Skip to main content
Glama
DataForB2B

DataForB2B MCP Server

Official
by DataForB2B

Search Companies

search_company
Read-onlyIdempotent

Search companies using structured filters.

Instructions

Search companies using structured filters.

Use this for any company search: translate the user's intent (e.g. "AI startups in France that raised Series A") into structured filters on specific columns (industry, country, employee count range, funding stage, founded year, etc.). The available columns and operators are documented on the filters parameter.

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

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoNumber of companies 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 — basic info: name, tagline, description, domain, universal_name, keyword (full-text across name/tagline/description), industry · size & locations: employee_count, country_iso_code, city, region, office_country, office_city, office_region · growth: employee_growth_1m, employee_growth_6m, employee_growth_12m, recent_hires_count · metadata: founded_year, company_type, follower_count, page_verified, category · funding & investors: last_funding_amount_usd, last_funding_date, funding_stage_normalized, has_funding, investor · live job postings (hiring signal): job_title, job_location. 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 — mid-size fintech/payments companies in the US or France: {"op":"and","conditions":[{"op":"or","conditions":[{"column":"category","type":"=","value":"fintech"},{"column":"description","type":"=","value":"payment processing"}]},{"column":"country_iso_code","type":"in","value":["US","FR"]},{"column":"employee_count","type":"between","value":50,"value2":500}]}
order_byNoColumn to sort by, e.g. "follower_count", "employee_count", "founded_year", "last_funding_amount_usd".
enrich_liveNoWhen true (1.5 credits/company), each company is enriched live from LinkedIn so data is fresh. When false (0.75 credits/company), data is served from the cached database — faster and cheaper.
order_directionNoSort direction.desc

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoNumber of companies returned in this page.
errorNoHTTP-style status code, present only when the call failed.
totalNoTotal number of matching companies (estimate).
detailNoError message, present only when the call failed.
offsetNoPagination offset of this page.
resultsNoMatching company objects.
credits_usedNoCredits consumed by this search.
has_next_pageNoWhether more results are available.
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds useful behavioral context beyond annotations: it returns paginated companies and that matching depends on the FilterGroup's op (ALL/ANY). This informs the agent about response shape and filter semantics without contradicting the annotations.

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

Conciseness5/5

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

The description is compact: three sentences, front-loaded with the core purpose. It avoids restating schema details and instead directs the agent to the schema for specifics. Every sentence contributes to either identifying the tool's purpose or guiding its usage.

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

Completeness4/5

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

Given the complexity of nested filter groups and the richness of the input schema, the description sufficiently covers the tool's search semantics, pagination, and filter-group behavior. It leverages the schema's extensive field-level documentation rather than duplicating it. A minor gap is the lack of any mention of output schema or response fields, but the output schema is present and reduces the need for that in the description.

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?

Schema coverage is 100%, so the baseline is 3. The description adds value by telling the agent to translate natural-language user intent into structured filters and by pointing to the filters parameter for available columns and operators. It also highlights the role of FilterGroup.op in combining conditions, which helps the agent construct valid filter objects.

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 companies using structured filters,' using a specific verb and resource that clearly distinguishes it from sibling tools like search_people or search_posts. It further reinforces the scope with 'Use this for any company search,' making the tool's purpose unambiguous.

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

Usage Guidelines4/5

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

The description explicitly states 'Use this for any company search' and provides concrete guidance on translating user intent into structured filters. It does not explicitly name alternatives or exclusion cases, but the sibling tools operate on different entities, so the usage context is clear enough for an agent to select it appropriately.

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