Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Search LinkedIn people

linkedin_live_people_search_v2
Read-onlyIdempotent

Search LinkedIn people by keyword, title, company, school, industry, or location filters and paginate results to build targeted prospect or candidate lists.

Instructions

Search LinkedIn people by keyword and filters. Optional inputs: count, start, cursor, keyword, firstName and 9 more. Returns a list (use cursor when paginated). Put free text in keyword (singular). currentCompany and pastCompany take comma-separated numeric LinkedIn company ids, not names; get one from linkedin_live_organization_resolve_v2 with the company slug. Example: {"keyword":"cfo","currentCompany":"1441"}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "linkedin_live_people_search_v2"
  }
}

Input Schema

NameRequiredDescriptionDefault
countNo
startNo
titleNoJob title, e.g. `CFO` or `Head of Sales`. Multi-word titles are supported. One title per request: comma-separated titles are rejected.
cursorNo
schoolNoComma-separated numeric LinkedIn school IDs, e.g. `1646`. School names are not accepted.
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
keywordNo
industryNoComma-separated numeric LinkedIn industry IDs, e.g. `4`. Industry names are not accepted.
lastNameNo
firstNameNo
llm_modelYesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess.
geoEntityIdNoComma-separated numeric LinkedIn geo IDs for where people are based, e.g. `103644278` (United States). Place names are not accepted. [Find a geo ID](https://www.socialfetch.dev/docs/api/v2/linkedin/geo-ids).
pastCompanyNo
currentCompanyNo
conversation_idNoEcho the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it.
profileLanguageNo
serviceCategoryNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds that the result is a list and that cursor is used for pagination, but says nothing about rate limits, result caps, or credit cost for a 17-parameter open-world search.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the purpose, then the highest-risk gotchas (ID formats) and a concrete JSON example. The enumeration of optional inputs with 'and 9 more' is redundant against the schema and slightly wastes space, but overall it is compact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 17-parameter, open-world search with no output schema, the definition covers the ID-format traps and pagination direction but omits default page size, result-count behavior, and the conversation_id sequencing constraint (left only to the schema). Adequate but with clear gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is low (41%), and the description does helpfully document that currentCompany/pastCompany require comma-separated numeric company IDs rather than names, and that keyword is singular free text. It leaves other undocumented parameters (lastName, profileLanguage, serviceCategory, cursor origin) unexplained and only summarizes the rest as '9 more', so it only partially compensates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Search LinkedIn people by keyword and filters'), which is enough to separate it from profile/employment-history siblings. It does not explicitly contrast with linkedin_live_person_resolve_v2 or profile_batch, so sibling differentiation is only implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives actionable in-tool guidance ('Put free text in keyword (singular)', 'use cursor when paginated') and correctly routes company-id lookup to linkedin_live_organization_resolve_v2. However, it never says when to choose this search over person_resolve or the profile tools, so selection guidance remains implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools