LinkedIn MCP Server
An MCP server for LinkedIn REST API v2 that enables AI assistants to create, list, and delete posts, manage events, upload images, comment, and react—featuring OAuth 2.0 with session persistence, local post history tracking, and multiple automated tests
Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
souravdasbiswas
Source: Glama
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
linkedin_auth_startStart the LinkedIn OAuth authentication flow. Returns a URL the user must open in their browser to authorize the application.
linkedin_auth_callbackComplete the LinkedIn OAuth flow by providing the authorization code and state from the callback URL.
linkedin_auth_logoutRevoke the LinkedIn access token and log out.
linkedin_create_eventCreate a LinkedIn event. Supports online, in-person, and hybrid formats.
linkedin_get_eventGet details of a LinkedIn event by its ID.
linkedin_create_postCreate a new LinkedIn post. Supports text posts and posts with article links. Use linkedin_upload_image first if you want to attach an image.
linkedin_delete_postDelete a LinkedIn post by its URN. You can only delete your own posts.
linkedin_create_commentComment on a LinkedIn post.
linkedin_react_to_postReact to a LinkedIn post (like, celebrate, support, love, insightful, funny).
linkedin_upload_imageUpload an image for use in a LinkedIn post. Returns an image URN to use with linkedin_create_post.
linkedin_list_my_postsList posts you created through this MCP server. Shows text preview, visibility, and URN for each post.
linkedin_get_my_profileGet the authenticated LinkedIn user's profile including name, headline, and profile picture URL.
linkedin_get_my_emailGet the authenticated LinkedIn user's email address.
linkedin_get_auth_statusCheck the current LinkedIn authentication status, granted scopes, and token expiry.
linkedin_get_rate_limitsGet current rate limit usage for all LinkedIn API endpoints that have been called.
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
When Vitest UI server is listening, arbitrary file can be read and executed
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default
LINKEDIN_API_BASE_URLNo https://api.linkedin.com API base URL (override for testing)LINKEDIN_AUTH_BASE_URLNo https://www.linkedin.com/oauth/v2 Auth base URLLINKEDIN_CLIENT_IDe =your_client_id \LINKEDIN_CLIENT_SECRETe =your_client_secret \LINKEDIN_MCP_DATA_DIRNo ~/.linkedin-mcp Directory for token storageLINKEDIN_REDIRECT_URINo http://localhost:3000/callback OAuth redirect URITool annotations
No tools have read-only/destructive annotations
Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.
All four hints declared on every tool
15/15 tools missing one or more hints — linkedin_auth_start (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); linkedin_auth_callback (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); linkedin_auth_logout (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +12 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.
For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.
Tool inputs are validated
8/15 tool handlers declare input schemas (53%)
Declare an inputSchema with zod/joi/yup on every tool definition.
Tool handlers catch errors
14/15 tool handlers wrap calls in try/catch (93%)
Wrap each tool handler body in try/catch and return a structured error response.
Tests pass
npm test failed — tests do not pass
Make sure npm test runs cleanly. Common cause: missing build step or missing env vars.
Shell command execution
3 child_process calls — runs shell commands
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Production dependencies are patched
0 critical, 3 high severity in production deps — @modelcontextprotocol/sdk@1.12.1 (high), @modelcontextprotocol/sdk@1.12.1 (high)
Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.
Dev dependencies
1 critical/high in dev-only deps (does not ship to users)
Upgrade dev dependencies when convenient.
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/souravdasbiswas/linkedin-mcp-server)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check