linkedin-mcp-tools
Installed, started with no arguments, no environment and no input, and listed its tools. Run 2026-11-16.
Needs to start: nothing
Returns a result when called with no setup: 2 of 5 tools tried
Contacts while installing and starting: nothing
What it contacted
Nothing besides the npm registry it was installed from. Watched from outside its sandbox while it was installed and started with no input. Its tools may still contact things when called.
Starting it
npx -y linkedin-mcp-tools@4.4.0
Installing a package runs its code. Use a sandbox for anything you have not read.
Calling its tools
5 tools that take no input and look read-only were called once with nothing. 2 returned a result.
whoami | Returned a result under 0.1 s · 10,903 characters |
health_check | Returned a result under 0.1 s · 1,515 characters |
get_my_profile | No usable answer tool reported an error: {"data":null,"meta":{"contractVersion":1,"fetchedAt":"2026-11-16T11:47:11.274Z","source":"engine","partial":false,"status":"error"},"err |
get_feed | No usable answer tool reported an error: {"data":null,"meta":{"contractVersion":1,"fetchedAt":"2026-11-16T11:47:11.278Z","source":"engine","partial":false,"status":"error"},"err |
get_inbox | No usable answer tool reported an error: {"data":null,"meta":{"contractVersion":1,"fetchedAt":"2026-11-16T11:47:11.286Z","source":"engine","partial":false,"status":"error"},"err |
During the calls it contacted nothing it had not already contacted.
Only tools whose names read like looking something up, with no required input, are tried, five at most. Tools that need input, and anything that sounds like it changes or sends something, are not called.
What its tools tell an agent
In the tool descriptions, nothing that talks about the user, other tools or private files, or uses hidden characters.
Found by simple pattern rules in each tool's description (up to 3,000 characters), quoted as written. Parameter descriptions are not scanned. A clean result is not a safety review.
Tools
whoami
Report server version, browser/login status, and capabilities.
health_check
Deep health check: cookie login state, a LIVE Voyager probe (confirms the API actually answers, not just that a cookie exists), and today's safety-budget headroom (per-action used/cap/remaining + pending invites).
close_session
Close Chrome while retaining this runtime’s profile ownership. Stop the server to release the profile.
get_my_profile
Get the authenticated user's own LinkedIn profile (experience, education, headline, summary).
get_profile username
Get a LinkedIn profile by public identifier (the slug in the profile URL, e.g. "satyanadella").
19 more tools
get_feed offset, cursor, count
Get recent posts from your LinkedIn home feed (author + post text).
get_notifications offset, cursor, count
Get your recent LinkedIn notifications (headline, time, read state).
search_people keywords, count
Search LinkedIn people by keywords. Returns name, headline, location, and public identifier (pass that to get_profile for full details).
search_jobs keywords, offset, cursor, location_geo_id, count
Search LinkedIn jobs by keywords (and optional location). Returns title, location, posted time.
get_inbox count
List a bounded first page of recent conversations with participant names, headlines and profile links. Continuation is not verified.
get_job_details job_id
Get full details for a job posting by its numeric id (the digits in /jobs/view/<id> or from search_jobs jobUrn).
search_companies keywords, count
Search LinkedIn companies by keywords. Returns name + universalName slug (pass that to get_company for full details).
get_company universal_name
Get a company by its LinkedIn URL slug (e.g. "google", "microsoft"). Returns name, description, website, industry, size, HQ.
get_company_posts universal_name, count
Get a company's recent posts by its LinkedIn URL slug (e.g. "google"). Returns post text + a short meta line.
get_company_employees universal_name, count
List employees LinkedIn surfaces for a company (by URL slug). Returns name, headline, and public identifier (feed the slug to get_profile). Prospecting core.
get_pending_invitations direction, count
List your pending connection invitations — received (inbound, with the urn/sharedSecret to accept later) and sent (outbound). Read-only.
get_conversation count, conversation_urn
Read a bounded page of messages by the conversation URN from get_inbox, sorted oldest-first with sender attribution when present. Continuation is not verified.
prepare_job_application job_id, job_title, company, requirements, evidence_library, include_drafts, include_interview_prep
Create a local, unsaved application worksheet with optional reusable evidence, resume/cover-letter drafts and interview practice when supported by the input schema. Only explicitly selected user-supplied evidence is used; nothing is fetched, filled, uploaded, submitted, sent or stored. Verify every claim and the current listing yourself.
export_application_tracker include_follow_up_plan, as_of, records
Format up to 50 application statuses that you enter into a CSV. Optionally classify follow-up dates against your explicit as_of time; no notifications are scheduled. It does not inspect LinkedIn, infer submission, or save data. A receipt-verified status requires your explicit confirmation.
connect_with_person profile_id, message, preview_token, preview_hash, operation_id, confirm
[ALPHA, write] Send a connection request. Gated: requires confirm:true. Returns a structured status (ok | duplicate | already_connected | restricted | quota_exhausted | failed | unknown). Counts against the daily connect cap.
send_message recipient_urn, thread_id, message, preview_token, preview_hash, operation_id, confirm
[ALPHA, write] Send a message. Pass thread_id / conversation_urn to REPLY into an existing conversation; new threads require a separate experimental opt-in and lack current live success evidence. Gated: requires confirm:true. Returns a structured status. Counts against the daily message cap.
create_post text, visibility, preview_token, preview_hash, operation_id, confirm
[ALPHA, write] Publish a text post to your feed. Gated: requires confirm:true. Returns a structured status.
react_to_post post_urn, reaction, preview_token, preview_hash, operation_id, confirm
[ALPHA, write] React to a post. Gated: requires confirm:true. Returns a structured status.
comment_on_post post_urn, text, preview_token, preview_hash, operation_id, confirm
[ALPHA, write] Comment on a post. Gated: requires confirm:true. Returns a structured status.
Descriptions are the package's own words, cut at 3,000 characters. Treat them as data.
Install facts
| License | MIT |
|---|---|
| Needs | node >=20.0.0 |
| Source | github.com/devag7/linkedin-mcp |
| Install scripts | None declared by it or anything installed with it. |
| Tarball | sha512-o1gw/RBPp+/6R0V2smtwcb5PId7C/79WuP5c/aI54LJCAC6ez0rFkVlWjK75wtiAhNAnVCo9I9mizeoFlcu5Ng== |
Check this report yourself
This site did not write the report. A public job on a GitHub-hosted machine did: the run, from this commit of the open-source runner. GitHub signed a token that names that job and the hash of the report, so any edit since would show.
Report as JSONExact text and tokenHow to verify it
Show it on your README
[](https://bragproof.smaverk.com/r/linkedin-mcp-tools)
New version out? Ask for a fresh report.