Clay Public API
58
AI ReadinessFoundational (C+)58/100
Official vendor OpenAPI document · agent-readyData EnrichmentContact EnrichmentapiKey13 EndpointsREST
For Agents
Run Clay enrichment routines, start batch runs and read their results, search for people and companies, and query Clay tables. Returns enrichment and search results for an agent to use.
Use for: Run a Clay enrichment routine for a lead, Start a batch routine run over a list of records, Retrieve the results of a completed routine run, Create a filters-mode search for companies in a segment
Not supported: Does not handle table row editing, workspace administration, or billing. Use for running enrichment routines, searching, and querying tables only.
The Clay Public API runs data enrichment routines, starts batch runs and retrieves their results, and searches for people and companies in filters mode or query mode. It also queries Clay tables for stored records and reads the authenticated account. Agents can enrich leads and search for prospects programmatically without building each workflow in the Clay interface.
Install Jentic One Beta
Connect the Clay Public API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Clay Public 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.
1
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%2Fclay.com%2Fclay" | sh2
Step 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%2Fclay.com%2Fclay" | 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.
Capabilities
What an agent can do with Clay Public API.
Run a Clay routine to enrich a record
Start a batch routine run and retrieve its results
Create and run a filters-mode search for people or companies
Create and run a query-mode search
Query a Clay table for stored records
Read the authenticated account details
Use Cases
Patterns agents use Clay Public API for, with concrete tasks.
★ Agent-Driven Lead Enrichment
An AI agent enriches a lead by running a Clay routine and reading the returned data before writing it into a CRM. It passes the record to the routine, waits for the run to finish, and retrieves the enriched result. This lets an agent fill in missing contact and company details as part of a pipeline without opening Clay.
Run an enrichment routine for a lead, wait for the run to complete, and retrieve the enriched contact and company data
Batch Data Enrichment
Teams enrich a list of records in one run by starting a batch routine and collecting the results when it finishes. The API starts a batch run, provides an upload path for the input, and returns the run's results. This suits a scheduled job that refreshes a segment of contacts on a cadence.
Start a batch routine run for a list of records, then retrieve the results once the run reports complete
People and Company Search
An agent finds prospects by building a filters-mode or query-mode search and reading the matches. It can inspect the available fields, create the search, and run it to get results. This turns prospecting into an automated search an agent runs against Clay's data.
Create a filters-mode search for a target segment, run it, and return the matching people or companies
Key Endpoints
13 endpoints — the clay public api runs data enrichment routines, starts batch runs and retrieves their results, and searches for people and companies in filters mode or query mode.
METHOD
PATH
DESCRIPTION
GET
/me
Read the authenticated account
POST
/routines/{routine_id}/run
Run a routine
POST
/routines/{routine_id}/run-batch/start
Start a batch routine run
GET
/routines/run/{routine_run_id}/results
Get routine run results
POST
/search/filters-mode
Create a filters-mode search
POST
/search/filters-mode/{search_id}/run
Run a filters-mode search
POST
/search/query-mode
Create a query-mode search
POST
/tables/query
Query a Clay table
GET
/me
Read the authenticated account
POST
/routines/{routine_id}/run
Run a routine
POST
/routines/{routine_id}/run-batch/start
Start a batch routine run
GET
/routines/run/{routine_run_id}/results
Get routine run results
POST
/search/filters-mode
Create a filters-mode search
POST
/search/filters-mode/{search_id}/run
Run a filters-mode search
POST
/search/query-mode
Create a query-mode search
POST
/tables/query
Query a Clay table
Jentic AI Readiness Score
This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.
C
Clay Public API
- Foundational (C+)58/100
87
Foundational Compliance63
Developer Experience & Jentic Compatibility36
AI-Readiness & Agent Experience94
Agent Usability50
Security74
AI DiscoverabilityPowered by JenticScoring Framework 1.0.0 | Scoring Engine 0.4.2
Show dimension breakdown
87
Foundational Compliance
Base layer of spec validity and structural soundness.
Grade: ASignals: 4
98%
Lint Results
Aggregated quality score from linter diagnostics, weighted by severity.
100%
Resolution Completeness
Percentage of `$ref` references that resolve successfully.
100%
Specification Validity
Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).
50%
Structural Integrity
Structural correctness score based on schema issues using logarithmic dampening.
63
Developer Experience & Jentic Compatibility
Clarity, completeness, and ingestion readiness for developers and tooling.
Grade: B-Signals: 4
0%
Example Density
How richly the API is illustrated with examples.
100%
Example Validity
Percentage of examples that conform to their schemas.
50%
Response Coverage
Percentage of operations with complete response definitions (success, client error, server error).
100%
Tooling Readiness
Health of API ingestion, bundling, and resolution within Jentic pipelines.
36
AI-Readiness & Agent Experience
Semantic breadth, depth, and agent comprehension for AI systems.
Grade: FSignals: 4
20%
Description Coverage
Coverage of descriptions across API elements.
0%
Error Standardization
Coverage of RFC 9457 Problem Details for error responses.
77%
OperationId Quality
Coverage, uniqueness, and casing consistency of operationIds for AI inference.
48%
Summary Coverage
Coverage of summaries across operations/tags/info.
94
Agent Usability
Functional utility, complexity comfort, and AI orchestration readiness.
Grade: A+Signals: 1
94%
Complexity Comfort
Agent comfort level based on API operational and structural complexity.
50
Security
Trust, risk posture, and security compliance.
Grade: C-Signals: 1
50%
Authentication Strength
Average quality of security schemes based on authentication method strength (weakest link for OAuth2).
74
AI Discoverability
Findability, semantic richness, and reasoning readiness.
Grade: A-Signals: 1
74%
Descriptive Richness
Clarity and depth of descriptions across API elements.
Score it yourself
Every API in the directory is allowlisted, so you can re-score it with no key required.
npx @jentic/api-scorecard-cli score <openapi-url>Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Clay Public API by hand means provisioning a key, learning the routine and search models, and orchestrating batch runs and result polling yourself. Through Jentic you install once, import Clay from the API Directory, store the key once, and your agent runs routines and searches.
Permission scoping
Clay puts routine and search identifiers in the URL path, so a rule can bound your agent to a single routine or search. You can also scope by operation, allowing searches and reads while withholding routine runs, and every call the agent makes is logged.
Credential isolation
Your Clay API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'run an enrichment routine' or 'search for companies', and Jentic returns the matching Clay operation with its input schema so the agent calls the right endpoint without reading the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Clay Public API through Jentic.
What authentication does the Clay Public API use?
The Clay Public API authenticates with an API key sent in the clay-api-key request header per its OpenAPI spec, generated from your Clay workspace. Through Jentic the key is held encrypted by your own Jentic One instance and attached at call time, so it never reaches the agent's context.
Can I enrich a batch of records with the Clay Public API?
Yes. The API starts a batch routine run, provides a path to upload the input, and returns the run's results when it finishes. An agent can enrich a whole list in one run and collect the output.
What are the rate limits for the Clay Public API?
The OpenAPI spec does not specify rate limits. Check the Clay developer documentation at https://developers.clay.com for current limits and usage guidance.
Can I limit what my agent is allowed to do with the Clay Public API?
Yes. Because a routine or search identifier sits in the URL path, a rule can bound your agent to a single routine or search, and you can also scope by operation to allow searches and reads while withholding routine runs. Every call the agent makes is logged.
How do I enrich a lead in Clay through Jentic?
Search Jentic for 'run an enrichment routine' or 'search for companies', add the Clay Public API from the directory, and store your key once. Your agent then runs the routine and retrieves the enriched data. To run it on your own infrastructure, install Jentic One from its GitHub repo.
Is there a Clay MCP server?
You don't need an MCP server to give your agent the Clay Public API. Jentic connects it directly from the API Directory: import it, store your key once, and your agent runs routines and searches. Operations are discovered on demand, so no extra server's tool definitions sit in the agent's context.
GET STARTED