LinkedIn Sales Navigator

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/nick-choudhary-linkedin-sales-nav-mcp

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

12 read · 2 write · 5 delete

Secrets

None asked for

Install scripts

Not scanned yet

Runs as

Python package

Tools (19)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• check_repliesCheck For Replies

  Read the Sales Navigator inbox and mark leads who replied. Sends nothing. Reads structured message threads — a reply is a message whose author is the lead rather than you, matched to leads by the stable member_id, so nothing depends on parsing rendered text or guessing who spoke last. Only leads this server recorded a send for are considered; a conversation with someone you messaged by hand elsewhere is left alone. A lead marked `replied` still counts as contacted, so a reply can never cause a duplicate first touch. Args: campaign: Restrict matching to one campaign. Omit for all. sc…

• check_session_statusCheck Session Statusread-only

  Check whether the browser profile has a live Sales Navigator session. Launches (or reuses) the browser and verifies it lands on a signed-in /sales page. Use this first when searches fail — it tells you if you need to run `--login` again. Returns: Dict with logged_in (bool), plus the profile directory and headless setting for this server.

• enrich_leadsEnrich Leads With Open Profile Statusread-only

  Add Open Profile / InMail status to a saved contact search. Search results cannot carry this. Sales Navigator's search payload has an `openLink` field, but it is `false` for everyone — the real flag is `memberBadges.openLink`, which only the profile endpoint returns, one request per lead. There is no bulk endpoint. Two methods: * `compose` (default): clicks Message on each lead's row in the search results (no lead page load) and records what the panel loads — Open Profile status plus **contact info** (emails, websites, phones), **insights** (recent posts, job change, shared connecti…

• export_resultsExport Resultsread-only

  Export a saved query's records to files under the output folder. Args: url_or_hash: The query's url_hash (from list_queries) or its original search URL. ctx: FastMCP context. format: 'json', 'csv', or 'both' (default). JSON is the full store view; CSV is flat columns for spreadsheets. include_raw: Include LinkedIn's raw element JSON in the export. Returns: Dict with url_hash, record_count, and the written file paths (output/<url_hash>/query.json + the record file(s)).

• fetch_lead_profilesFetch Full Lead Profilesread-only

  Fetch full profiles for a query's leads — depth 3, drafting material. Same endpoint as `enrich_leads`, much wider projection: headline, summary, full position descriptions, educations, skills, languages, volunteering, connection counts. About 15 KB per lead against ~240 bytes for the enrichment screen. Deliberately separate from `enrich_leads`. The screen runs across a whole list to find who is free to message; this runs only for the leads you are about to write to. Merging them would pull heavy payloads for leads you never contact, and would make "recent activity" as stale as the screen. R…

• get_lead_profileGet Lead Profileread-only

  Read one stored full profile — the payload you draft a message from. Reads from the local store only; it does not call LinkedIn. Run `fetch_lead_profiles` first for leads that have not been fetched. Args: member_id: Stable LinkedIn member id.

• get_resultsGet Results Sampleread-only

  Pull a bounded slice of a saved query's records into the conversation for analysis. Bounded on purpose — for large sets, prefer export_results and analyze the file with code rather than loading everything into context. Args: url_or_hash: The query's url_hash or original search URL. ctx: FastMCP context. limit: Max records to return (1-200, default 25). offset: Records to skip (for paging through the sample). Returns: Dict with url_hash, total_records, returned, offset, and `records`.

• list_queriesList Saved Queriesread-only

  List every saved search and its progress. Returns: Dict with `queries`: for each, url_hash, url, scraper_type, status (new|in_progress|paused|complete), last_page, total_available, records_count. Use a url_hash with export_results or get_results.

• next_outreach_batchNext Outreach Batchread-only

  Leads eligible for a first message, best channel first. Read-only. Excludes anyone already sent to in ANY campaign — dedupe is on the stable member_id, so a person found by three searches is messaged once — and anyone already handled in this campaign. With open_profile_only (the default) only leads confirmed Open Profile by enrich_leads come back: those are free to message. Run enrich_leads first or this returns nothing. Args: url_or_hash: The query's url_hash or original search URL. campaign: A label for this outreach run, e.g. "direct-mail-q3". Dedupe is global, but status…

• outreach_nextOpen Next Lead For Outreach

  Open the next eligible lead's message panel and return what to draft from. Walks the search results row by row in the visible browser and clicks Message on the next lead that is not yet contacted. The panel's own data is captured -- Open Profile status, contact info, insights (recent posts, job change, shared connections), existing conversation. Leads that are not Open Profile or already have a conversation are skipped and recorded; the first eligible one is left open and returned. Then draft from `lead` and call `outreach_submit`. Modes: * draft -- submit saves the draft; nothing is…

• outreach_skipSkip The Open Lead

  Close the open lead's panel without sending and record the reason.

• outreach_statusOutreach Statusread-only

  Counts by status and channel, plus remaining daily cap. Args: campaign: Restrict to one campaign. Omit for all.

• outreach_submitSubmit Draft For The Open Leadcan change or delete data

  Fill the open lead's panel with this draft, then act per the mode. The draft is validated first (length, banned phrases, and every `evidence_used` entry must be a field of the `lead` returned by outreach_next). In supervised/auto mode the panel is filled, a countdown runs in the page, and at zero the panel is read back -- so edits made during the countdown are what gets checked and sent. Skip in the page records the lead as skipped. Sends use the same two-phase commit, daily cap and dedupe as send_message, and only ever go to Open Profile leads. Args: url_or_hash: Same query as outreach_…

• pipeline_statusPipeline Statusread-only

  One funnel view of a query: scraped → enriched → open → profiled → sent. State otherwise lives across four tables; this joins it so "where is everything?" is one call instead of mental arithmetic. Args: url_or_hash: The query's url_hash or original search URL.

• reconcile_outreachReconcile Ambiguous Sends

  Settle sends stuck in `sending` by checking LinkedIn itself. A `sending` row means the Send click happened but the outcome was never recorded — a crash, a killed browser, a disconnect. The message either went out or it did not, and only LinkedIn knows. This opens each lead's conversation, looks for our own message text, and resolves the row to `sent` or `failed`. Sends nothing. Until reconciled, an ambiguous lead is treated as already-contacted, so the uncertainty can never produce a duplicate — it can only delay a legitimate follow-up. Args: campaign: Restrict to one campaign. Omit for…

Signals

Stars

2

Forks

1

Open issues

0

Weekly downloads

35

Last commit

Sep 23, 2026 (1 month ago)

Last release

Aug 20, 2026 (2 months ago)

Last package publish

Aug 20, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.nick-choudhary/linkedin-sales-nav-mcp

Version

1.2.0

Auth

No auth

Packages

pypi linkedin-sales-nav-mcp

License

MIT

Repository

github.com/nick-choudhary/linkedin-sales-nav-mcp

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql