Loading MCP servers…
MCP servers
DataForB2B
Power your sales or recruiting AI agent with live B2B data. DataForB2B is a people and company search API with 70+ filters including job title, skills, company size, LinkedIn URL, funding stage, investor, past employers, certifications, years of experience, GitHub repositories, languages and more. Enrich any profile with verified work emails and GitHub profiles. Data sourced live across 60+ public sources. GDPR and CCPA compliant.
Follow the source guide for connection and authentication details.
Available tools
search_natural_language
Search people or companies using a free-form English query. The backend LLM interprets the query and builds structured filters automatically. Use this for fuzzy intent like "software engineers in Paris with 5+ years" or "AI startups in France that raised Series A". For deterministic filtering on specific columns, prefer `search_people` or `search_company` which take an explicit FilterGroup.
search_people
Search professional profiles using structured filters. Use this when you want precise, deterministic filtering on specific columns (exact country, company size range, funding stage, etc.). For free-form queries like "AI engineers in Berlin who recently raised", prefer `search_natural_language` which builds these filters from English. Returns paginated profiles matching ALL/ANY filter conditions depending on the `op` of the FilterGroup. Available columns for `filters.conditions[].column`: Profile: first_name, last_name, profile_location, profile_country (ISO-2, e.g. "US", "GB", "FR"; use GB for UK), profile_industry, follower_count, keyword (full-text on headline) Current job: current_company, current_title, current_job_location, current_company_industry (e.g. "Information Technology & Services", "Computer Software"), current_company_category (lowercase: "software", "consulting", ...), current_company_size ("2-10", "11-50", "51-200", "201-500", "501-1000", "1001-5000", "5001-10000", "10001+"), current_company_id, current_employment_type ("Full-time", "Part-time", "Self-employed", "Freelance", "Contract", "Internship", ...), years_in_current_position, years_at_current_company, current_company_has_funding (bool), current_company_funding_stage ("seed_round", "series_a", ..., "series_h", "pre_seed_round", "angel_round", "grant", "private_equity_round", "undisclosed"; legacy values without _round suffix also exist — use `in` with both forms), current_company_investor Past jobs: past_company, past_title, past_job_location, past_company_industry, past_company_size, past_company_id, past_employment_type, years_at_past_company Skills: skill (e.g. "Python", "JavaScript", "Machine Learning") Education: school, degree, degree_level ("Bachelor", "Master", "PhD", "Associate"), field_of_study Languages: language (e.g. "English"), language_iso (e.g. "en"), language_proficiency ("Native", "Professional", "Limited", "Elementary") Certifications: certification, certification_authority Experience: years_of_experience, num_total_jobs, is_currently_employed (bool) Operators: `=`, `>`, `>=`, `<`, `<=`, `between` (requires value and value2), `in` (value is a list), `like` (text search, case-insensitive).
search_company
Search companies using structured filters. Use this when you want precise filtering on specific columns (industry, country, employee count range, funding stage, founded year, etc.). For free-form queries like "AI startups in France that raised Series A", prefer `search_natural_language` with category="company". Returns paginated companies matching ALL/ANY filter conditions depending on the `op` of the FilterGroup. Available columns for `filters.conditions[].column`: Basic: name, tagline, description, domain, universal_name (slug), keyword (full-text), industry (lowercase: "software development", "it services and it consulting", "financial services", ...) Size: employee_count (int) or employee_count range ("1-10", "11-50", "51-200", "201-500", "501-1000", "1001-5000", "5001-10000", "10001+") Headquarters: country_iso_code (ISO-2), city, region Offices: office_country (ISO-2), office_city, office_region Growth: employee_growth_1m, employee_growth_6m, employee_growth_12m (float, %), recent_hires_count Metadata: founded_year, company_type ("PRIVATELY_HELD", "PUBLIC_COMPANY", "NON_PROFIT", "PARTNERSHIP", "SELF_OWNED", "EDUCATIONAL", "SELF_EMPLOYED", "GOVERNMENT_AGENCY"), follower_count, page_verified (bool), category (lowercase: "software", "consulting", "financial services", ...) Funding: last_funding_amount_usd, last_funding_date (YYYY-MM-DD), funding_stage_normalized ("seed_round", "series_a", ..., "pre_seed_round", "angel_round", "grant", "private_equity_round", "undisclosed"), has_funding (bool) Operators: `=`, `>`, `>=`, `<`, `<=`, `between` (requires value and value2), `in` (value is a list), `like` (text search, case-insensitive).
enrich_profile
Enrich a single professional profile with detailed profile data, work email, personal email, and/or GitHub profile. Each enrichment flag controls one data source and bills separately.
enrich_company
Enrich a single company with full data from public sources (description, industry, headquarters, employee count, funding, offices, etc.).
search_lookalike
Find similar people or companies using AI-powered vector similarity. Provide either `profile` (to find similar people) OR `company` (to find similar companies) — not both. Optionally narrow results with `country` or `location`.