"How to find people on Facebook" matching MCP tools:

• ads_get_adA

  Manifold MCPA

  One ad from a platform's public library, with its creative text, where it sends people, and who it was aimed at and reached. Use when: reading the offer and the call to action behind an ad you found in a list. Not for: a set of ads, use ads_search_ads or ads_get_advertiser_ads. What is said in an ad video, use the platform's transcript tool. Returns: Record. advertiser, headline, body, format, first_shown, last_shown, active, versions (near-identical copies Meta groups, a sign the advertiser scaled it), impressions, spend, countries, placements, targeting[], cta, destination_url, media_url, plus variations[] (carousel cards on facebook, text variants on google), reach, reach_by_country[], reach_by_age_gender[] and payers[] (payer, beneficiary). Impressions and spend are the ranges the library publishes, so they are text. Reach, its age split and payers come from Meta's EU and UK disclosure, so only facebook ads that ran there have them. On google, first_shown falls back to the earliest region's date and is null when the library dates neither; the ads_get_advertiser_ads row for the same ad carries it. Cost: 1 credit. Cached 7 days. Example: {"platform": "facebook", "id": "1185617869915074"}

  ConnectorAPI key

• people-search-tasksA

  DesearchB

  Your People Search tasks, newest first, with status, counts, cost, why each ended search stopped (completion_reason, coverage_limited), and the metadata labels set on people-search. Free; it lists your own tasks, not the people they found (read those with people-search-status or people-profiles). Use it to find a task_id (filter by metadata to find the searches of one campaign), or to see which searches are still queued, running, or paused: a new search is refused while too many are active.

  ConnectorNo auth

• facebook_get_commentsA

  Manifold MCPA

  The comments on one Facebook post. Use when: reading what people replied to a page or a group post. Not for: the post itself, use facebook_get_post. Comments across many posts, which Facebook does not offer. Returns: List. rows[]: one comment each: author, created_at, text (cut at 2000 characters), likes, replies, and parent_id and depth for a reply. Cost: 1 credit per page. Cached 6 hours. Example: {"url": "https://www.facebook.com/reel/1535656380759655"}

  ConnectorAPI key

• get_facebook_postsA

  Georgia Prisoners' Speak Public DataA

  What people on Facebook are saying about Georgia's prisons: public posts in the Ga. Prisons Exposed group and comments on GPS's own Facebook posts that GPS kept (families, formerly incarcerated people, former officers, advocates), newest first, each with its author, date, link and label: 'first-hand or inside account' (something specific that happened, seen or lived by the author or told by someone inside), 'opinion', 'idea for change', or 'news retold'. Filters: q (words), facility (a prison name, e.g. "Telfair"), days (default 30, max 365), label (account | opinion | idea | news), limit (default 10, max 60). `counts` gives items and people per label for the whole match. These are the authors' own views and accounts, never GPS findings: attribute and link every quote. Names of people in custody and GDC numbers are removed before the data leaves GPS.

  ConnectorNo auth

• facebook_cityEventsA

  TrueScrapeB

  Get the events of a city. Public events Facebook is suggesting for a city, from its Events Explore feed (e.g. https://www.facebook.com/events/explore/saint-petersburg-florida/111326725552547). `time` narrows the window to today, this week, or next week; without it Facebook returns whatever it has queued as upcoming, in whatever order it ranks them. Only the first, server-rendered page: host and description are not exposed on this listing (only on /v1/facebook/event). `pagination.hasMore` says whether Facebook has more; this endpoint returns no cursor to fetch them. Costs 1 credit.

  ConnectorNo auth

• facebook_postCommentsA

  TrueScrapeB

  Comments on a post. Top-level comments on a public Facebook post, with author, reaction count and reply count, in Facebook's "Most relevant" order. The first page is the head of the thread Facebook renders into the post, usually two comments; pass `pagination.cursor` back for the next ten. The post's full comment total is on /v1/facebook/post. Use /v1/facebook/comment-replies for the replies under one comment. `likeCount` is only as precise as Facebook publishes it: comment reactions ship in abbreviated form ("2.4K") with no exact figure anywhere in the payload, so counts above about a thousand are rounded at source. Costs 1 credit.

  ConnectorNo auth

• post_apollo_mixed_people_api_searchA

  AIsa Go-To-MarketC

  Use the People API Search endpoint to find net new people in the Apollo database. Several filters are available to help narrow your search. This endpoint is optimized for API usage and does not consume credits. This endpoint is primarily designed for prospecting net new people. This endpoint does not return email addresses or phone numbers. Use the People Enrichment or Bulk People Enrichment endpoints to enrich data. This endpoint requires a master API key. Refer to Create API Keys to learn how to create a master API key. To protect Apollo's performance for all users, this endpoint has a display limit of 50,000 records (100 records per page, up to 500 pages). Add more filters to narrow your search results as much as possible. This limitation does not restrict your access to Apollo's database; you just need to access the data in batches. <!-- aisa-pricing:start --> Published reference price: $0.012 USD per successful request. Account-specific pricing and final settlement may differ. <!-- aisa-pricing:end -->

  ConnectorOAuth

• messaging_list_chatsA

  NilyoC

  List personal chats for WhatsApp, Instagram, Facebook or Telegram. For Facebook Pages use facebook_list_inboxes and facebook_list_inbox_chats; never fall back to the personal inbox. Chats are most recently active first; use it to find a chat_id. LinkedIn requires inbox-specific listing. V2 filters: type, before/after (on the chat's last activity), archived and unread; WhatsApp pages by offset, other providers by cursor. For 'messages received between X and Y' call messaging_list_recent_messages, which also reads the messages.

  ConnectorOAuth

• facebook_searchA

  SocialAPIsA

  Search Facebook by keyword: pages, people, posts, videos and locations. Actions: - action=pages: Find Facebook pages by keyword (brand, business or topic name), optionally near a location. Returns page names, URLs, categories and follower counts, 3 per call, plus an end_cursor. Use it when you don't have the page URL; then call facebook_page (action=details) with a result's URL. For locations, get a location_uid from action=locations. Pricing: 1 credit per call. Inputs: query (required), location_uid (optional), end_cursor (optional). - action=people: Find public Facebook profiles by name or keyword, optionally near a location (location_uid from action=locations). Returns names, profile URLs and pictures, plus work, education and location where public, and an end_cursor. Pricing: 1 credit per call. Inputs: query (required), location_uid (optional), end_cursor (optional). - action=posts: Search public Facebook posts by keyword, optionally filtered by location (location_uid from action=locations) and date range. Returns posts with text, author and engagement, plus an end_cursor. To list one page's posts, use facebook_page (action=posts) instead. Pricing: 1 credit per call. Inputs: query (required), location_uid (optional), start_time (optional), end_time (optional), recent_posts (optional), end_cursor (optional). - action=videos: Search public Facebook videos by keyword, optionally most recent first or live videos only. Returns video titles, URLs and view counts, plus an end_cursor. Pricing: 1 credit per call. Inputs: query (required), most_recent (optional), videos_live (optional), fields (optional), end_cursor (optional). - action=locations: Look up Facebook places by name (city, region, venue) and get their location_uid. The location_uid is only used to filter action=pages, action=people and action=posts; it is not a Marketplace location (use facebook_marketplace (action=city_coordinates) for that). Pricing: 1 credit per call. Inputs: query (required).

  ConnectorNo auth

• list_conversationsA

  PostPlanifyA

  List private direct message conversations from Instagram and Facebook Messenger for a workspace, newest first. Each conversation includes the customer, the last message preview, whether it needs a reply, who it is assigned to, and replyWindow (canReply, expiresAt): Instagram and Facebook only allow replies within 24 hours of the customer's last message. These are private messages: only summarize or quote them for the user who asked. Use needsReply to find conversations waiting on an answer, then list_conversation_messages to read one.

  ConnectorOAuth

• create_comment_automationA

  oriiionB

  Create a comment→DM automation. Once created it is LIVE and will DM real people automatically, so show the user the exact dmMessage, keywords and which account it runs on, and get their approval first. Use an accountId from list_comment_automations. Instagram and Facebook only.

  ConnectorNo auth

• find_people_behind_reposA

  AyHireA

  Find the developers who build open-source projects: searches GitHub for repositories (most stars first) matching a query, topic or language, then lists the people who contributed most to them, ranked by how many of those repos they build and how much they contributed. Bots and AI coding agents are excluded. Pass repo ('owner/name') for the people behind one exact project, or org ('vercel') for the people behind an organization's repos (each person has public_member; false only means not shown as a member). Mining several seed repos one after another is often the best way to find strong people. location keeps people whose GitHub location is in one of the places, plus people who list no location, marked location_match: 'unknown' (unknown is never a mismatch; location_unknown: 'exclude' leaves them out). page reads the next set of repos. With role_id, people the role has already seen are left out (unless include_seen) and the search goes in the role's history. Free (GitHub only).

  ConnectorAPI key

• search_jobsA

  nü people Job ServerA

  Searches currently open jobs on the nü people website. Use this tool when the user wants to find matching jobs by keyword, role, skill, location, or contract type. Returns a list of public job summaries.

  ConnectorNo auth

• compare_peopleA

  MentionFoxA

  Two to five people set out side by side, line by line — how they work, how they come across, where their careers have gone, how deep their experience runs, how visible they are, who they are connected to. You get a table you can read down a column for one person or across a row to see how they differ. Tell it what the comparison is for and the framing follows: people to pitch, partners to weigh, guests or speakers to prepare for. Not a consumer report: never for deciding whether to hire, admit, lend to or house anyone. It compares people you have already looked up; if fewer than two of them are on file it says so and charges nothing. If a name matches more than one person you get the candidates for that name, also free. Costs 15 credits per comparison, whatever the number of people. Plans and credits: https://mentionfox.com/pricing

  ConnectorNo auth

• job_demandA

  Job SpotterC

  What job seekers are searching for, by role and place. For "how many people are looking for care jobs in Leeds?" or "what are people searching for in Bristol?". Anonymous weekly counts of searches on Job Spotter by role words and place over the last 8 weeks, with the listings people found per search. Leave out what to get the most searched roles in a place (with a rising or falling trend), or where to get the places a role is searched most. For a role, it also gives the easiest places to find openings: where each search finds the most listings. A group is shown only when it holds 10 or more searches.

  ConnectorNo auth

• update_mediaA

  AutomateSocialsA

  Sets or clears the alt text of a picture in this project: what it shows, for people who cannot see it. Pass null or "" to clear it. At most 1000 characters. It goes out with the picture to LinkedIn, X, Facebook and Instagram whenever a post does not give its own.

  ConnectorNo auth

• update_mediaA

  AutomateSocialsA

  Sets or clears the alt text of a picture in this project: what it shows, for people who cannot see it. Pass null or "" to clear it. At most 1000 characters. It goes out with the picture to LinkedIn, X, Facebook and Instagram whenever a post does not give its own.

  ConnectorNo auth

• list_facebook_pagesA

  ShortSyncA

  Lists the Facebook Pages the user can post to with a Facebook login they already made in ShortSync (in this or any of their workspaces), and which Page this workspace posts as now. Use it to connect Facebook to another workspace or switch Pages without a new sign-in: pass a page id to select_facebook_page. When there is no Facebook login yet, the result includes a connect_url for the user to sign in to Facebook first.

  ConnectorOAuth

• list_tagsA

  PostPenA

  Lists the people and organisations in the user’s PostPen tag list. Each has name, write_as (how to write it in save_draft content or network_text, e.g. "@[PWD Delhi]"), and its handle on x, instagram and threads and its LinkedIn company (company and link), null where it has none. Write a tag as write_as in the text; PostPen turns it into @handle on X, Instagram and Threads, tags the LinkedIn company on LinkedIn, and uses the plain name on Facebook, YouTube and any network without a handle for it. When the user names someone to tag, look them up here first.

  ConnectorOAuth

• people-search-exportA

  DesearchB

  The people your own People Searches found, as CSV or JSON Lines text: one search (task_id), or everyone found on one platform (platform, with the same q, sort, and filters as people-profiles). Free: it reads people your earlier searches found and runs no new search. The reply is a note with the row count, then the file text cut at a row boundary to max_rows rows and 50,000 characters; the note says how many rows were cut and where to get the whole file. CSV keeps its header row. The data came from public profiles and posts, with only the contacts each person lists publicly.

  ConnectorNo auth

• meta_build_campaignA

  Agency AutopilotB

  Build a whole Meta (Facebook and Instagram) campaign in one step: the campaign, one ad set (goal, daily budget, locations, ages) and 1-5 ads (text, headline, button, link, with one image, a 2-10 image carousel or a video), all running from the client's Facebook Page. Everything is created inside a PAUSED campaign, so nothing spends until it is turned on (meta_set_campaign_status). Call WITHOUT confirm first: the preview downloads and checks every image and has Meta check the campaign. Then confirm: true creates it; if any later step fails, everything made so far is deleted, so no half-built campaign is left. Goals: website_leads (needs pixel_id), landing_page_views, link_clicks, calls (needs a CALL_NOW button with phone_number), reach. Instant Forms (the form inside Facebook) are not available yet: send people to the client's site.

  ConnectorOAuth