DataForB2B

Power your sales or recruiting AI agent with live B2B data.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • 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 "s
  • 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
  • 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.). Fo

What data it sees

Do you need an account

No: the server works without sign-in

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.

How to connect

How to connect DataForB2B to Claude

The server address to paste into Claude settings:

https://dataforb2b--datafor-b2b.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect DataForB2B to ChatGPT

The server address to paste into ChatGPT settings:

https://dataforb2b--datafor-b2b.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect DataForB2B to Cursor

The server address to paste into Cursor settings:

https://dataforb2b--datafor-b2b.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (6)

Raw names from tools/list. Only developers need these.

search_natural_languageSearch 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_peopleSearch 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_companySearch 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_profileEnrich 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_companyEnrich a single company with full data from public sources (description, industry, headquarters, employee count, funding, offices, etc.).
search_lookalikeFind 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`.