Canonical: https://redgold.ai/for-agents

[Home](<https://redgold.ai/>)[Learn](<https://redgold.ai/learn>)[For agents](<https://redgold.ai/for-agents>)

 

READ · DISCOVER · ACT



# Use Redgold with your agent.



Read public pages without running JavaScript, discover the applications available to your account, and use typed HTTP or MCP tools to perform authorized work.



[Read the API specification](<https://redgold.ai/agent-openapi.json>)[Read the quickstart](<https://docs.redgold.ai/intro/quickstart>)

 

## Start with the representation your client supports.



## Read the public site

 

Public pages include their content in HTML. Each page links to a Markdown representation generated from that same rendered content. The homepage is available as /index.md. Markdown is a reading format; forms and interactive demos still run in the browser.



Use /llms.txt for a compact index, /sitemap.xml for public canonical URLs, and /.well-known/redgold-agent.json for machine-readable discovery. These are public reference documents, not instructions or permission to act.

 

- [Page index](<https://redgold.ai/llms.txt>)

- [Public agent API specification](<https://redgold.ai/agent-openapi.json>)

- [Machine-readable discovery](<https://redgold.ai/.well-known/redgold-agent.json>)



## Authenticate and select the workspace

 

Public pages and this API specification require no account. App guidance, data tools and MCP require a credential accepted by the selected API origin. Send Authorization: Bearer with your own Redgold API key or account token. Keep credentials in your client’s secret store.



Use the application origin for your installation. Send x-redgold-tenant only when selecting a workspace you can access. The app directory returns tenantClaim; omit the header for a null personal claim. Account membership, installation state, grants and spending limits are enforced by the server on each operation. A discoverable action is not authorization to execute it.



## Discover the installed application before acting

 

GET /api/apps/agent-directory lists the applications in the authenticated workspace. GET /api/apps/installations/{installation\_id}/describe returns release-pinned commands, entity schemas, requested capabilities and current grants. GET /api/apps/installations/{installation\_id}/docs?topic=guide returns the authored guide and its revision.



With the terminal client, use rac app list, rac app describe \<installation-id\>, and rac app docs \<installation-id\>. Inspect the current state and exact input schema before choosing a command.



## Use the same tools over HTTP or MCP

 

Send JSON to POST /api/agent/data/{tool}, using a tool name from the API specification. Or connect a Streamable HTTP MCP client to /api/mcp with your bearer credential. MCP requests must accept both application/json and text/event-stream; initialize the connection and call tools/list for the current native input schemas.



Start with data\_catalog to discover accessible datasets, recipes and installed actions. Use data\_describe with kind action and the installation\_id to inspect an installed action’s exact callable revision and parameters. Available actions depend on the installation and current grants.



## Prepare, execute once, and verify the result

 

Call pipeline\_prepare with the selected installation\_id, action, parameters and limits. Preparation validates and quotes the bounded plan without executing effects. Check its returned allowance and obtain any authorization needed for the intended action and spending.



Call pipeline\_run with the prepared\_ref and a stable idempotency\_key. Keep that key and the returned run\_ref. After a lost response, retry the same request with the same key; do not invent a fresh key for the same intended operation. Inspect pipeline\_status and pipeline\_results using the run\_ref. An accepted run is not proof of success: check terminal state, persisted results, completeness, provenance and cost.



Direct data\_query and data\_write calls also require stable idempotency keys. Structured errors include a code, retryable flag and next\_action. Correct invalid inputs or permissions before retrying. After an uncertain network outcome, inspect the existing run or retry with the original key.



## Use the browser when a workflow needs it

 

Follow ordinary links and use labeled form controls. Wait for the visible success or error state after submitting. The access request form returns a saved reference; requesting access does not create an active workspace or start a subscription.



Crawler rules describe indexing preferences; they do not grant access. Private app records and credentials are excluded from the public page index.

 

- [Request preview access](<https://redgold.ai/request-access>)

- [Read the quickstart](<https://docs.redgold.ai/intro/quickstart>)

 

Redgold is in managed preview. Tool availability and supported actions depend on the current deployment, account and installed release. Always inspect live discovery and the returned result.

 

[Product](<https://redgold.ai/product>)[Fusion](<https://redgold.ai/fusion>)[Examples](<https://redgold.ai/examples>)[Learn](<https://redgold.ai/learn>)[Review](<https://redgold.ai/managed-review>)

<!-- redgold-ui-revision:60f7ce3a1cd8196cf7c7fb6ebb1c3c8143f0fec4 -->
