Skip to main content
Glama
DataForB2B

DataForB2B MCP Server

Official
by DataForB2B

Search People

search_people
Read-onlyIdempotent

Search professional profiles using structured filters.

Instructions

Search professional profiles using structured filters.

Use this for any people search: translate the user's intent (e.g. "AI engineers in Berlin who recently raised") into structured filters on specific columns (country, company size range, funding stage, etc.). The available columns and operators are documented on the filters parameter.

Returns paginated profiles matching ALL/ANY filter conditions depending on the op of the FilterGroup.

To find people at a SPECIFIC company you already identified (e.g. via search_company or enrich_company), filter on current_company_id (or past_company_id) with that company's id (e.g. "org_xxx") — NOT current_company (the name), which also matches other companies that happen to share the name and adds noise.

To target people by their COMPANY's business (e.g. "founders of AI sales-agent startups"), qualify the company itself: filter current_company_category (lowercase, holds precise niche values — "artificial intelligence", "sales automation", "saas") and/or current_company_industry, and when no category fits the niche, current_company_keyword (full-text on the employer's name/tagline/description — OR several "=" phrase variants). keyword searches the PERSON's own headline, so it fits attributes of the person themselves; for a company trait it matches unrelated people ("sales agent" → real-estate agents, sales reps).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoNumber of profiles to return (max 100; use offset to paginate further).
offsetNoPagination offset (number of results to skip).
filtersYesFilter group: {"op": "and"|"or", "conditions": [<condition or nested group>, …]}; groups can be nested. Columns — profile: first_name, last_name, profile_location, profile_country, profile_industry, follower_count, keyword (headline full-text) · current job: current_company, current_title, current_job_location, current_company_industry, current_company_category, current_company_size, current_company_id, current_company_keyword (full-text on the employer's name/tagline/description), current_employment_type, years_in_current_position, years_at_current_company, current_company_has_funding, current_company_funding_stage, current_company_investor · past jobs: past_company, past_title, past_job_country, past_company_industry, past_company_size, past_company_id, past_employment_type, years_at_past_company · skills & education: skill, school, degree, degree_level, field_of_study · languages: language, language_iso, language_proficiency · certifications: certification, certification_authority · experience & contact: years_of_experience, num_total_jobs, is_currently_employed, has_email, has_phone. Operators: =, !=, >, >=, <, <=, in, not_in, like, not_like, regex, between, is_null, is_not_null — semantics and per-column value formats are documented on the condition fields of the schema. Example — fintech CEOs/founders in the US or UK: {"op":"and","conditions":[{"op":"or","conditions":[{"column":"current_title","type":"regex","value":"CEO"},{"column":"current_title","type":"like","value":"Founder"}]},{"column":"current_company_category","type":"=","value":"fintech"},{"column":"profile_country","type":"in","value":["US","GB"]}]}
order_byNoColumn to sort by, e.g. "follower_count", "years_of_experience".
enrich_liveNoWhen true (1.5 credits/profile), each profile is enriched live from LinkedIn so data is fresh. When false (0.75 credits/profile), data is served from the cached database — faster and cheaper. Default is false: live enrichment of many profiles is slow and can time out, so opt in only when freshness matters.
order_directionNoSort direction.desc
reveal_personal_emailNoWhen true, the actual personal_emails array is included on each result (extra credits per email revealed). When false, only the has_personal_email boolean flag is returned.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoNumber of profiles returned in this page.
errorNoHTTP-style status code, present only when the call failed.
totalNoTotal number of matching profiles (estimate).
detailNoError message, present only when the call failed.
offsetNoPagination offset of this page.
resultsNoMatching profile objects.
credits_usedNoCredits consumed by this search.
has_next_pageNoWhether more results are available.
total_is_cappedNoTrue if total reached the 10000 cap.
Behavior5/5

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

The description discloses key behavioral traits: pagination of results, ALL/ANY matching based on FilterGroup `op`, and the risk of matching unrelated companies when using `current_company` by name. It also warns that `keyword` searching on a company trait can return unrelated people, adding significant context beyond the readOnly/openWorld annotations.

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?

The description is front-loaded with a one-line purpose, followed by logically separated paragraphs covering usage, pagination, and advanced filtering tips. While longer than a minimal description, each sentence carries practical weight for a tool with a complex nested filter schema, and the structure aids readability.

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

Completeness5/5

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

Given the tool's complex schema and rich output schema, the description covers the primary use cases, points to the schema for parameter details, and explains common pitfalls. It addresses pagination, group semantics, and specific intent translation (e.g., converting natural language to filters), making it complete for an agent to invoke correctly.

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

Parameters4/5

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

The input schema already provides exhaustive detail on columns, operators, and value formats (100% coverage). The description adds strategic filter-construction semantics, such as using OR groups for same-column alternatives and choosing between `current_company_category` and `current_company_keyword` based on niche fit, which is not merely a restatement of the schema.

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

Purpose5/5

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

The description opens with 'Search professional profiles using structured filters,' clearly identifying the verb (search), resource (professional profiles), and method (structured filters). It distinguishes itself from sibling tools like search_company and search_posts by focusing exclusively on people search.

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

Usage Guidelines5/5

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

It explicitly states 'Use this for any people search' and provides actionable guidance such as using `current_company_id` instead of `current_company` to avoid noise, and contrasting `keyword` (person headline) with `current_company_keyword` (employer). It also references sibling tools (search_company, enrich_company) for obtaining company IDs.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/DataForB2B/dataforb2b-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server