Skip to main content
Glama
306,292 tools. Last updated 2026-07-25 05:14

"Finding people on LinkedIn using their names" matching MCP tools:

  • Find people on LinkedIn by keywords and filters. The right tool when you have a name, role, or 'who is the X at Y' question without a profile URL. Pass keywords (free text: name, title, or both) and any of first_name, last_name, title, school, current_company, past_company. If keywords is omitted it is derived from the name or title filters; school or company filters alone are rejected with INVALID_INPUT, so include keywords with those. Company filters accept a company name, slug, numeric id, or URN. current_company names are matched by LinkedIn's own company search: typo-tolerant and fuzzy, so results can include people whose headline merely mentions the company; when you need exact filtering, pass the numeric id or URN (linkedin_get_company returns both). past_company names are resolved to an id for you. Costs 10 credits including the first 10 results; each further 10 results add 1 credit (limit max 30; trial keys max 10). A cursor page is a NEW call priced the same way by its own limit, so one limit=30 call is much cheaper than three limit=10 pages; prefer a larger limit over paginating. Do NOT combine a past_company NAME or a company-URL filter with limit=30: resolving those spends one of the call's three internal fetches, so that combination is rejected; keep limit<=20 with them or pass the numeric id. current_company names never spend a fetch, so they combine with any limit. Returns name, position, location, urn, public_identifier per result, a cursor for the next page, and total_matches. Results with is_anonymous=true are private profiles; do not pass them to linkedin_get_profile. For one known person with a URL/slug, call linkedin_get_profile directly instead.
    Connector
  • Enrich existing contacts with their full LinkedIn profile data via the connected LinkedIn account (Unipile) — headline, location, current company & position, full experience, education and skills are scraped from each contact's profile URL and saved onto the contact (and merged into profile_data). Use after search_google_xray to flesh out lightly-saved leads. Each contact is a real LinkedIn profile view, so keep batches small; max 8 per call. Returns per-contact enrichment status.
    Connector
  • Identify what a LinkedIn URL points at before fetching it. Give any LinkedIn profile, company, or post URL (utm params, www/m subdomains, trailing slashes are fine); get back {type: person|company|post, id, handle, canonical_url}. For profile URLs, id is the stable person URN; for company URLs, id is the stable company URN; for post URLs, id is the activity URN extracted from the URL. For people, use the returned handle or id with linkedin_get_profile or linkedin_get_posts. For companies, use the returned HANDLE with linkedin_get_company or linkedin_get_posts; the company URN/id is a linkedin_search_people filter input, not a fetch identifier. Costs 2 credits. Skip this tool when you already have a slug, URN, or clean URL: linkedin_get_profile and linkedin_get_company accept those directly, so resolving first would waste 2 credits. Not for non-LinkedIn URLs; it returns INVALID_INPUT for those.
    Connector
  • Search long-term memory using semantic similarity. ALWAYS SEARCH BEFORE ANSWERING marketing/strategy questions. Use short, specific keywords as queries. Available chapters: icp, strategy, campaigns, analytics, brand, competitors, learnings, general, pipeline, signals, playbook. TAG FILTERING: Memories are auto-tagged. Use metadata_filter with tags key to filter (e.g. metadata_filter: { chapter: 'campaigns', tags: 'linkedin' }).
    Connector
  • Fill a PDF form with the given field values and save the result to disk. WORKFLOW: 1) Call list_form_fields first to get exact field names and their x/y positions. 2) Use position coordinates to confirm which field is which — higher y = higher on page. 3) Pass exact field names from list_form_fields here. Never guess field names. Use for single-page or short forms (under 5 pages). Use fill_form_multipage for longer forms. Returns ok:false with unknown_fields if ALL provided field names are invalid. Returns ok:true with a warnings.unknown_fields list if SOME names are invalid (partial fill).
    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

Matching MCP Servers

Matching MCP Connectors

  • LinkedIn data for AI agents: search, profiles, companies, posts. Free key, self-minted, no signup.

  • linkedin-humblebrag MCP — wraps StupidAPIs (requires X-API-Key)

  • Strips the background from a video frame-by-frame using rembg (u2netp) on AetherWave's Python service. Pass a public `videoUrl`. Choose `bgType: "transparent"` for an alpha-channel WebM output (compositing) or `bgType: "color"` with a `customColor` hex for a solid replacement. 2 credits per second. Slowest tool in the surface (per-frame processing); a 6s clip takes ~4 min, a 30s clip ~15-20 min. Works best on subjects with clear edges (people, products). Returns the processed video URL (R2-hosted).
    Connector
  • Profiles I've vouched in (people who used one of my invite codes). Returns handle + display_name + avatar_url + when they joined. Symmetric counterpart of `list_my_invite_codes` — that one is keyed on the codes I issued, this one is keyed on the humans who actually showed up.
    Connector
  • Browse available video compositions and their expected props schemas. Call this before using clipform_render_composition to discover visual styles and their input props. For narrated slideshows from images, use clipform_generate_video instead.
    Connector
  • Find an honest scripture prayer for what someone is feeling after leaving the church: broken trust, anger, grief, fear, loneliness, shame, or doubt. Give a feeling in their own words (e.g. "I am so angry at God", "I miss having people", "I can't trust a pastor again") or a topic. Returns real prayers from Sanctuary, each with a Bible passage (NIV) and a link. For people who left the church but did not leave Jesus. Not counseling; anyone in crisis is pointed to 988.
    Connector
  • Resolve one or more game names to their Steam appids on needmoar.games. Call this first to turn a title like "Hollow Knight" into the numeric appid the versus and game_detail tools need. Accepts several names at once — pass every game the user mentioned in a single call and match each to its result.
    Connector
  • Head-to-head verdict for two games on needmoar.games: which one players like more, each game's community score (the share of a library it beats) and rank, and the full distribution of opinions on both. Use this to answer "do people prefer A or B?". Pass Steam appids — resolve names with search_games first. The response links to the matching /vs page you can cite.
    Connector
  • Backfill Chats Pull all existing LinkedIn conversations from Unipile into Iridium. Run this once after connecting LinkedIn to populate your inbox. Also repairs any blank participant names from a previous backfill. Takes 10-30 seconds depending on conversation count. ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
    Connector
  • Run Company Commenting Pipeline Generate LinkedIn comment drafts on recent posts by people who work at specific companies. USE THIS when the user names one or more companies: "comment on posts from people at Stripe" "I want to be visible to Anthropic and OpenAI engineers" "engage with anything Ramp employees posted this week" DO NOT USE for topic- or keyword-based commenting ("find me AI posts to comment on", "comment on posts about RAG") — use run_commenting_pipeline instead, which searches the whole of LinkedIn by the user's saved comment_topics. How it differs: this tool searches by AUTHOR COMPANY and recency only, with no keyword filter — ANDing a keyword against a single employer usually returns nothing on LinkedIn. Topical relevance is then judged by the model over whatever those employees actually posted. As a result it may legitimately return zero drafts if nobody at those companies posted anything worth engaging with; that is a valid outcome, not an error, and you should say so plainly rather than retrying. Takes up to 5 companies per call. Companies with no matching LinkedIn page come back in unresolved_companies — tell the user which ones failed. After calling this tool, ALWAYS display every draft to the user in full: **Post by [author_name] ([company]):** [post_text — display the complete text, never truncate] **Drafted comment:** [comment_text — display in full] Do NOT call approve_comment_draft or schedule anything unless the user explicitly asks. Args: companies: Company names, e.g. ["Stripe", "Ramp"]. Max 5. n: How many drafts to generate (default 3, capped by the user's remaining daily cap). date_posted: "past_24h" | "past_week" | "past_month". Default "past_week". ### Responses: **200**: Successful Response (Success Response) Content-Type: application/json
    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
  • Search ENS names using natural language. Supports all query types: - Filtered search: "4-letter words under 0.1 ETH" - Concept search: "ocean themed names" (semantic similarity across 3.5M indexed ENS names) - Creative search: "names for a coffee brand" (AI-generated suggestions) - Collection search: "crypto terms expiring soon" - Activity: "what sold recently?" - Availability check: "is coffee.eth taken?" - Bulk check: "check apple.eth, banana.eth, cherry.eth" - Collection/club floor: "999 club floor", "cheapest 10k club names" (returns real listings sorted by price) Returns structured results with name, price, owner, tags, and availability info. It searches the NAME database by pattern/length/price/club/vibe — it does NOT know who real-world people, teams, brands, athletes, musicians, or films are. For "find me NBA players / pop stars / Pixar films / presidents" use enumerate_entities instead (it returns correctly-spelled labels). Use this for "floor of <club>" / "cheapest in <collection>" (find_alpha can't — it has no collection param). For lifecycle-window lists — "which names are in premium / Dutch auction", "names in grace period", "expiring soon" — use get_expiring_names instead: its grace/premium statuses are on-chain-validated and premium rows carry live pricing.
    Connector
  • Composite snapshot of a specific user's activity on a project. Returns an identity block (visitorId, userEmail, userName, firstSeen, lastSeen), total pageviews, total custom events, session count, top pages this user visited, their most-fired event names, and their 20 most recent events with props. Use this for 'how is dancleary54@gmail.com using my app?' style questions — one call, full picture. For ad-hoc drill-down (just a count, just recent events) pass `user` to the individual tools instead. Default window is the last 7 days.
    Connector
  • Show the user's default paper size and orientation preferences (set on their account page). Useful when the user hasn't specified pageSize/orientation explicitly — call this to honor their defaults instead of using A4/Portrait blindly.
    Connector
  • Send a message to a thread, channel, or contact. Supports Telegram, Email, LinkedIn, and other connected channels. For LinkedIn posts (comment_thread kind), this posts a comment on the post. Can automatically resolve recipients and channels when not specified. Can send files/images/documents as attachments — pass `attachments=[file_id, ...]` with integer file IDs obtained from collections.list_files, search.files, or files.search. `text` is optional when attachments are provided.
    Connector
  • GET /trips/:tripID/discovery — Get the discovery block for a trip Discovery-only read for a trip. Returns the same `discovery` block as `GET /trips/:tripID` (people, fullPool, whyToMeet, events, overlappingTrips) without the trip body. Useful for callers that just want "who should I meet on this trip?" — the AI agent gets the ranked top-10 + their `whyToMeet` paragraphs in a single request. Use `?include=` to subset the response — comma-separated from `people,fullPool,whyToMeet,events,overlappingTrips`. Default is all. Common patterns: - `?include=people,whyToMeet` — top-10 picks + their AI-written "why you should meet them" paragraphs (keyed by userID, each carrying `{ text, generatedAt }`) - `?include=fullPool` — every visible DCer travelling/local during the trip window - `?include=events` — just events in the destination city during the trip window Open to any authenticated DCer; hidden + guest profiles are filtered out.
    Connector