a360-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| A360_API_KEY | No | API key for authentication (mutually exclusive with A360_PASSWORD) | |
| A360_PASSWORD | No | Password for authentication (mutually exclusive with A360_API_KEY) | |
| A360_USERNAME | Yes | Service account username | |
| A360_TOOL_PACKAGE | No | Tool package to enable (core, diagnose, full, etc.) | core |
| A360_CONTROL_ROOM_URL | Yes | Control Room base URL (e.g. https://cr.example.com) |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_bot_actionsA | List a bot's action nodes (parsed), not the raw JSON. |
| get_executionB | Fetch one execution's status, message and error detail. |
| list_executionsC | Search execution history via POST /v3/activity/list. |
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 3 tools
Each tool has a clear, distinct purpose: get_bot_actions retrieves bot action definitions, get_execution fetches a single execution's details, and list_executions searches execution history. There is no ambiguity or overlap between these operations.
All tool names follow a consistent verb_noun pattern, using get_ for singular resources and list_ for collections. The naming is predictable and adheres to standard conventions.
With only 3 tools, the server is at the lower end of the typical range, but each tool covers a distinct aspect of the domain (bot actions and executions). It feels slightly thin but is still reasonable for a focused utility.
The server lacks essential operations such as listing bots (making it impossible to discover bot IDs for get_bot_actions) and does not support execution lifecycle actions like starting or canceling executions. This creates significant gaps for agents trying to perform broader workflows.