AdaptOrch MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ADAPTORCH_CONTROL_PLANE_TOKEN | No | AdaptOrch API key (ado_...). Optional forintrospection; required for tool calls. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| adaptorch_runC | Submit a task payload to AdaptOrch control-plane and optionally wait. |
| adaptorch_get_runC | Get run summary by run_id. |
| adaptorch_get_artifactsC | Get run artifacts by run_id. |
| adaptorch_list_runsB | List recent AdaptOrch control-plane runs, newest first. |
| adaptorch_cancel_runB | Request cancellation of an in-flight run by run_id. |
| adaptorch_server_metricsA | Return redacted MCP tool-call counters and latency percentiles. |
| adaptorch_capabilitiesA | Return supported synthesis modes, connectors, and server capabilities. |
| adaptorch_usageA | Return the calling tenant's current usage window: plan level, period, used, limit, remaining, and usage percentage. The tenant is resolved server-side from the configured API key. |
| adaptorch_plan_catalogA | Return the current AdaptOrch hosted cloud plan catalog: Starter $0, Pro $39, Team $149. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Each tool has a clearly distinct purpose: run submission, run retrieval, artifacts, listing, cancellation, metrics, capabilities, usage, and plan catalog. There is no meaningful overlap between run-management tools and account/capability tools.
All tools use the same adaptorch_ prefix and snake_case, making the surface predictable. Most names are noun-oriented rather than verb_noun, but the pattern is still consistent and readable.
Nine tools is well-scoped for a control-plane MCP server, covering run operations plus account/capability metadata without feeling bloated or thin.
The core run lifecycle is covered: submit, list, get, cancel, and retrieve artifacts, along with usage, capabilities, metrics, and plan catalog. Minor gaps may exist around richer run logs/events or retry behavior, but common workflows are well supported.