Skip to main content
Glama
458,356 tools. Updated 2026-08-17 03:15

"Find people on LinkedIn by name" matching MCP tools:

  • Find a person's professional profile by name (+company) via Coresignal — returns title, current company, location, LinkedIn URL, work experience and education. LinkedIn-adjacent people data. Example: coresignal_employee({ name: "Patrick Collison", company: "Stripe", _apiKey: "your-key" })
    Connector
  • Search Wikidata for items or properties by text query. Returns QIDs or PIDs with labels, descriptions, and match metadata indicating whether the hit was on a label or alias. Use type="item" for real-world concepts (people, places, works) and type="property" to find predicate P-IDs. The API returns no total count — pagination is offset-based with no result ceiling indicator.
    Connector
  • LinkedIn ad performance — impressions, clicks, cost, website conversions, leads and social actions — pivoted by CAMPAIGN (default), CAMPAIGN_GROUP, CREATIVE, ACCOUNT, CONVERSION, PLACEMENT_NAME, IMPRESSION_DEVICE_TYPE, SERVING_LOCATION… or by AUDIENCE DEMOGRAPHICS: MEMBER_COMPANY_SIZE, MEMBER_INDUSTRY, MEMBER_SENIORITY, MEMBER_JOB_TITLE, MEMBER_JOB_FUNCTION, MEMBER_COUNTRY_V2, MEMBER_REGION_V2, MEMBER_COMPANY. The MEMBER_* pivots are what LinkedIn is uniquely good at — job title, seniority and company size are targeting dimensions no other platform reports — and LinkedIn allows exactly ONE pivot per report, so ask for them one at a time and join the answers yourself. An unknown pivot or granularity is refused BY NAME rather than forwarded. On a demographic pivot LinkedIn returns only the top 100 values, DROPS any value under 3 events (so the rows will not sum to the campaign total) and lags 12–24 hours behind the performance numbers — the note says so, every time. Window via since/until (YYYY-MM-DD). ZERO rows genuinely means no delivery in that window; say exactly that and never present zeros as measured performance. A LinkedIn TEST ad account NEVER returns analytics, and the note says so when that is what you are looking at. Read-only, free.
    Connector
  • Create a LinkedIn campaign inside an existing campaign group. Created DRAFT — it spends NOTHING until activated with set_linkedin_ads_status(confirm:true) — and a campaign on its own carries no creative, so it cannot serve an impression. Budget amounts are in the ad account’s currency; tell the user that LinkedIn may spend UP TO 150% of a daily budget on a high-opportunity day before they pick a number. Two LinkedIn behaviours to repeat rather than hide: on manual, target-cost or cost-cap bidding a unitCost of 0 means the campaign never delivers, and LinkedIn DEFERS some validation on DRAFT objects, so a clean create can still fail at activation — never promise it will run. TARGETING IS MANDATORY on LinkedIn — a campaign with no audience is refused outright — so pass locations (and optionally include/exclude facets like titles, industries, seniorities or staffCountRanges), or a raw targetingCriteria. Resolve every targeting value with search_linkedin_ads_targeting first: they are opaque URNs and MUST NOT be invented. LinkedIn’s own enums for type, objectiveType and costType are passed straight through, and LinkedIn’s refusal is surfaced verbatim if one is wrong. Read back before you are told it exists.
    Connector
  • List the LinkedIn COMPANY PAGES the connected account administers — id, name and the role held on each. ALWAYS call this before post_to_linkedin_page when there is more than one Page: publishing to the wrong company Page is a public mistake and Hermoso never chooses for the user. If it comes back empty, the account holds no Page admin role, or LinkedIn has not granted this app the organization scopes — say that plainly rather than guessing an id. Read-only, free.
    Connector
  • Build a retargeting audience on a connected Meta ad account. Three kinds: kind:"website" (people whose visited URL contains urlContains, seen by pixelId — pass the brand’s own domain for "all visitors"; retentionDays up to 180), kind:"engagement" (people who did `event` on the brand’s Facebook Page, or its Instagram business profile with source:"instagram"; retentionDays up to 730), or kind:"lookalike" (sourceAudienceId + country + ratio 0.01–0.20, lookalikeType "similarity" or "reach"). CREATING AN AUDIENCE SPENDS NOTHING — it is a definition; money only moves when an ad set targets it and that campaign is activated through set_meta_campaign_status(confirm:true). Meta needs roughly 30 minutes and ~1,000 people before a new audience can be targeted, so a fresh one reporting no size is normal. Customer-list uploads are deliberately NOT supported here (hashed personal data + Meta’s Custom Audience Terms) — send the user to Ads Manager for those.
    Connector

Matching MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    MCP server for the Mamba Labs People Finder & Email Verifier actor on Apify. Give it a company domain, name or LinkedIn URL and it returns the people at that company who match your role, seniority and department filters, each as a structured contact record with an optional verified business email.
    1
    0
    MIT
  • A
    license
    A
    quality
    D
    maintenance
    Enables searching and scraping of LinkedIn for structured data on people, companies, and job listings. It allows AI clients to retrieve detailed profiles, experience, and activity sections using browser automation.
    7
    174
    MIT

Matching MCP Connectors

  • Turn a LinkedIn campaign group, campaign or CREATIVE (the ad itself) on (ACTIVE) or off (PAUSED). Pass level:"campaign" + campaignId, level:"campaignGroup" + campaignGroupId, or level:"creative" + creativeId. All three tiers must be ACTIVE for an ad to serve — activating only the campaign leaves a DRAFT creative sitting there showing nothing. ACTIVATING STARTS REAL AD SPEND — you MUST first show the user the campaign and its budget, get an explicit yes, then call with status:"ACTIVE" and confirm:true. Pausing is always safe. The resulting status is READ BACK from LinkedIn along with its servingStatuses before you are told it took: LinkedIn defers validation on drafts, so activation is exactly where a hidden problem surfaces, and the note reports what LinkedIn actually says rather than what was requested.
    Connector
  • HOW MANY LINKEDIN MEMBERS a targeting spec reaches, before any budget is committed — the cheapest sanity check there is on a B2B audience, and it needs no ad account. Pass locations plus optional include:{titles, industries, seniorities, staffCountRanges, jobFunctions, skills, …}; search_linkedin_ads_targeting resolves any of those names to the URNs LinkedIn demands, free. THE CRITICAL THING TO SAY WHEN REPORTING: a returned total of 0 means the audience is UNDER 300 PEOPLE, not that it is empty — LinkedIn suppresses any count below 300 to protect member privacy, and 300 is also the minimum audience a campaign may run against, so a 0 means this targeting is too narrow to advertise to. The figure is a rounded approximation, so quote it as an estimate and never as a headcount. Read-only, 0 credits.
    Connector
  • Structured LinkedIn Ad Library search by company name, keyword, or companyId — use for a targeted B2B pull; use research_ads for open-ended research. Returns compact JSON {advertiser, headline, description, cta, link, media, dates, impressions} per ad — LinkedIn is the one library exposing real impression counts. Spends ScrapeCreators credits (~1).
    Connector
  • Search the web for any topic and get clean, ready-to-use content. Best for: Finding current information, news, facts, people, companies, or answering questions about any topic. Returns: Clean text content from top search results. Query tips: describe the ideal page, not keywords. "blog post comparing React and Vue performance" not "React vs Vue". Use category:people / category:company to search through Linkedin profiles / companies respectively. If highlights are insufficient, follow up with web_fetch_exa on the best URLs.
    Connector
  • Gets a contact from the Mac's Contacts app (Contacts.app) by name or ID. Pass `name` to look up directly by name (no need to search_contacts first — if several people match it returns a compact list to choose from), or `contact_id` for an exact lookup. For Microsoft 365 use m365_get_contact instead.
    Connector
  • Returns the current skill cluster data for public jobs on the nü people website. Use this tool when the user wants an overview of which skills or technologies are currently in demand.
    Connector
  • Get the profile of one person in crypto by id: name, description or bio, teams_count, positions held, and linked projects plus social and code accounts. Use for 'who is Vitalik Buterin', 'background on Charlie Lee', 'projects tied to this founder'. Find the personId first with search or resolveId using type 'people'; this tool needs the exact id, not a name. Read-only. Params: personId (required) is a canonical person id such as 'vitalik-buterin' or 'satoshi-nakamoto'; an unknown id returns not found. No API key required.
    Connector
  • Change a LinkedIn campaign’s daily and/or total budget. On a LIVE (ACTIVE) campaign this changes real spend immediately — and LinkedIn can spend up to 150% of a daily budget on a high-opportunity day — so show the user the new amount, get an explicit yes, then call with confirm:true. The currency must match the ad account’s. Read back after the change.
    Connector
  • Record something one person paid for the group. Split equally by default; pass split_between for a subset, or shares for an uneven split. One expense covers one set of people — a receipt whose items aren't all shared by everyone is several expenses, so call this once per group of items that the same people share, rather than splitting the total equally. Works on simple, accountless splits. Secure splits (created by a signed-in user) are read-only here and must be opened in a browser.
    Connector
  • Search XPay Hub for paid API services. Use this PROACTIVELY when the user asks you to: search the web, find emails, enrich contacts/companies, verify emails, find similar websites, extract web page content, get company news, search for people by title/company, get job postings, generate images, or any data lookup task. Returns matching servers with slugs, tool counts, and pricing. Use xpay_details next to see the full tool list for a server.
    Connector
  • Opens a real browser window on the Mac for the user to sign into a website themselves (you never handle their password). After they log in, the session is saved on this Mac and reused by web_navigate/web_read/web_screenshot — they won't need to log in again. Use a stable `session` name per site (e.g. 'linkedin'). NOTE: automating sites like Instagram/LinkedIn may violate their terms — the user accepts that risk.
    Connector
  • Find the work email for a person by name + company domain — give a person's full name and their company domain and get their verified business email (with job title and LinkedIn when available). B2B prospecting / outreach. Example: findymail_find_email({ name: "Patrick Collison", domain: "stripe.com", _apiKey: "your-findymail-key" })
    Connector
  • Create a LinkedIn post on behalf of a connected profile. By default the post is saved as a 'draft' in the LinkedIn Posts page so the user can review/edit it before publishing. Set auto_publish=true to publish immediately — that path still respects the user's MCP human-in-the-loop setting (when approval is required, the post stays as a draft and the user must publish it from the LinkedIn Posts page in the app). A random 30–180 s anti-detection delay is applied before the publish call. Attachments are not supported via MCP — add images in the in-app post editor.
    Connector
  • Search through a user's LinkedIn bookmarks using either keyword (text) search or semantic (meaning-based) search. Supports all list_bookmarks filters, full-text search via the q field, and semantic search via the vector_search_term field for natural language or topic-based queries. IMPORTANT: At least one of 'q', 'vector_search_term', or 'author' must be provided. If the user asks to find posts by a specific author (e.g., 'Show posts by John Doe', 'Find posts from Suresh sambantham'), use the 'author' parameter instead of putting the author name in the 'q' field. Use 'q' for searching post content, not for filtering by author.
    Connector