easy for an agent to select the right tool.
All tools follow a consistent verb_noun naming pattern (e.g., get_connections, search_jobs, send_connection_request). The verbs are appropriate and descriptive, with no deviations in style or convention.
With 6 tools, the server is well-scoped for LinkedIn interactions, covering key areas like profiles, connections, jobs, and messaging. Each tool earns its place without being overwhelming or insufficient for the domain.
The tool set covers core LinkedIn functionalities well, including reading (profiles, connections, jobs, messages) and writing (connection requests). Minor gaps exist, such as no tools for updating profiles, managing connections (e.g., removing), or interacting with posts, but agents can still handle common workflows effectively.