Crunchbase

Endpoint

Hosted endpoint · transport http

Connect

This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):

For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:

If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:

Tools

• cb_expert_query_answer — Answers a natural-language question using live Crunchbase data; the expert service interprets the question, constructs and executes the queries, and returns an answer with supporting results. Each response carries a request_id needed for cb_expert_submit_feedback.
• cb_expert_build_search — Translates a natural-language description of the entities you want into a compiled, structured Crunchbase search, handling field resolution, operator selection and value formatting.
• cb_expert_query_domain — Answers meta-questions about the shape of the Crunchbase data domain - what entities, fields and relationships exist, and whether a draft question is answerable. Does not query records.
• cb_expert_resolve_entity — Disambiguates an entity name against the Crunchbase catalog and resolves it to a canonical entity; returns a single match when confident, otherwise a ranked candidate list.
• cb_expert_submit_feedback — Records user feedback on a previous cb_expert_query_answer result; negative feedback may trigger the expert service to rewrite the query and return corrected results.
• cb_reference — The schema reference for everything else. Returns Markdown documentation for a given path; empty path or "index" returns the full navigable index. Paths include entities, entities//fields[/], entities//cards, field_types, operators, and guidance/{search_query,build_search,query_answer}.
• cb_entity_autocomplete — Searches Crunchbase entities by name and returns matching identifiers with short descriptions - the way to obtain valid identifiers (including locations and categories used as filter values) before calling other tools.
• cb_entity_get — Retrieves the full profile for one already-identified entity - fields plus relationship cards. Documented as the most expensive call in the toolset.
• cb_search_query — Executes a structured search and returns matching entities with the requested fields - the deterministic, repeatable precision instrument.
• cb_list_query — Returns all saved lists owned by the caller, with names, entity counts and timestamps.
• cb_list_create — Creates a new empty list from a single name parameter.
• cb_list_add_entities — Appends entities to an existing list, from list_id and an array of entity_ids.
• cb_list_get — Returns the entity identifiers in a list, with after_id for pagination.
• cb_metering_get_state — Returns the caller-visible meter states for the current user - which limits apply and how they affect each tool. Takes no parameters.

About MCP

The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.

Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.