Skip to main content
Glama

Server Details

Flux (fluxgraph.app) is a hosted LinkedIn MCP server for post analytics and research on any public profile or company page. Ask which days, formats, and lengths beat an account's own baseline, with the sample size behind each finding. A free preview covers up to 50 recent posts, and usage limits apply. You share no LinkedIn login or cookie. Flux reads public data through a third-party data provider, is read-only on LinkedIn, and is not affiliated with LinkedIn.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A3.5/5.0

Scored across 72 tools

Disambiguation3/5

Descriptions do a good job separating paid LinkedIn pulls from free local-library reads, previews, and graph queries, but the set still contains many near-neighbors: get_posts vs search_posts vs find_similar_posts, list_profiles vs list_streams, get_post_set_engagers vs linkedin_post_reactions/comments, and several engagement/outreach analytics tools. An agent can disambiguate with careful reading, but the boundaries are not obvious from names alone.

Naming Consistency4/5

Almost every tool uses snake_case with a predictable action/resource shape, and domain prefixes like linkedin_, preview_, get_, list_, and resolve_ are applied reasonably consistently. There are minor convention shifts (linkedin_company_info vs resolve_company, preview_profile vs get_profile_summary), but nothing chaotic.

Tool Count1/5

72 tools is an extreme surface for a single MCP server, far beyond a well-scoped set. Even for a broad LinkedIn intelligence platform, the count creates discovery and selection burden and strongly suggests many operations should be consolidated or split into separate servers.

Completeness3/5

Coverage is broad across profiles, streams, collections, segments, campaigns, engagers, credits, and graph traversal, so core workflows are mostly supported. However, obvious lifecycle gaps remain: no list_campaigns/get_campaign, no delete_collection or delete_segment, and limited update operations for several entities, which will force agents into dead ends or workarounds.

Publisher details

Operator
Elegant Atomics
Vendor relationship
Independent
Privacy policy
Not provided
Trust center
Not available
Restrictions
Two preview tools offer a free preview of up to 50 recent posts, with usage limits. Other tools need a sign-in or API key, and most need a paid plan.

Available Tools

72 tools
add_campaign_accountsAdd Campaign AccountsA
Idempotent
Inspect

[Act · writes] 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. Accounts already in the campaign (same linkedin_company_id, or same case-insensitive trimmed company_name) and repeats within the same call are not re-added; they are returned under skipped. Free — costs 0 credits.

Inputs: accounts (required), campaign_id (required).

add_to_collectionAdd Posts to CollectionA
Idempotent
Inspect

[Act · writes] 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.

Inputs: post_ids (required), collection_id (required).

add_to_segmentAdd People to Audience SegmentA
Idempotent
Inspect

[Act · writes] Add one or more people (by person_id) to a manual audience segment. Existing members are silently ignored. Smart segments are rejected: their membership is computed from config by resolve_segment. Unknown person_ids are rejected as a whole (nothing is added). Free — costs 0 credits.

Inputs: person_ids (required), segment_id (required).

claim_previewClaim a previewed profileA
DestructiveIdempotent
Inspect

[Act · writes · irreversible] 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.

Inputs: preview_id (required).

create_campaignCreate CampaignBInspect

[Act · writes] 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.

Inputs: name (required), description.

create_collectionCreate Post CollectionAInspect

[Act · writes] 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.

Inputs: name (required), type (required), config, description.

create_segmentCreate Audience SegmentAInspect

[Act · writes] 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','Chief']}) 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'). Smart segments only match people connected to you: people who engaged with posts you can see in Flux (your own profile, tracked/monitored profiles, and posts you collected) and people in your campaigns' constellations. Smart segment membership is computed, so add_to_segment / remove_from_segment do not apply to it. Free — costs 0 credits.

Inputs: name, type, config, template, +2 more.

create_streamCreate StreamAInspect

[Act · writes · schedules paid runs] 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.

Inputs: name (required), type (required), params, schedule, +3 more.

delete_streamDelete StreamA
DestructiveIdempotent
Inspect

[Act · writes · destructive] 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.

Inputs: stream_id (required).

enrich_peopleEnrich People (job history)AInspect

[Acquire · 3 credits/person enriched] Look up full LinkedIn profiles for up to 100 people and store their current title, company, headline and job history (every position). Job history is what get_outreach_path (coworker / alumni paths) and get_alumni_engagers search, and engagers collected from reactions/comments have none until enriched — when those tools report missing coverage they return a _meta.next_step with the exact person_ids to pass here. Pass person_ids (people.id from any engager / path tool) and/or linkedin_urls. Costs 3 credits per person successfully enriched. People you already have (connected to you: they engaged with your posts, are in your campaigns or segments, or you pulled or enriched them) who were enriched in the last 90 days are skipped for free unless refresh=true; anyone else is looked up and charged normally; failed or not-found lookups are free. The balance must cover 3 × the people to be looked up (after skips and max_credits) before anything runs; you are charged only for successes.

Inputs: refresh, person_ids, max_credits, linkedin_urls.

find_similar_postsFind Similar PostsA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: text (required), limit, profile_id, collection_id.

get_alertsGet Stream AlertsA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: limit, unread_only.

get_alumni_engagersAlumni / Coworker Engagers for a CompanyA
Read-onlyIdempotent
Inspect

[Read · free] Given a company (company_url, LinkedIn's numeric linkedin_company_id as linkedin_company_info returns it, an exact company_name, or a companies.id UUID), 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. Matches need job history on file, and engagers collected from reactions/comments usually have none: coverage counts candidates (engagers whose headline or current company names the company) with and without job history, and when missing data may hide matches _meta.next_step names enrich_people with the exact person_ids to pass and its credit cost. The company must be saved in Flux: if it is not, the error's _meta.next_step names linkedin_company_info (1 credit) with the arguments that save it; a company_name that matches several saved companies returns candidates to pick from instead of guessing. Pure DB read — no LinkedIn pull, no credits charged.

Inputs: limit, relation, company_id, company_url, +2 more.

get_campaign_statsGet Campaign StatsA
Read-onlyIdempotent
Inspect

[Read · free] 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. Outcomes logged for people who are not campaign entries are counted under an unattributed bucket in both by_pool and by_tier, so breakdowns always sum to the totals. Free — costs 0 credits.

Inputs: campaign_id (required).

get_company_engagement_overlapCompany Engagement OverlapA
Read-onlyIdempotent
Inspect

[Read · free] Given two companies, return the people who engaged (reacted or commented) with posts published by BOTH companies' own LinkedIn pages, counting only company-page posts and engagers already collected in your library. Use it to find people interested in two target accounts at once. It does NOT compare which employees of each company engage with you (for that, use get_post_engagers_by_company). It needs data collected first: each company's page posts (a company stream, or linkedin_company_posts) and their engagers (get_post_set_engagers on those posts, or linkedin_post_reactions / linkedin_post_comments); when a company has no page posts in your library the response says so. Identify each company by company_x_url, company_x_linkedin_id (LinkedIn's numeric id, as linkedin_company_info returns it), company_x_name (exact, case-insensitive; several matches return candidates instead of a guess) or company_x_id (companies.id UUID). A company not saved in Flux returns _meta.next_step naming linkedin_company_info (1 credit). Pure DB read — no LinkedIn pull, no credits charged.

Inputs: limit, company_a_id, company_b_id, company_a_url, +5 more.

get_cost_estimateGet Cost EstimateA
Read-onlyIdempotent
Inspect

[Meta · free] Preview what a tool call will cost before running it. Pass tool_name plus the params you intend to call it with: variable-cost tools (get_post_set_engagers, map_constellation, enrich_people, linkedin_profile_posts, linkedin_company_posts, linkedin_post_reactions, linkedin_post_comments, run_stream_now) are priced from those params with the same formula the tool's balance pre-check uses. Returns { tool_name, cost_max, cost_typical?, unit, explanation, cost (= cost_max), balance, sufficient, known_tool }. cost_max is the worst case the balance must cover; cost_typical is what such a call usually costs (you are charged only for what is actually fetched). Also accepts a stream type (external_profile, company, topic, person_interests, hiring_signals, ad_watch) to preview its per-page run price (stream_cost). Free.

Inputs: tool_name (required), params.

get_credit_balanceGet Credit BalanceB
Read-onlyIdempotent
Inspect

[Meta · free] Return the authenticated user's current credit balance, the current calendar month's credit period (UTC), that month's allocation if one was granted (null otherwise), credits used since the period started, and the most recent allocation. Free.

Inputs: no named parameters.

get_engagement_briefGet Engagement BriefA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: person_id, target_id, linkedin_url.

get_engagement_industry_breakdownEngagement Industry BreakdownA
Read-onlyIdempotent
Inspect

[Read · free] 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. Needs engagers synced first: if the post(s) have no recorded engagements, run get_post_set_engagers (1 credit per page, works on a collection or profile) as the usual first step; linkedin_post_reactions / linkedin_post_comments (1 credit per page of up to 100 people, so usually 1 credit each) pull a single post.

Inputs: depth, post_id, post_url, sample_companies_per_bucket.

get_engager_position_historyEngager Position HistoryA
Read-onlyIdempotent
Inspect

[Read · free] Return a person's full employment timeline from the position graph. Only for people connected to you: they engaged with posts you can see in Flux, are in one of your campaigns or segments, or you pulled them (an engagement pull, or their profile via linkedin_profile_info / linkedin_profile_posts). Anyone else returns not-found with a next_step to pull their profile via linkedin_profile_info. Sorted current-first, then most-recent past by started_at desc. Pure DB read — no LinkedIn pull, no credits charged.

Inputs: person_id, linkedin_url.

get_inbound_attributionGet Inbound AttributionA
Read-onlyIdempotent
Inspect

[Read · free] Which of your posts bring in DMs, leads and clients, next to which get engagement. Reads the inbound outcomes logged with log_outcome (inbound_dm | lead | client) for one of your tracked profiles over the last days (default 90). Returns totals, top_by_outcomes (posts credited with at least one outcome), top_by_engagement (your most-engaged posts in the window, with their outcome counts, so the two rankings can be compared), by_format, and the unattributed outcomes still waiting for a post (fix with log_outcome outcome_id + post_url). Engagement is not used to attribute: outcomes are matched by post_url, message text and timing. Free — costs 0 credits.

Inputs: profile_id (required), days.

get_outreach_pathOutreach Path to TargetA
Read-onlyIdempotent
Inspect

[Read · free] 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. Paths only exist where job history is on file, and engagers collected from reactions/comments usually have none: the response's coverage says how many candidates (the target, and engagers tied to the target's companies) have job history, and when missing data may hide paths _meta.next_step names enrich_people with the exact person_ids to pass and its credit cost. Pure DB read — no LinkedIn pull, no credits charged.

Inputs: limit, max_hops, target_person_id, target_linkedin_url.

get_outreach_queueGet Outreach QueueA
Read-onlyIdempotent
Inspect

[Read · free] Return a prioritized outreach queue. Provide exactly one of three scopes: • campaign_id — full Constellation queue, one row per person (their best entry's composite_score, pool, recommended_action), with targets[] listing every target they connect to ({target_id, entry_id, composite_score, pool, recommended_action, target_person: {person_id, full_name, current_title}}) and prior outreach_log entries. Pools: coworker = same company as the target (no relationship implied), engager = someone the target engages with, mutual = someone several targets engage with. Pass a target_person.person_id to get_outreach_path to check warm paths. • 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.

Inputs: pool, limit, segment_id, campaign_id, +1 more.

get_post_engagers_by_companyEngagers Grouped by CompanyA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: limit, post_id, post_url, industry_urn, +1 more.

get_posting_insightsGet Posting InsightsA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: profile_id (required), scope, date_to, date_from.

get_postsGet PostsA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: profile_id (required), page, scope, search, +7 more.

get_post_set_engagersGet Post-Set EngagersAInspect

[Acquire · 1 credit/page + 3/person enriched] Pull from LinkedIn (costs credits) and return the consolidated, deduped people who reacted to or commented on a SET of posts — one tracked profile's posts (profile_id), a post collection (collection_id), or an explicit list of up to 50 posts (post_ids and/or post_urls, e.g. the post_ids linkedin_post_search returns; a URL not yet in Flux is stubbed for free, no save_post needed). Fetches only posts not synced within freshness_days, walks up to max_pages_per_post pages (100 people/page) of reactions and of comments per post, includes comment replies, and enriches (title/company via a profile lookup) only never-seen people, up to max_enrich. Costs 1 credit per page fetched (a page is up to 100 people; a post with under 100 reactions and under 100 comments = 2 credits; the most a post can cost is 2 × max_pages_per_post) + 3 per person enriched; cached posts and cached pages are free. The balance must cover the worst case (posts × 2 × max_pages_per_post + max_enrich × 3) before anything runs (get_cost_estimate with these params returns the same number); you are charged only for pages actually fetched. When the balance is short, the insufficient_credits error spells out what the worst case assumed and lists suggestions (smaller max_pages_per_post / max_posts / max_enrich, each with its resulting max) that fit the balance. Per-post reactions_fetched / reactions_total / comments_total / truncated tell you when a post had more engagers than were fetched.

Inputs: force, post_ids, max_posts, post_urls, +5 more.

get_profile_summaryGet Profile SummaryA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: profile_id (required).

get_stream_feedGet Stream FeedA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: stream_id (required), limit.

get_target_warmth_briefTarget Warmth BriefA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: days_back, person_id, linkedin_url.

get_topic_insightsGet Topic InsightsA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: profile_id (required), n, scope, bigrams, +2 more.

get_usage_historyGet Usage HistoryB
Read-onlyIdempotent
Inspect

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

Inputs: limit, reason, date_to, date_from, +1 more.

linkedin_company_infoLinkedIn Company InfoAInspect

[Acquire · 1 credit] Fetch one LinkedIn company (numeric id, name, industry, size, location, website, description). Costs 1 credit per call. Use it to resolve a company to its numeric LinkedIn id, which linkedin_people_search (company) and linkedin_job_search (companyId) take for an exact company match. Look up by linkedin_url when you have it: a lookup by name returns the best match, which can be a different company with a similar name. The company is saved to companies.

Inputs: name, refresh, linkedin_url, universal_name.

linkedin_company_postsLinkedIn Company PostsAInspect

[Acquire · 5 credits/page] 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').

Inputs: linkedin_url (required), refresh, max_posts.

linkedin_post_commentsLinkedIn Post CommentsAInspect

[Acquire · 1 credit/page] Fetch the people who commented on a single LinkedIn post (and their comment text), including replies to comments. Costs 1 credit per page of up to 100 comments, walking up to max_pages pages (default 10), so at most max_pages credits; cached pages are free. The output's fetched / total_available / truncated fields say when the post had more comments than were fetched. Each comment and reply is persisted to post_engagements with the commenter and full comment text.

Inputs: post_url (required), refresh, max_pages.

linkedin_post_reactionsLinkedIn Post ReactionsAInspect

[Acquire · 1 credit/page] Fetch the people who reacted to a single LinkedIn post. Costs 1 credit per page of up to 100 reactions, walking up to max_pages pages (default 10), so at most max_pages credits; cached pages are free. The output's fetched / total_available / truncated fields say when the post had more reactions than were fetched. Engagers (with reaction kind) are persisted to the post_engagements graph so subsequent queries about who-engages-with-whom are SQL, not API calls.

Inputs: post_url (required), refresh, max_pages.

linkedin_post_searchLinkedIn Post SearchAInspect

[Acquire · 5 credits] Search LinkedIn posts by keyword. Costs 5 credits per call. Returns a single page of matching posts, each with a post_id (stored as a stub, no extra credit) you can pass to get_post_set_engagers to pull who engaged; _meta.next_step has that call ready.

Inputs: query (required), filters, refresh.

linkedin_profile_commentsLinkedIn Profile CommentsAInspect

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

Inputs: linkedin_url (required), refresh.

linkedin_profile_infoLinkedIn Profile InfoAInspect

[Acquire · 5 credits] 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.

Inputs: linkedin_url (required), refresh.

linkedin_profile_postsLinkedIn Profile PostsAInspect

[Acquire · 5 credits/page] 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.

Inputs: linkedin_url (required), refresh, max_posts.

linkedin_profile_reactionsLinkedIn Profile ReactionsAInspect

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

Inputs: linkedin_url (required), refresh.

list_collectionsList Post CollectionsA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: type.

list_profilesList ProfilesA
Read-onlyIdempotent
Inspect

[Read · free] List all tracked LinkedIn profiles for the authenticated user. Returns profile IDs needed by other tools.

Inputs: no named parameters.

list_segmentsList Audience SegmentsA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: type.

list_segment_templatesList Segment TemplatesA
Read-onlyIdempotent
Inspect

[Meta · free] List available smart-segment templates. Pass a template id to create_segment to pre-fill its config predicate without crafting one from scratch. Each template's description states exactly what its config matches; like every smart segment, it only matches people connected to you (engagers on your visible posts and people in your campaigns). Free — costs 0 credits.

Inputs: no named parameters.

list_streamsList StreamsA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: type, include_inactive.

log_outcomeLog OutcomeAInspect

[Act · writes] Record an outcome by hand. Two kinds. • Outbound (campaign outreach): action sent_request | accepted | replied | no_response with campaign_id and exactly one of person_id or linkedin_url (any profile URL form). The person must be connected to you (in one of your campaigns or segments, engaged with posts you can see in Flux, or pulled by you); anyone else returns not-found with a next_step to pull their profile via linkedin_profile_info. A person outside this campaign's mapped constellation is still logged (with a warning) and get_campaign_stats counts it under unattributed. • Inbound (results your own posting brought in): action inbound_dm | lead | client with profile_id (your tracked profile from list_profiles, whose posts it counts against). No campaign. When the user pastes a LinkedIn DM conversation, pass the whole paste as message_text and set occurred_at to the date of its first message (ISO 8601; omit only if the paste has no date). The sender's linkedin_url is optional and never triggers a paid lookup. Flux matches the outcome to the post that most likely prompted it: post_url if given, else for a lead or client the post already credited for this person's earlier inbound outcome, else the conversation's opening text and timing against your posts from the 30 days before. The result says the method (explicit | inherited | matched | recency | none) and lists up to three candidate posts. When nothing was matched and candidates exist, show them to the user and ask which post it was; then call again with outcome_id and that post_url to correct it. get_inbound_attribution reports which posts bring in DMs, leads and clients. Free — costs 0 credits.

Inputs: action (required), note, post_url, person_id, +6 more.

map_constellationMap ConstellationAInspect

[Acquire · 1 + 3×targets 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. The response lists the selected targets (target_id, person_id, full_name, current_title, linkedin_url) and _meta.next_step(s): get_outreach_queue for the scored queue, then get_outreach_path (free) to check warm paths to the top targets. Pools: coworker = other senior people at the same account from the lead search (no relationship with you is implied); engager = someone a target engages with; mutual = someone several targets engage with. Costs at most 1 + 3 × max_targets credits (7 at max_targets=2, 16 at the default 5, 61 at 20): the lead search is a bundled 1 credit, a deliberate discount on linkedin_people_search's 5 credits per page; the balance must cover that worst case, and only what is actually spent is charged and reported in the response.

Inputs: campaign_account_id (required), max_targets, title_keywords.

pause_streamPause StreamA
Idempotent
Inspect

[Act · writes] 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.

Inputs: stream_id (required).

preview_posting_insightsPreview posting insightsA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: preview_id (required).

preview_profilePreview a LinkedIn profileA
Idempotent
Inspect

[Acquire · free] 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.

Inputs: linkedin_url (required).

preview_search_postsSearch previewed postsA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: query (required), preview_id (required).

remove_from_collectionRemove Posts from CollectionA
DestructiveIdempotent
Inspect

[Act · writes · destructive] Remove one or more posts (by post_id) from a collection. Missing members are silently ignored. Free — costs 0 credits.

Inputs: post_ids (required), collection_id (required).

remove_from_segmentRemove People from Audience SegmentA
DestructiveIdempotent
Inspect

[Act · writes · destructive] Remove one or more people (by person_id) from a manual audience segment. Missing members are silently ignored. Smart segments are rejected: their membership is computed from config by resolve_segment. Free — costs 0 credits.

Inputs: person_ids (required), segment_id (required).

resolve_collectionResolve Post CollectionA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: collection_id (required), limit.

resolve_companyResolve CompanyA
Read-onlyIdempotent
Inspect

[Read · free] Look up a company saved in Flux by exactly one of name (case-insensitive exact match), linkedin_url, linkedin_company_id (LinkedIn's numeric id) or company_id, free. Returns company_id, linkedin_company_id, name, linkedin_url, page_type and coverage for you: connected_people_current (people connected to you, meaning they engaged with posts you can see, are in your campaigns or segments, or you pulled or enriched them, who hold a current position there) and engagers_current (those of them who engaged with your posts, with their engagement total). A name shared by several saved companies returns candidates to pick from. A company that is not saved returns _meta.next_step = linkedin_company_info (1 credit), which saves it. Generic placeholders (Self-employed, Freelance, Stealth...) are refused. Pure DB read, no LinkedIn pull, 0 credits.

Inputs: name, company_id, linkedin_url, linkedin_company_id.

resolve_peopleResolve PeopleA
Read-onlyIdempotent
Inspect

[Read · free] Resolve up to 200 LinkedIn profile URLs and/or person_ids to people in your Flux graph, free. Each result has person_id, the stored LinkedIn URL, matched_via (exact / canonical / member_id / public_identifier / none), name, current title and company, and coverage: has_positions (job history on file), enriched_at, engaged_with_you (engagements on your posts), in_campaigns (how many of your campaigns include them) and connected_via (engaged / campaign / segment / pulled). Only people connected to you resolve: someone who engaged with posts you can see, is in your campaigns or segments, or whom you pulled or enriched. Anyone else comes back as matched_via "none", the same as an unknown URL. _meta.next_step is the enrich_people call (with its credit cost) that saves the unmatched URLs and fills job history for matched people who lack it. Use it to triage a list of URLs before spending credits. Pure DB read, no LinkedIn pull, 0 credits.

Inputs: person_ids, linkedin_urls.

resolve_segmentResolve Audience SegmentA
Read-onlyIdempotent
Inspect

[Read · free] 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 (title_contains / company_contains) and returns matches ordered by engagement with your posts. Smart segments only match people connected to you: people who engaged with posts you can see in Flux (your own profile, tracked/monitored profiles, and posts you collected) and people in your campaigns' constellations. Free — costs 0 credits.

Inputs: segment_id (required), limit.

resume_streamResume StreamA
Idempotent
Inspect

[Act · writes] 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.

Inputs: stream_id (required).

run_stream_nowRun Stream NowAInspect

[Acquire · stream price/page] 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.

Inputs: stream_id (required), resume, max_pages, history_days.

save_postSave LinkedIn PostAInspect

[Acquire · 1 credit · writes] 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.

Inputs: url (required), collection_id.

score_connectionsScore ConnectionsA
Idempotent
Inspect

[Act · writes] 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.

Inputs: campaign_id (required).

score_draftScore DraftA
Read-onlyIdempotent
Inspect

[Read · free] 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.

Inputs: hour (required), text (required), day_of_week (required), format, +2 more.

search_postsSearch PostsA
Read-onlyIdempotent
Inspect

[Read · free] 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).

Inputs: query (required), profile_id (required), mode, limit, +1 more.

suggest_anglesSuggest AnglesAInspect

[Read · 5 credits] 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.

Inputs: topic (required), profile_id, collection_id.

traverse_graphExecute a SELECT against the Engagement GraphA
Read-onlyIdempotent
Inspect

[Read · free] Executes a TS-validated SELECT-only SQL query against the engagement graph and returns rows. Needs the schema and the caller_user_ids / caller_tracked_lp_ids that traverse_graph_help returns (it also has 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.

Inputs: sql (required).

traverse_graph_helpEngagement Graph Schema + Examples (for traverse_graph)A
Read-onlyIdempotent
Inspect

[Meta · free] 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.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
      16
      11 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources