> ## Documentation Index
> Fetch the complete documentation index at: https://veryfront.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Agents API

> How agent definitions, capabilities, and project installations fit together.

The Agents API manages the definitions that give agents their behavior. An agent combines instructions with the tools, skills, prompts, and resources it can use.

## Definitions and executions

An agent definition belongs to a project. A run executes that definition with a particular input and runtime target. Editing a definition and starting a run are separate operations; the [Execution API](/docs/cloud/apis/execution) manages runs and their progress.

Definitions stored in project source can have different versions on different branches or in deployed environments. The selected source determines which definition a read or edit addresses.

## Capabilities

Prompts provide reusable instructions. Tools expose callable actions, skills package reusable behavior, and resource documents provide project configuration. An agent's capabilities describe what is available to that agent.

Tools from connected services also depend on the [Integrations API](/docs/cloud/apis/integrations) and the caller's access to a connection. Attaching a tool to an agent does not grant access to the external account.

A support agent might combine triage instructions, a ticket-reading tool, and knowledge lookup. The definition describes those capabilities; each incoming question produces a separate run with its own input and result.

## Discovery and installation

The accessible-agent collection lists agents across projects you can access. The template catalog describes agents that can be forked or installed.

A public catalog entry must be installed or forked into a project before it can run. Use the returned `actions` to determine what the caller can do.

| Catalog field | Use |
| - | - |
| `kind` | Distinguishes `template_agent` from `installable_agent`. |
| `template_project` | Identifies the project and source path for a template fork. |
| `installability` | Reports whether an installable agent is installed, available to install, or unavailable in the project context. |
| `card` | Supplies display metadata. It does not grant execution access. |

Project lists identify runnable definitions with `source_project_agent` or `installed_project_agent`. Check `can_run` and `runtime_readiness`; readiness does not replace authorization.

Use a run's `run_snapshot` to identify the agent definition, runtime target, and requester selected for that execution.

The [Evaluations API](/docs/cloud/apis/evaluations) tests agent behavior against datasets and metrics.

## Get started

[Create an agent](/docs/cloud/agents) shows how to save and inspect a definition before starting work.

## API references

* [REST endpoints](/docs/cloud/rest/apis/agents-api)
* [GraphQL queries and mutations](/docs/cloud/graphql/apis/agents)
* [MCP tools](/docs/cloud/mcp/apis/agents)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.