For Agents
Look up companies, people, funding rounds, and investments on Crunchbase, plus run faceted searches and autocomplete queries against the v4 dataset.
Use for: Find Crunchbase data for the company stripe.com, Search for Series B fintech companies founded after 2020, Get the full funding history of OpenAI, Look up the investor profile for Sequoia Capital
Not supported: Does not handle CRM record creation, outbound messaging, or financial transaction execution - use for reading Crunchbase company, people, and funding data only.
Jentic publishes the only available OpenAPI specification for Crunchbase API, keeping it validated and agent-ready. The Crunchbase REST API provides firmographic, financial, and relationship data on organisations, people, funding rounds, acquisitions, investments, events, and funds. The 15 endpoints cover entity lookups by ID, faceted search across each entity type, autocomplete, and deleted-entity tracking. Authentication uses an API key delivered either in the X-cb-user-key header or as a user_key query parameter.
Install Jentic One Beta
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Crunchbase API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fcrunchbase.com%2Fcrunchbase-api" | shStep 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fcrunchbase.com%2Fcrunchbase-api" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
What an agent can do with Crunchbase API.
Look up an organisation, person, funding round, acquisition, investment, event, or fund by Crunchbase entity ID
Run faceted searches over organisations, people, funding rounds, acquisitions, investments, and funds with structured query bodies
Autocomplete entity names for type-ahead UI components
Track deleted entities to keep a downstream cache or CRM in sync
GET STARTED
Pull funding history and investor relationships for a target company
Discover companies by industry, location, headcount, or funding stage filters
Patterns agents use Crunchbase API for, with concrete tasks.
★ Sales Account Research
Pull firmographic context (headcount, location, funding stage, last raise) on a target list of accounts before an outbound sales sequence. Crunchbase's organisation lookup and search endpoints return structured fields ready to populate a CRM.
POST to /data/searches/organizations with a filter for funding_stage=series_b and location_identifier matching 'United States', then enrich each result via GET /data/entities/organizations/{entity_id}.
Investor and Portfolio Mapping
Build a network map of investors, funds, and the companies they have backed by walking funding-round, investment, and fund entities. Crunchbase exposes the relationship edges directly so the agent does not have to scrape secondary sources.
POST /data/searches/funding-rounds with a filter for investor_identifiers containing the target VC, then GET /data/entities/funding-rounds/{entity_id} for each row to retrieve full investor and amount detail.
M&A and Deal Flow Tracking
Monitor acquisitions and large funding events in target sectors by polling search endpoints with date filters, then resolving each acquisition or funding round to full detail. Useful for competitive intelligence and deal-team briefings.
POST /data/searches/acquisitions filtering announced_on within the last 30 days for a target industry, then GET /data/entities/acquisitions/{entity_id} for each match to capture buyer, target, and amount.
Type-ahead Company Picker
Power a type-ahead UI in an internal tool by calling the autocomplete endpoint as the user types and resolving the chosen suggestion to its full organisation record on selection. Keeps lookups fast and reduces the size of the search payload.
Call GET /data/autocompletes with the user's partial input and entity_def_ids=organization, then on selection call GET /data/entities/organizations/{entity_id} for full detail.
Agent-Driven Company Intelligence
Allow an AI agent to answer ad-hoc analyst questions ('How much has this company raised?', 'Who else did the Series A?') by routing through Jentic so the API key stays in the vault and the agent only needs to express its intent.
Search Jentic for 'find company funding history', load the lookup-organization operation, and execute it with the company's Crunchbase entity ID.
15 endpoints — jentic publishes the only available openapi specification for crunchbase api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/data/entities/organizations/{entity_id}
Look up an organisation by ID
/data/entities/people/{entity_id}
Look up a person by ID
/data/searches/organizations
Faceted search over organisations
/data/searches/funding-rounds
Search funding rounds
/data/searches/acquisitions
Search acquisitions
/data/autocompletes
Autocomplete entity names
/data/deleted_entities
Retrieve recently deleted entities
/data/entities/organizations/{entity_id}
Look up an organisation by ID
/data/entities/people/{entity_id}
Look up a person by ID
/data/searches/organizations
Faceted search over organisations
/data/searches/funding-rounds
Search funding rounds
/data/searches/acquisitions
Search acquisitions
/data/autocompletes
Autocomplete entity names
/data/deleted_entities
Retrieve recently deleted entities
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Crunchbase API by hand means placing your key in the X-cb-user-key header, building the POST search bodies for organizations and funding rounds, and handling autocomplete calls yourself. Through Jentic you install once, import the Crunchbase API from the API Directory, store the API key once, and your agent calls it.
Permission scoping
Crunchbase puts the entity id in the URL path for lookups (/data/entities/organizations/{entity_id}), so a rule can pin your agent to reading one organization or person. You choose the operations it may call, so the search endpoints are not included unless you add them.
Credential isolation
Your Crunchbase API key is stored once, encrypted, by your own Jentic One instance and injected into the X-cb-user-key header at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'find company funding history' or 'look up a person', and Jentic returns the matching Crunchbase operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Alternatives and complements available in the Jentic catalogue.
Specific to using Crunchbase API through Jentic.
Why is there no official OpenAPI spec for Crunchbase API?
Crunchbase does not publish an OpenAPI specification. Jentic generates and maintains this spec so that AI agents and developers can call Crunchbase API via structured tooling. It is validated against the live API and kept up to date. Get started with Jentic One, the self-hosted execution layer.
What authentication does the Crunchbase API use?
The API uses an API key, passed either in the X-cb-user-key request header or as the user_key query parameter. Through Jentic the key is stored encrypted in the vault so the agent never receives its raw value.
Can I search Crunchbase for companies by funding stage with this API?
Yes. POST a search query body to /data/searches/organizations including a funding_stage filter and any other facet filters (location, industry, headcount). The response returns matching organisation entities that can be expanded via /data/entities/organizations/{entity_id}.
How do I retrieve a company's full funding history through the Crunchbase API?
First look up the organisation via GET /data/entities/organizations/{entity_id}, then call POST /data/searches/funding-rounds filtering on funded_organization_identifier to retrieve every round attached to that company.
What are the rate limits for the Crunchbase API?
The OpenAPI specification does not document numeric rate limits. Crunchbase enforces tier-dependent quotas - review your contract with Crunchbase API Support (api@crunchbase.com) and watch for HTTP 429 responses.
How do I look up a company through Jentic?
Run pip install jentic, search 'find company funding data', load the lookup-organization operation, and execute it with the Crunchbase entity ID. Jentic resolves the API key automatically from the vault.
Can I limit what my agent is allowed to do with the Crunchbase API?
Yes. Because you run Jentic One yourself, your own rules decide which Crunchbase operations and credentials the agent may use, so you can grant only the lookup endpoints like GET /data/entities/organizations/{entity_id} and GET /data/entities/people/{entity_id} while withholding the faceted search endpoints. Since the entity id sits in the URL path for those lookups, a rule can pin the agent to reading a single organization or person. The POST search endpoints such as /data/searches/organizations and /data/searches/funding-rounds are not available to the agent unless you explicitly add them.