canonical: https://jentic.com/apis/citability.ai/citability

# Citability API

Jentic publishes the only available OpenAPI specification for Citability API, keeping it validated and agent-ready. Citability is a domain intelligence platform that scores AI visibility, citation readiness, and agentic commerce readiness across more than 600 million domains. The API exposes around 200 endpoints for scanning a domain, scoring it against the AI Discovery Protocol (ADP), validating llms.txt and Schema.org markup, detecting MCP endpoints, and pulling enrichment data such as verticals, leads, and directory entries. It is designed for SEO and AI-readiness teams that need programmatic access to citation and discoverability signals.

## For AI agents

Score, scan, and enrich any domain for AI citation readiness, llms.txt compliance, MCP endpoint detection, and agentic commerce signals across roughly 200 endpoints.

## Scope

Does not handle web hosting, content publishing, or general SEO rank tracking - use for AI readiness scoring, ADP compliance scans, and Citability directory data only.

## Capabilities

- Score a single domain for AI discovery and citation readiness via `/api/v1/domain/{domain}`
- Run batch scoring across many domains in one call with POST `/api/v1/domain/batch`
- Scan a domain for ADP (AI Discovery Protocol) compliance including llms.txt and Schema.org
- Run a unified 3-pillar scan combining visibility, citation, and agentic commerce signals
- Pull filtered leads and verticals from the enrichment dataset for go-to-market segmentation
- Browse and search the public Citability directory of scored domains

## Use cases

### Bulk AI-readiness audit for a website portfolio

An SEO or AI-readiness team submits up to thousands of portfolio domains via POST `/api/v1/scan/batch`, gets back ADP scores covering llms.txt, Schema.org, and content extractability, and rolls the results into a quarterly readiness report. The unified scan endpoint adds a 3-pillar score combining visibility, citation, and agentic commerce.

Example prompt: Call POST `/api/v1/scan/batch` with an array of 50 domains, then aggregate the ADP scores by category and identify the bottom-quartile domains.

### Sales intelligence for AI-native tooling

A vendor selling AI-readiness products pulls filtered leads from `/api/v1/leads`, segments them by vertical via `/api/v1/leads/verticals`, and exports a target list as CSV. Each lead includes Citability's priority and ADP scores so the sales team can lead with a specific gap (no llms.txt, missing Schema.org, no MCP endpoint).

Example prompt: Call GET `/api/v1/leads` with a vertical filter for 'e-commerce' and a max ADP score of 40, then export the result via GET `/api/v1/leads/export.`

### MCP endpoint discovery across a directory

An agent platform team uses Citability's directory and scan endpoints to discover which domains expose MCP endpoints. Domains in the directory are scored for agentic commerce readiness, so the team can prioritise integration partners that already speak MCP rather than cold-emailing every vendor.

Example prompt: Call GET `/api/v1/directory/search` with a query for 'mcp' and filter the result to entries where the agentic commerce score is above 70.

### AI agent-driven domain enrichment via Jentic

An agent loaded with the Citability tool through Jentic searches by intent ('score a domain for AI readiness'), receives the schema for `/api/v1/domain/{domain}`, and enriches a CRM record with the citation score, ADP gaps, and recommended fixes. This turns Citability into a callable tool inside any agent workflow.

Example prompt: Through Jentic, search 'score a domain for AI readiness', load the schema for `/api/v1/domain/{domain}`, and call it for the prospect's domain.

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| GET | `/api/v1/domain/{domain}` | Get the AI opportunity score for a domain |
| POST | `/api/v1/domain/batch` | Score multiple domains in a single call |
| GET | `/api/v1/scan/{domain}` | Scan a domain for ADP compliance |
| POST | `/api/v1/scan/{domain}/unified` | Run a unified 3-pillar scan |
| GET | `/api/v1/leads` | Get filtered leads |
| GET | `/api/v1/leads/export` | Export leads as CSV |
| GET | `/api/v1/classify/{domain}` | Classify a domain by vertical |
| GET | `/api/v1/directory/search` | Search the Citability directory |

## Key resources

- **Domain** — Score, priority, and combined readiness data for a single domain or a batch of domains
- **Scan** — ADP compliance scans (llms.txt, Schema.org, MCP detection, content extractability) for one or many domains
- **Leads** — Filtered prospect lists with enrichment data and CSV export
- **Classify** — Vertical classification for domains, with caching controls
- **Directory** — Searchable directory of scored domains with statistics

## Why Jentic

- **Setup:** Wiring the Citability API by hand means calling its domain scoring, ADP compliance scan, and directory endpoints and handling the batch and unified-scan responses yourself, even though it needs no credential. Through Jentic you install once, import the Citability API from the API Directory, and your agent calls it.
- **Permission scoping:** Citability puts the domain in the URL path (`/domain/{domain}`, `/scan/{domain}`), and its writes are batch and scan submissions, so scope the agent to the operations it needs, such as scoring a domain and running a compliance scan. You choose the operations it may call, so lead export or directory search is included only if you add it.
- **Credential handling:** Citability requires no credential, so there is nothing to store; if you later put it behind your own gateway key, Jentic One stores that key encrypted and injects it at execution time so it never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'score a domain for AI readiness' or 'run an ADP compliance scan', and Jentic returns the matching Citability operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Clearbit API** — Domain enrichment API focused on firmographics rather than AI-readiness signals
- **FullContact API** — Person and company enrichment that pairs well with Citability domain scores
- **HubSpot CRM Objects** — CRM destination for Citability scores and lead exports

## FAQ

### Why is there no official OpenAPI spec for Citability API?

Citability does not publish an OpenAPI specification on its public site. Jentic generates and maintains this spec so that AI agents and developers can call Citability 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 Citability API use?

The OpenAPI spec does not declare a security scheme on the public endpoints; Citability typically gates production usage behind an account-level token issued from the dashboard at citability.ai. Through Jentic, any required token is held in your encrypted Jentic One instance and injected at execution time.

### Can I score a single domain for AI readiness?

Yes. GET `/api/v1/domain/{domain}` returns the AI opportunity score for one domain, and GET `/api/v1/scan/{domain}` returns the ADP compliance breakdown (llms.txt, Schema.org, MCP detection, content extractability) for the same domain.

### Can I score many domains in a single call?

Yes. POST `/api/v1/domain/batch` accepts an array of domains and returns scores for each, and POST `/api/v1/scan/batch` does the same for full ADP scans. This is the recommended way to audit a portfolio of websites.

### What are the rate limits for the Citability API?

The OpenAPI spec does not declare rate limits. Citability enforces them at the account level, so production integrations should add retry-with-backoff on 429 responses and prefer the batch endpoints over single-domain loops.

### How do I score a domain from an AI agent through Jentic?

Run pip install jentic, then have the agent search 'score a domain for AI readiness', load the schema for GET `/api/v1/domain/{domain}`, and execute the call. Jentic resolves any required credential and returns the JSON score directly to the agent.

### Can I limit what my agent is allowed to do with the Citability API?

Yes. Because you run Jentic One yourself, your own rules decide which Citability operations the agent may call, so you can allow it to score a domain with GET `/api/v1/domain/{domain}` and run an ADP compliance scan with GET `/api/v1/scan/{domain}` while withholding everything else. Citability puts the domain in the URL path and its writes are batch and scan submissions, so you can grant POST `/api/v1/domain/batch` and POST `/api/v1/scan/batch` only when a portfolio audit needs them. Lead export via GET `/api/v1/leads/export` and directory search via GET `/api/v1/directory/search` are included only if you add them to the agent's permitted set. Citability needs no credential, but if you later place it behind your own gateway key, that key stays with your self-hosted instance and is injected at execution time rather than exposed to the agent.