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., "@remote-mcp-linkedin extract LinkedIn profile for Jane Smith"
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.
Read-only MCP server for collecting visible LinkedIn profile, post, and contact-network data and turning profile data into structured dossiers. It uses a local browser bridge, so the browser session stays on the user's machine.
Opens visible LinkedIn profile pages through a local browser bridge
Extracts basic public / visible profile data
Collects visible profile posts from /recent-activity/all/
Searches visible people/contact-network results, defaulting to 1st-degree contacts
Builds a structured dossier for AI agents
Exposes the result through MCP tools
Related MCP server: LinkedIn MCP Server
linkedin_profile_get - returns normalized visible profile data
linkedin_profile_posts - returns visible posts from a profile activity page
linkedin_contact_network_search - returns visible people-search/contact results
linkedin_profile_dossier - returns a structured profile dossier with evidence, gaps, warnings, and confidence
Read-only by design
No messages, likes, comments, connection requests, or job actions
No cookies or browser session data are exported
The browser runs locally
python3 -m venv .venv
source .venv/bin/activate
python -m pip install -e ".[dev]"
export REMOTE_MCP_LINKEDIN_BRIDGE_TOKEN="replace-with-a-long-random-token"
remote-mcp-linkedin-server
remote-mcp-linkedin-bridgeSmall prototype.
Working:
MCP server
local bridge
profile data tool
profile posts tool
contact network search tool
dossier tool
JSON result storage
Not ready:
robust LinkedIn parser
production extraction
advanced profile analysis
MIT
Build a deterministic structured dossier from visible profile sections.
Inputs: username, profile_url, include_posts. Returns: object
Return normalized raw visible profile sections via the local bridge.
Inputs: sections, username, profile_url. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have clearly distinct purposes: one produces a structured dossier, the other returns raw profile sections. There is no ambiguity about which to use for a given task.
Both tools share the 'linkedin_profile_' prefix, but one uses a noun ('dossier') and the other a verb ('get'), which is inconsistent. A consistent verb-noun pattern would be clearer.
With only two tools, the server feels thin for a platform as broad as LinkedIn. However, the tools are well-focused on profile data, so the count is borderline reasonable for that narrow scope.
The server covers only profile retrieval in two formats, missing many common LinkedIn operations like searching, messaging, or managing connections. This is a significant gap for general LinkedIn usage.
Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.
Hosted LinkedIn MCP server on your own account: 35 tools for search, profiles, inbox, posts, pages.
A hosted LinkedIn MCP server for your own account. Paste one address into Claude, ChatGPT, Cursor or n8n to read your inbox, send messages and invitations, and search people. Free to start. Not made by LinkedIn.
Managed LinkedIn MCP server for AI agents: search, connect, message and enrich on accounts you own.
