Linked API
io.github.Linked-API/linkedapi-mcp · v2.3.21 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Manage LinkedIn messages, connections, posts, and profile data through Linked API.
Source: https://github.com/Linked-API/linkedapi-mcp
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 101 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 8 tool(s) can execute commands or delete data (remove_connection, nv_delete_list, nv_delete_saved_search, nv_remove_account_from_list, nv_remove_lead_from_list and 3 more). Require confirmation before the agent calls them. |
What was checked
- https://mcp.linkedapi.io/mcp: answers without auth
- npm: @linkedapi/mcp@2.3.21 (static checks only; code not executed)
Public tools: send_message, sync_inbox, get_inbox, sync_conversation, get_conversation, sync_network, get_network, manage_conversation, check_connection_status, retrieve_connections, send_connection_request, withdraw_connection_request, retrieve_pending_requests, retrieve_invitations, accept_invitation, ignore_invitation, remove_connection, search_companies, search_people, search_jobs, search_posts, fetch_company, fetch_person, endorse_person_skill, endorse_person_skills, fetch_post, fetch_job, react_to_post, comment_on_post, react_to_comment
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-linked-api-linkedapi-mcp-5ba18bd0)