> For the complete documentation index, see [llms.txt](https://docs.autommate.com/userguide/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.autommate.com/userguide/mcp-and-ai-reference.md).

# MCP and AI reference

Tool arguments, response examples, execution contracts and guidance for AI consumers.

Retrieve exact tool parameters, supported operations, run states and response limits. On 21 October 2026, the reviewed connection advertised 71 tools, including authoring, services, deployments and native application configuration. This is a dated connection inventory, not a build-wide availability or runtime certification. Use the active tool schemas and the capability guide before acting.

## Build a service from verified context

* [Build a service with an AI assistant](https://docs.autommate.com/userguide/mcp-and-ai-reference/structured-service-authoring) — outcome, native components, Govern/Execute/Prove and a controlled lifecycle.
* [Resolve deployment inputs](https://docs.autommate.com/userguide/mcp-and-ai-reference/deployment-input-resolution) — reuse valid context, Engage payloads and earlier Work Item outputs; ask only for unresolved decisions.
* [Discover native apps, triggers and Data Manager](https://docs.autommate.com/userguide/mcp-and-ai-reference/native-app-trigger-and-data-discovery) — find the installed component and its exact contract before building a custom alternative.

### Choose your workflow

| Task                                      | Reference                                                                                                                                                  |
| ----------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Check what this connection can do         | [Capabilities and version scope](/userguide/mcp-and-ai-reference/capabilities-and-version-scope.md)                                                        |
| Read one exact tool contract              | [MCP tool reference](/userguide/mcp-and-ai-reference/tools.md)                                                                                             |
| Create, test and improve an automation    | [Build with an AI assistant](/userguide/mcp-and-ai-reference/build-with-an-ai-assistant.md) — use only authoring tools available on the active connection. |
| Implement a concrete scenario             | [Use cases and examples](/userguide/mcp-and-ai-reference/use-cases-and-examples.md) — existing-flow walkthroughs and clearly labelled design recipes.      |
| Make the references available to an agent | [Read documentation from an AI client](/userguide/mcp-and-ai-reference/read-documentation-from-an-ai-client.md)                                            |

* [For AI agents: read this first](/userguide/mcp-and-ai-reference/for-ai-agents-read-this-first.md)
* [MCP: connect an AI assistant to Autom Mate](/userguide/mcp-and-ai-reference/connect-an-ai-client-with-mcp.md)
* [Discovery tool contracts](/userguide/mcp-and-ai-reference/discovery-tool-contracts.md)
* [Inspection tool contracts](/userguide/mcp-and-ai-reference/inspection-tool-contracts.md)
* [Run an existing Hyperflow through MCP](/userguide/mcp-and-ai-reference/run-an-existing-autom-through-mcp.md)
* [Track run status and verify results](/userguide/mcp-and-ai-reference/track-run-status-and-verify-results.md)
* [Agent behavior: errors, missing information, and safe interpretation](/userguide/mcp-and-ai-reference/agent-behavior-errors-missing-information-and-safe-interpretation.md)

### Response examples

[Read MCP responses and tool errors](/userguide/mcp-and-ai-reference/read-mcp-responses-and-tool-errors.md) — Interpret successful reads, connector validation errors, and execution failures as distinct results.

[Read discovery results and pagination](/userguide/mcp-and-ai-reference/read-discovery-results-and-pagination.md) — Use returned identifiers, scope notes, and opaque cursors without assuming universal collection limits.

[Read Hyperflow and action input contracts](/userguide/mcp-and-ai-reference/read-hyperflow-and-action-input-contracts.md) — Read Hyperflow and action inputs, typed defaults and readable flow data before execution.

[Read run history and failure evidence](/userguide/mcp-and-ai-reference/read-run-history-and-failure-evidence.md) — Correlate runs by operation ID and interpret states, summary steps, errors, and bounded failure history.

[Read platform summaries schedules and agent health](/userguide/mcp-and-ai-reference/read-platform-summaries-schedules-and-agent-health.md) — Use summaries, running schedules and agent metrics to choose the next diagnostic read.