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%2Fdata.crunchbase.com%2Fcrunchbase" | 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%2Fdata.crunchbase.com%2Fcrunchbase" | 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.
Search organizations across the Crunchbase database with structured filters
Search people by role, location, and organization affiliation
Search funding rounds and acquisitions by date, size, and investor
Retrieve full Crunchbase entity records for organizations, people, funding rounds, and acquisitions
Resolve autocomplete queries for organization and person pickers
GET STARTED
Authenticate via the user_key query parameter scoped to the calling account
Patterns agents use Crunchbase API for, with concrete tasks.
★ Outbound Sales Prospecting
Build a target account list of recently funded companies with structured filters instead of scraping news. POST /searches/organizations supports filters by funding stage, industry, geography, and date, and GET /entities/organizations/{entity_id} returns the full company profile for downstream CRM enrichment. Suitable for sales teams targeting venture-backed companies.
Search organizations matching 'Series B' funding stage in 'fintech' from the last 12 months, then retrieve full profiles for the top 25 results.
Investor and Acquisition Tracking
Track a specific investor's portfolio activity or watch acquisitions in a sector. POST /searches/funding_rounds and POST /searches/acquisitions accept investor and acquirer filters, and the matching GET endpoints return full deal records. Useful for venture analysts, M and A teams, and investor-relations functions.
Search funding rounds led by a target investor in the last 90 days, then retrieve each round entity and produce a markdown digest grouped by industry.
CRM Account Enrichment
Enrich CRM company records with Crunchbase firmographics and funding history at sync time. GET /entities/organizations/{entity_id} returns the canonical record for an org, and POST /searches/organizations resolves company name and domain to an entity. Useful for sales operations teams keeping Salesforce or HubSpot accounts current.
For each company domain in the CRM nightly sync, search organizations to resolve the entity ID and pull the full GET /entities/organizations/{entity_id} record into the CRM custom fields.
Founder and Executive Research
Research founders or executives by querying Crunchbase people records and joining them with their organization affiliations. POST /searches/people accepts role and organization filters, and GET /entities/people/{entity_id} returns the full profile. Useful for executive recruiting, journalism, and competitive research.
Search people with role 'Founder' at organizations in 'climate tech' and return the top 20 person entity records.
Agent-Driven Market Research via Jentic
AI agents that produce competitive briefs, deal sheets, or sourcing lists can call Crunchbase through Jentic without holding the user_key. The agent searches Jentic for the relevant intent, loads the schema, and runs the search or entity lookup with the key held in Jentic's vault. This keeps the Crunchbase subscription credential isolated from the agent's prompt context.
Use Jentic to search 'search crunchbase organizations', load POST /searches/organizations, and execute it with the user's industry and funding-stage filters.
9 endpoints — jentic publishes the only available openapi specification for crunchbase api, keeping it validated and agent-ready.
METHOD
PATH
DESCRIPTION
/searches/organizations
Search organizations with structured filters
/searches/people
Search people across the dataset
/searches/funding_rounds
Search funding rounds
/searches/acquisitions
Search acquisitions
/autocompletes
Resolve autocomplete suggestions
/entities/organizations/{entity_id}
Get an organization entity
/entities/people/{entity_id}
Get a person entity
/entities/funding_rounds/{entity_id}
Get a funding round entity
/searches/organizations
Search organizations with structured filters
/searches/people
Search people across the dataset
/searches/funding_rounds
Search funding rounds
/searches/acquisitions
Search acquisitions
/autocompletes
Resolve autocomplete suggestions
/entities/organizations/{entity_id}
Get an organization entity
/entities/people/{entity_id}
Get a person entity
/entities/funding_rounds/{entity_id}
Get a funding round entity
What agents get from Jentic-routed access to this vendor.
Setup
Wiring Crunchbase by hand means learning its user_key query auth against api.crunchbase.com/api/v4 and building the search and retry plumbing for organizations, people, and funding rounds yourself. Through Jentic you install once, import the Crunchbase API from the API Directory, store the key once, and your agent calls it.
Permission scoping
Crunchbase drives its search endpoints from the request body while entity reads take an entity_id in the path (/entities/organizations/{entity_id}), so limit the agent to the operations it needs, such as searching organizations or fetching one entity. This API is read-only here, so the agent can only query what you allow it to query.
Credential isolation
Your Crunchbase user_key is stored once, encrypted, by your own Jentic One instance and appended as the user_key query parameter at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'search Crunchbase organizations' or 'fetch a funding round', and Jentic returns the matching operation with its input schema so the agent calls the right endpoint without browsing the data.crunchbase.com 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 publishes only descriptive documentation. Jentic generates and maintains this OpenAPI specification 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 Crunchbase API uses an API key passed as the user_key query parameter on every request. Through Jentic the user_key is held in the vault and appended to outbound requests so it never enters the agent's context.
Can I search funding rounds with the Crunchbase API?
Yes. POST /searches/funding_rounds accepts structured filters such as date range, investor, and round size, and GET /entities/funding_rounds/{entity_id} returns the full record for a specific round.
What are the rate limits for the Crunchbase API?
The OpenAPI spec does not declare explicit numeric limits. Limits are governed by your Crunchbase data licence - apply backoff on 429 responses and prefer paginated search calls over high-frequency entity lookups.
How do I enrich a CRM record through Jentic?
Run pip install jentic, then search Jentic for 'search crunchbase organizations', load the POST /searches/organizations schema, and execute it with the company name or domain. Pipe the resulting entity_id into GET /entities/organizations/{entity_id} for the full record.
Does the Crunchbase API support autocomplete?
Yes. GET /autocompletes accepts a query and returns matching organizations and people, suitable for typeahead pickers in CRM and prospecting tools.
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 restrict it to just the calls it needs, such as POST /searches/organizations or a single GET /entities/organizations/{entity_id} read. The Crunchbase API is read-only here, so the agent can only query the data you allow and cannot write or modify anything. You can grant search access to people, funding rounds, and acquisitions selectively or withhold it, keeping the user_key credential under your control.
Know of an official OpenAPI document? Contribute it →
For Agents
Search Crunchbase organizations, people, funding rounds, and acquisitions and retrieve full entity records to enrich CRM and prospecting workflows.
Use for: I want to find all Series B fintech companies funded in the last year, Search Crunchbase for people with a CTO role at SaaS startups, Retrieve the funding history of a specific Crunchbase organization, Find acquisitions by a specific acquirer over the last quarter
Not supported: Does not handle email enrichment, web traffic data, or technographics - use for Crunchbase organization, people, funding round, and acquisition data only.
Jentic publishes the only available OpenAPI specification for Crunchbase API, keeping it validated and agent-ready. Crunchbase is the canonical dataset of private companies, funding rounds, acquisitions, and people in the global startup ecosystem. The API exposes nine endpoints across search, autocomplete, and entity retrieval covering organizations, people, funding rounds, and acquisitions. Authentication uses an API key passed as the user_key query parameter against the https://api.crunchbase.com/api/v4 base URL.