Flux LinkedIn MCP

List all tracked LinkedIn profiles for the authenticated user. Returns profile IDs needed by other tools.

Takes no parameters.

Analyze a public LinkedIn profile or company page without a Flux account: pulls the latest ~50 posts (once per profile) and returns a teaser: post count, average engagement, the format that beats the baseline, the top post and the recent trend, plus a preview_id. The full breakdown (best day and hour, top and bottom posts with reasons, trends by format) and keyword search need a free Flux account: call preview_posting_insights or preview_search_posts with the preview_id, which asks the person to sign in where the client supports it, or give the person the continue_url if that call fails. Call claim_preview after sign-in only when the person says the profile is theirs.

Full breakdown for a previewed profile (from preview_profile): best day, hour, format and length, the top and bottom 5 posts with measured reasons, and engagement trend by format. Requires a free Flux account; calling it asks the person to sign in where the client supports it, otherwise use continue_url from preview_profile.

Keyword search over the latest 50 posts of a previewed profile (from preview_profile). Case-insensitive substring match; returns matching posts ordered by engagement. Requires a free Flux account; calling it asks the person to sign in where the client supports it, otherwise use continue_url from preview_profile.

Make a profile from preview_profile your own Flux dashboard. Call this only when the person says the profile is theirs: the person cannot undo a claim. Requires sign-in; creates a free dashboard showing the latest 50 posts, one per account. Refuses if the account already has a dashboard; the breakdown tools still work then.

List a tracked profile's persisted posts with full metrics and text — query against the local post library, no LinkedIn pull, free. Use this when the caller already has a profile_id and wants to read its posts. Filter by date range, post type, minimum engagement, or text. Pass `scope` (a post_collections.id) to restrict to a specific collection (e.g. an external profile, topic stream, or hand-curated set). Paginated. For keyword/semantic search across posts, use `search_posts`. For fresh LinkedIn pulls, use `linkedin_profile_posts`.

Get KPI summary for a tracked profile: total posts, average engagement (broken down by likes/comments/shares/conversation rate), posts per week, engagement trend, top format, and posting goal status.

Get optimal posting patterns for a profile: best day of week, best hour, format performance breakdown, and character length sweet spot. Includes full metric breakdown (likes, comments, shares, conversation rate) for every bucket. All metrics relative to the user's own baseline. Pass `scope` (a post_collections.id) to recompute the patterns against a specific collection.

Surface the most-frequent topics in a profile's posts, with engagement context. Returns top N unigrams and (optionally) top N bigrams ranked by post count, each with avg_engagement, vs_baseline, and a sample_post_url. Mirrors the dashboard topics chart, server-side. Pass `scope` (a post_collections.id) to scope the analysis to a collection.

Get engagement time series for a profile with gap-filled buckets, rolling averages, and trend direction. Each bucket includes avg engagement, likes, comments, shares, and conversation rate. Useful for understanding whether engagement is growing or declining. Pass `scope` (a post_collections.id) to plot trends for a specific collection.

Keyword + semantic search over persisted posts in the local library — full-text + pgvector cosine, no LinkedIn pull, free. Use this when the caller has a query string and wants ranked persisted-post results. Pass `scope` (a post_collections.id) to limit to a specific collection. For fresh LinkedIn keyword pulls, use `linkedin_post_search` instead (5 credits).

Return the authenticated user's current credit balance, this period's monthly allocation, and credits used since the period started. Free.

Takes no parameters.

Return recent credit_ledger transactions for the authenticated user. Filter by tool name, reason, or date range. Paginated. Free.

Given an MCP tool name, return its credit cost so you can preview an action before running it. Also accepts a stream type (external_profile, company, topic, person_interests, hiring_signals, ad_watch) to preview the per-page cost create_stream / run_stream_now will charge. Returns { tool_name, cost, balance, sufficient, stream_cost? }. Tools not in the registry are assumed to cost 0. Free.

Create a new research stream (external profile, company, topic, person interests, hiring signals, or ad watch). Running the stream on its schedule costs credits (see get_cost_estimate for the per-type cost). own_profile streams are not created here — they come from subscription checkout.

List all research streams for the authenticated user (external profiles, companies, topics, person interests, hiring signals, ad watches, and own_profile). Pass `type` to filter. Replaces list_profiles for the streams-first world, but list_profiles continues to work for V1-compatible callers.

Return the most recent posts a stream has collected into the library, newest first by published_at. Use this to browse what a topic / external profile / person_interests / company stream has surfaced on its schedule.

Pause a stream so it stops running on its cron schedule. Existing posts remain in the library. Use resume_stream to re-enable it. own_profile streams are billing-managed and cannot be paused here.

Resume a paused stream. Sets active=true and queues it to run on the next cron tick by clearing next_run_at. own_profile streams are billing-managed and cannot be resumed here.

Delete a stream and its stream_runs. Posts collected by the stream stay in your library (stream_id is set to NULL via ON DELETE SET NULL) so historical data isn't lost. Auto-collection is deleted with the stream. own_profile streams cannot be deleted through this tool; the own profile is managed from Settings and billing.

Trigger an immediate run of an active stream, bypassing its schedule. The run is fire-and-forget — the response confirms the dispatch but post collection happens asynchronously. Credits are charged for pages actually walked, not pages requested: one page is taken upfront and the rest settled when the run finishes, so a run that stops early (or fails) costs less than max_pages implies. Paused streams must be resumed first. Use list_streams or get_stream_feed to see results once the run completes.

Fetch a LinkedIn person profile (headline, current role, work history, education, location). Costs 5 credits per call. Results are upserted into `people` (structured fields) and `linkedin_profiles` (so profile-brief renders) — same enrichment side-effect as the other linkedin_profile_* tools.

Fetch recent posts from a LinkedIn person profile. 5 credits per page of 50, up to 250 posts, charged only for pages actually fetched. Results are stored in the post library (source_type='external') and linked to a linkedin_profiles row so profile-brief can render research-only prospects.

Fetch recent posts from a LinkedIn company page. 5 credits per page of 50, up to 250 posts, charged only for pages actually fetched. Results are stored in the post library (source_type='external') and linked to a linkedin_profiles row (profile_type='company').

Search LinkedIn posts by keyword. Costs 5 credits per call. Returns a single page of matching posts.

Fetch the recent posts a LinkedIn person has reacted to. Useful for inferring interests. Costs 5 credits per call.

Fetch the recent posts a LinkedIn person has commented on. Useful for inferring interests and conversation partners. Costs 5 credits per call.

Search LinkedIn job postings. Useful for tracking hiring signals at target companies. Costs 5 credits per call.

Search the LinkedIn ad library. Useful for tracking competitor ad creative and messaging. Costs 10 credits per call.

Search LinkedIn people. Filter by company, title, location, or free-text keywords. Costs 5 credits per call. Returns a single page of matching profiles.

Search LinkedIn companies. Filter by keywords, industryId, or location. Costs 5 credits per call. Returns a single page of matching companies.

Fetch the people who reacted to a single LinkedIn post. Costs 5 credits per call. Engagers (with reaction kind) are persisted to the post_engagements graph so subsequent queries about who-engages-with-whom are SQL, not API calls.

Fetch the people who commented on a single LinkedIn post (and their comment text). Costs 5 credits per call. Each comment is persisted to post_engagements with the commenter and full comment text.

Find persisted posts whose embeddings are nearest to a free-text query — pgvector cosine over the local post library, no LinkedIn pull, free. Use when you have a *block of text* (a draft, a paragraph, a competitor's post) and want similar posts you've already collected. For keyword search prefer `search_posts`; for fresh LinkedIn keyword pulls use `linkedin_post_search`. Pass `profile_id` to scope to a tracked profile, `collection_id` to scope to a collection, or neither to search the entire library.

Predict how a draft post will perform against the user's historical data. Uses an OLS regression model with detrending, ridge regularization, and recency weighting — the same model used on the /score page. Returns a predicted engagement percentile, projected engagement range, factor breakdown, similar past posts, and improvement suggestions. Free. Pass `profile_id` to scope to a tracked profile, `collection_id` to scope to a collection, or neither to score against the user's full library.

Given a topic, suggest distinct content angles informed by what performs well in the user's scoped data. Pulls top-performing historical posts as context and calls OpenAI to generate 5 concrete angles. Costs 5 credits per call. Pass `profile_id` to scope to a tracked profile, `collection_id` to scope to a collection, or neither to use the user's full library.

List all audience segments for the authenticated user, with member counts. Audience segments are named groups of people (e.g. 'ICP — VPs of Marketing', 'Champions'). Free — costs 0 credits.

Create a new audience segment (named group of people) for the authenticated user. Set type='manual' for a hand-curated list (use add_to_segment to populate it), type='smart' with a `config` predicate (e.g. {title_contains:'VP'}) to define a dynamic segment resolved on-demand by resolve_segment, or pass `template` to pre-fill `config` from a built-in template (type defaults to 'smart'). Free — costs 0 credits.

Add one or more people (by person_id) to an audience segment. Existing members are silently ignored. Free — costs 0 credits.

Remove one or more people (by person_id) from an audience segment. Missing members are silently ignored. Free — costs 0 credits.

Resolve an audience segment into a concrete list of person_ids. For manual / auto_stream segments, returns stored members. For smart segments, evaluates the segment's `config` predicate against the people table and returns matches. Free — costs 0 credits.

List available smart-segment templates. Pass a template id to create_segment to pre-fill its `config` predicate without crafting one from scratch. Free — costs 0 credits.

Takes no parameters.

Return recent alerts for the authenticated user's streams. An alert is emitted whenever a scheduled stream run surfaces new items. Pass `unread_only=true` to skip alerts the user has already marked read. Free — costs 0 credits.

Create a new post collection for the authenticated user. Set type='manual' to hand-curate posts with add_to_collection, or type='smart' with a `config` predicate (e.g. {format:'video',min_likes:50}) to define a dynamic collection resolved on-demand by resolve_collection. Free — costs 0 credits.

Pin one or more posts (by post_id) into a collection you own — works on any collection type. On a 'manual' collection this is the only membership mechanism; on a 'smart' collection it adds the posts as extras alongside whatever the rule already matches (resolve_collection returns the union). Existing members are silently ignored. Free — costs 0 credits.

Remove one or more posts (by post_id) from a collection. Missing members are silently ignored. Free — costs 0 credits.

List all post collections for the authenticated user, with member counts. Includes manual collections, smart collections (predicate-based), and auto_stream collections (system-managed). Free — costs 0 credits.

Resolve a post collection into a concrete list of post_ids. For manual / auto_stream collections, returns stored members. For smart collections, evaluates the collection's `config` predicate against the user's posts and returns matches. Free — costs 0 credits.

Create a Constellation outreach campaign. A campaign groups target accounts, the people you care about at those accounts, and the warm connections you could approach to reach them. Free — costs 0 credits.

Add one or more target companies to a Constellation campaign. Each account is a company you want to reach; map_constellation is then run per-account. Free — costs 0 credits.

Map the professional graph around a target company. Finds senior decision-makers at the account, pulls each target's recent posts/reactions/comments to identify engagers, then scores every connection and produces a prioritized outreach queue. Credit cost scales with targets — bounded by `max_targets`. Max spend per call is ~175 credits; actual cost is reported in the response.

Re-score all constellation entries in a campaign and rewrite queue positions from highest to lowest composite score. Use after new engagers or targets are added. Free — costs 0 credits. Note: this tool requires a `campaign_id` because it writes back to the `constellation_entries` table. Segment- and url-list-scoped scoring is not yet supported — use `get_outreach_queue({segment_id})` or `get_outreach_queue({linkedin_urls})` for engagement-count ordering on those scopes; full composite scoring will land alongside the unified person-positions schema in a later phase.

Return a prioritized outreach queue. Provide *exactly one* of three scopes: • `campaign_id` — full Constellation queue with composite_score, pool, recommended_action, and prior outreach_log entries (the original campaign-scoped behavior). • `segment_id` — people in a saved audience segment, ranked by their engagement count against your tracked profiles' posts. No composite_score. • `linkedin_urls` — an ad-hoc list of LinkedIn URLs, same engagement-count ranking as segments. Free — costs 0 credits.

For one person, return their recent posts most relevant to what you post about — plus suggested talking points. Use before a warm comment or DM. Free — costs 0 credits. Identify the person via *exactly one* of: `target_id` (a Constellation target — original input), `person_id` (a row in `people`), or `linkedin_url` (any form). The non-campaign forms work even when no Constellation campaign exists.

Append an entry to the outreach log for a Constellation campaign. Use to record connection requests, acceptances, replies, or no-responses so get_campaign_stats can compute acceptance / reply rates over time. Free — costs 0 credits.

Summary stats for a Constellation campaign: target count, entry count, outreach volume, and acceptance / reply rates broken down by pool (coworker / engager / mutual) and composite-score tier. Free — costs 0 credits.

Save a LinkedIn post to your library by its URL. Resolves the post and stores it with source_type='saved'. Optionally pins the post into any collection you own (manual or smart — pinning into a smart collection adds it as an extra alongside the rule's matches). Costs 1 credit per call. Failed lookups don't charge.

Given a LinkedIn post URL or id, return the companies whose people engaged (reacted/commented), ranked by engager count. Joins through person_positions(is_current=true). Pure DB read — no LinkedIn pull, no credits charged. Engagers without a known current company are bucketed as `_unknown_company`. Optional industry_urn filter narrows to one industry.

Histogram of engagers' companies grouped by industry. Pivots on companies.industry_hierarchy (e.g. 'Tech > Software Development'). Depth=1 buckets by top-level, =2 by top+mid, =3 by full hierarchy. Engagers with no current company / no industry hierarchy bucket as `_unknown`. Pure DB read — no LinkedIn pull, no credits charged.

Given a company URL or id, return engagers (across your collected posts) who have a position at that company. Relation filter: 'coworker' = current employees, 'alumni' = any past or current position (most useful for page_type='SCHOOL' companies), 'any' = both. Pure DB read — no LinkedIn pull, no credits charged.

Return a person's full employment timeline from the position graph. Person must have engaged on at least one of your collected posts (engagement gate). Sorted current-first, then most-recent past by started_at desc. Pure DB read — no LinkedIn pull, no credits charged.

For a target person, summarize all engagement evidence between them and your collected posts: posts they reacted to, posts they commented on, frequency, recency, reaction kinds, comment text snippets. Computes a v0 warmth score from engagement count, comment signal, and recency. Pure DB read — no LinkedIn pull, no credits charged.

Returns the schema, FK edges, and 5 canonical SQL examples needed to write your own SELECT against the engagement graph via traverse_graph. Also returns YOUR resolvable identities (caller_user_ids, caller_tracked_lp_ids) — substitute these into example SQL when you write your query. Pure DB read — 0 credits. Free.

Takes no parameters.

Executes a TS-validated SELECT-only SQL query against the engagement graph and returns rows. CALL traverse_graph_help FIRST to get schema + caller_user_ids + canonical examples. Required: SQL must start with SELECT or WITH, contain no DML/DDL keywords, and reference one of your caller_user_ids or caller_tracked_lp_ids verbatim. Cap: 1000 rows, 5s statement timeout. Pure DB read — 0 credits.

Given two companies, return engagers across your collected posts who engaged with BOTH companies' posts. Cross-account intelligence — finds people interested in multiple targets simultaneously. Pure DB read — no LinkedIn pull, no credits charged.

Given a target person, find the shortest warm-intro path through your engager network. Walks coworker (shared current company) + alumni (shared past company / school) edges. Up to 3 hops. Pure DB read — no LinkedIn pull, no credits charged.

Return the consolidated, deduped people who reacted to or commented on a SET of posts — one tracked profile's posts (profile_id) or a post collection (collection_id). Fetches only posts not synced within freshness_days, and enriches (title/company via a profile lookup) only never-seen people, up to max_enrich. Costs 2 credits per post synced + 3 per person enriched; cached posts are free.