Official7 toolsLive

by veezeehq

LinkedIn people and company data for AI agents. Free 500-credit trial via the provision tool.

Topics

ai-agentslinkedinmcpmcp-servermodel-context-protocol

Captured live from the server via tools/list.

provision

Create a free trial account and get an API key, no signup and no card. Call this first if you have no key: you get 500 free credits. Over MCP, later calls in this same session authenticate automatically; over REST, send the key as 'Authorization: Bearer <key>' on every call. The response includes the api_key (shown exactly once, so store it) and a claim_url to keep the account permanently. Costs 0 credits. Trial limits: 1 concurrent call, 20 calls/minute, search capped at 10 results per call, 5 realtime fetches total. Not for checking your balance: that is get_usage.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

resolve_url

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 get_profile or get_posts. For companies, use the returned HANDLE with get_company or get_posts; the company URN/id is a search_people filter input, not a fetch identifier. Costs 2 credits. Skip this tool when you already have a slug, URN, or clean URL: get_profile and get_company accept those directly, so resolving first would waste 2 credits. Not for non-LinkedIn URLs; it returns INVALID_INPUT for those.

Parameters1

url

string

required

A LinkedIn URL, e.g. https://www.linkedin.com/in/williamhgates or .../company/microsoft.

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "A LinkedIn URL, e.g. https://www.linkedin.com/in/williamhgates or .../company/microsoft."
    }
  },
  "required": [
    "url"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_profile

Fetch one person's LinkedIn profile. identifier accepts a profile URL, the slug after /in/ (e.g. 'williamhgates'), or a urn:li:fsd_profile URN; URLs are cleaned automatically. Always returns the overview (name, headline, location, current position, follower counts) plus up to 2 requested sections from about|experience|education|skills at no extra cost; each section beyond 2 adds 2 credits (max 4 sections). Costs 4 credits base. If you only have a name, use search_people first; this tool does not search. Results from search_people with is_anonymous=true cannot be fetched here; treat them as 'someone matching this exists' and stop. Companies belong to get_company.

Parameters4

identifier	string	required	Profile URL, slug (after /in/), or urn:li:fsd_profile URN.
sections	array	optional	Extra profile sections. First 2 are included in the base price.
freshness	string	optional	recent (default) serves cached data from the last few hours when available; realtime forces a live fetch for +2 credits (refunded if we fall back to cached data).
max_credits	integer	optional	Spend ceiling for this one call. The call is rejected (nothing charged) if its quote exceeds this. Only the quote is ever reserved, never this ceiling.

Raw schema

{
  "type": "object",
  "properties": {
    "identifier": {
      "type": "string",
      "description": "Profile URL, slug (after /in/), or urn:li:fsd_profile URN."
    },
    "sections": {
      "description": "Extra profile sections. First 2 are included in the base price.",
      "maxItems": 4,
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "about",
          "experience",
          "education",
          "skills"
        ]
      }
    },
    "freshness": {
      "default": "recent",
      "description": "recent (default) serves cached data from the last few hours when available; realtime forces a live fetch for +2 credits (refunded if we fall back to cached data).",
      "type": "string",
      "enum": [
        "recent",
        "realtime"
      ]
    },
    "max_credits": {
      "description": "Spend ceiling for this one call. The call is rejected (nothing charged) if its quote exceeds this. Only the quote is ever reserved, never this ceiling.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "identifier"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

search_people

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. Company filters accept a company name, slug, numeric id, or URN; names are resolved 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 company NAME filter with limit=30: name resolution spends one of the call's three internal fetches, so that combination is rejected. With a company name keep limit<=20; for limit=30 pass the company's numeric id or URN (get_company returns both). 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 get_profile. For one known person with a URL/slug, call get_profile directly instead.

Parameters11

keywords	string	optional	Free-text query: a name, a title, or both.
first_name	string	optional
last_name	string	optional
title	string	optional	Current job title filter.
school	string	optional
current_company	string	optional	Company name, slug, numeric id, or urn:li:fsd_company URN.
past_company	string	optional	Same accepted forms as current_company.
limit	integer	optional	How many results to return.
cursor	string	optional	Cursor from a previous page.
freshness	string	optional	recent (default) serves cached data from the last few hours when available; realtime forces a live fetch for +2 credits (refunded if we fall back to cached data).
max_credits	integer	optional	Spend ceiling for this one call. The call is rejected (nothing charged) if its quote exceeds this. Only the quote is ever reserved, never this ceiling.

Raw schema

{
  "type": "object",
  "properties": {
    "keywords": {
      "description": "Free-text query: a name, a title, or both.",
      "type": "string"
    },
    "first_name": {
      "type": "string"
    },
    "last_name": {
      "type": "string"
    },
    "title": {
      "description": "Current job title filter.",
      "type": "string"
    },
    "school": {
      "type": "string"
    },
    "current_company": {
      "description": "Company name, slug, numeric id, or urn:li:fsd_company URN.",
      "type": "string"
    },
    "past_company": {
      "description": "Same accepted forms as current_company.",
      "type": "string"
    },
    "limit": {
      "default": 10,
      "description": "How many results to return.",
      "type": "integer",
      "minimum": 1,
      "maximum": 30
    },
    "cursor": {
      "description": "Cursor from a previous page.",
      "type": "string"
    },
    "freshness": {
      "default": "recent",
      "description": "recent (default) serves cached data from the last few hours when available; realtime forces a live fetch for +2 credits (refunded if we fall back to cached data).",
      "type": "string",
      "enum": [
        "recent",
        "realtime"
      ]
    },
    "max_credits": {
      "description": "Spend ceiling for this one call. The call is rejected (nothing charged) if its quote exceeds this. Only the quote is ever reserved, never this ceiling.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_company

Fetch one company's LinkedIn page: name, description, industry, employee count, headquarters, website, founding year, specialities, and the URN/numeric id you need for search_people company filters. identifier accepts a company URL, the slug after /company/ (e.g. 'microsoft'), or a website domain like 'microsoft.com'; numeric ids and URNs are search-filter inputs, not fetch identifiers. Domains are resolved to a company and verified against that company's website: a domain identifier always QUOTES base+4 credits (set max_credits accordingly), and the 4-credit resolution surcharge is refunded at settlement when the domain was resolved before, so known domains settle at the base price. A domain that cannot be verified to a company returns INVALID_INPUT with the closest matches instead of a guessed company. Costs 4 credits base. This tool does not search by name: if you only have an approximate company name, use search_people's current_company filter (it resolves names) or give the exact slug. For the company's posts, use get_posts with the same identifier.

Parameters3

identifier	string	required	Company URL, slug (after /company/), or website domain (e.g. 'microsoft.com'). Numeric ids/URNs are not fetchable; use them only in search_people company filters.
freshness	string	optional	recent (default) serves cached data from the last few hours when available; realtime forces a live fetch for +2 credits (refunded if we fall back to cached data).
max_credits	integer	optional	Spend ceiling for this one call. The call is rejected (nothing charged) if its quote exceeds this. Only the quote is ever reserved, never this ceiling.

Raw schema

{
  "type": "object",
  "properties": {
    "identifier": {
      "type": "string",
      "description": "Company URL, slug (after /company/), or website domain (e.g. 'microsoft.com'). Numeric ids/URNs are not fetchable; use them only in search_people company filters."
    },
    "freshness": {
      "default": "recent",
      "description": "recent (default) serves cached data from the last few hours when available; realtime forces a live fetch for +2 credits (refunded if we fall back to cached data).",
      "type": "string",
      "enum": [
        "recent",
        "realtime"
      ]
    },
    "max_credits": {
      "description": "Spend ceiling for this one call. The call is rejected (nothing charged) if its quote exceeds this. Only the quote is ever reserved, never this ceiling.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "identifier"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_posts

Fetch the recent LinkedIn posts of one person or one company. identifier accepts a profile or company URL, a slug, or a person URN; the entity type is detected automatically. Company URNs and numeric company ids are search-filter inputs, not fetch identifiers: use the company slug or URL here. Returns one page of posts (text, created_at, author, likes, comments_count, shares, is_repost, url) with a cursor for older posts. Costs 4 credits per page. Use this for 'what has X been posting', voice-of-company research, or activity checks before outreach. Not for reading one specific post you already have a URL for, and not for keyword search across LinkedIn; neither is supported in v1.

Parameters4

identifier	string	required	Person or company URL, slug, or URN.
cursor	string	optional	Cursor from a previous page for older posts.
freshness	string	optional	recent (default) serves cached data from the last few hours when available; realtime forces a live fetch for +2 credits (refunded if we fall back to cached data).
max_credits	integer	optional	Spend ceiling for this one call. The call is rejected (nothing charged) if its quote exceeds this. Only the quote is ever reserved, never this ceiling.

Raw schema

{
  "type": "object",
  "properties": {
    "identifier": {
      "type": "string",
      "description": "Person or company URL, slug, or URN."
    },
    "cursor": {
      "description": "Cursor from a previous page for older posts.",
      "type": "string"
    },
    "freshness": {
      "default": "recent",
      "description": "recent (default) serves cached data from the last few hours when available; realtime forces a live fetch for +2 credits (refunded if we fall back to cached data).",
      "type": "string",
      "enum": [
        "recent",
        "realtime"
      ]
    },
    "max_credits": {
      "description": "Spend ceiling for this one call. The call is rejected (nothing charged) if its quote exceeds this. Only the quote is ever reserved, never this ceiling.",
      "type": "integer",
      "minimum": 0,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "identifier"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

get_usage

Check your balance, plan, limits, and the last 10 charges (receipt ids included). Costs 0 credits and is exempt from the per-minute rate limit, so call it whenever you need to budget. The response includes upgrade_url: give it to your human when credits or plan limits block you; purchases credit this account directly with no login. Trial accounts also get the claim_url for keeping the account. Not for creating an account (provision) or fetching LinkedIn data.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "$schema": "http://json-schema.org/draft-07/schema#"
}

README.md2 KBView on GitHub

Veezee MCP server

LinkedIn people and company data for AI agents, over MCP or REST. This repo is the public home and issue tracker for the hosted server io.veezee/linkedin on the official MCP Registry. The server is a hosted service; there is nothing to build or run from this repo.

Endpoint: https://mcp.veezee.io/mcp (streamable-http). Legacy HTTP+SSE: https://mcp.veezee.io/sse.
Free trial: call the provision tool. 500 credits, no signup, no card, no key needed for that first call.
Website and docs: https://veezee.io
Found a bug or a gap? Open an issue or write hello@veezee.io.

The seven tools

tool	what it does
`provision`	create a free trial account, returns your API key
`resolve_url`	identify a LinkedIn URL
`get_profile`	get a person profile
`search_people`	search people
`get_company`	get a company
`get_posts`	recent posts by a person or company
`get_usage`	check credits and recent charges (free)

Full tool reference with schemas and credit costs: https://veezee.io/docs

Install

Claude Code:

code

claude mcp add --transport http veezee https://mcp.veezee.io/mcp

Codex CLI:

code

codex mcp add veezee --url https://mcp.veezee.io/mcp

Cursor (.cursor/mcp.json or ~/.cursor/mcp.json):

json

{
  "mcpServers": {
    "veezee": { "url": "https://mcp.veezee.io/mcp" }
  }
}

VS Code (.vscode/mcp.json):

json

{
  "servers": {
    "veezee": { "type": "http", "url": "https://mcp.veezee.io/mcp" }
  }
}

claude.ai: Settings > Connectors > Add custom connector > https://mcp.veezee.io/mcp.

More clients (Windsurf, Cline, Zed, plain REST), each snippet verified against the client's official docs: https://veezee.io/docs/clients

REST twin

Every tool has a REST route with identical semantics at https://api.veezee.io (contract: https://veezee.io/openapi.json). A typed TypeScript SDK and CLI ship as @veezee/sdk (docs: https://veezee.io/docs/sdk).

Install

Tools (7)

provisionresolve_urlget_profilesearch_peopleget_companyget_postsget_usage

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.veezee.io/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "linkedin": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.veezee.io/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

Linkedin

Topics

provision

resolve_url

get_profile

search_people

get_company

get_posts

get_usage

Veezee MCP server

The seven tools

Install

REST twin

Links

Install

Remote endpoint