Clay integration for AI agents.
Clay integration for AI agents with secure authentication and server-side credential injection. Open Connector runs the OAuth, seals the token in an encrypted vault, and serves Clay tools to your agent over MCP or a typed API — credentials injected server-side, every call audited, nothing leaving your infrastructure. Open source (AGPL-3.0) and self-hostable.
Real Clay actions, managed and audited.
Your user connects Clay once; your agent can then use Clay to run GTM routines, batch enrichments, structured searches, and table queries — scoped to the OAuth permissions you grant and the tool allowlist you configure. Every action is least-privilege and written to a tamper-evident audit trail.
- 1
Your user grants Clay access once (OAuth) — the token lands in the vault.
- 2
Your agent calls a tool over MCP or the typed API; Open Connector injects the credential server-side.
- 3
Every routed call appends a hash-chained audit record — nothing leaves your infra.
Supported Clay tools.
10 tools are generated from the published Clay catalog. Descriptions are plain text; each action remains subject to its configured authentication and tool allowlist.
Showing 10 tools. All published catalog entries are included in this page's server-rendered HTML.
- Create a search from structured filters
- Starts a new Clay search from a source type and structured filter fields.
- search
- List the filter fields available for a search source type
- Returns every filter field accepted by POST /search/filters-mode for the given source type, including each field's type, description, allowed values, and usage guidance. Call this before creating a search to build valid filters.
- search
- Get the authenticated user
- Returns the Clay user and workspace associated with the API key.
- me
- Fetch progress and results for a batch run
- Returns current status and results for an asynchronous batch routine run.
- routines
- Fetch progress and results for a routine run
- Returns current status and paginated results for an asynchronous routine run.
- routines
- Run a structured query across one or more tables
- Runs a structured query against Clay table data and returns records with field metadata.
- tables
- Run the search iterator and return the next page of results
- Returns the next page of records for an existing filter-mode search.
- search
- Execute a routine against 1-100 items
- Starts an asynchronous routine run for up to 100 input items.
- routines
- Issue a presigned PUT URL for uploading a batch input JSONL
- Creates a presigned URL for uploading a JSONL file used by a batch routine run.
- routines
- Start an async routine run-batch over an uploaded JSONL file
- Starts an asynchronous batch routine run over a previously uploaded JSONL file.
- routines
Clay integration, answered
- How do AI agents use Clay through Open Connector?
- Your user connects Clay once with one of its cataloged authentication methods. Open Connector stores the credential in an encrypted vault and exposes Clay tools to your agent over MCP or a typed API, with credentials injected server-side on each call.
- Is this a Clay MCP server?
- Yes. Open Connector can serve Clay as a named MCP server with a scoped allowlist and a per-user connection URL, so any MCP client can call Clay actions with credentials injected server-side.
- Where do Clay credentials live?
- In your own infrastructure. Open Connector keeps credentials in its own vault and injects them at call time, so they never leave your environment.
Give your agents Clay — keep the keys.
Open source, self-hostable, with Clay credentials that never leave your infrastructure. Run it from source today.