AI Intervention Agent
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| interactive_feedbackA | Ask the human user for interactive feedback through the Web UI. Use this tool whenever you need a human decision, clarification, confirmation, plan approval, design review, or final sign-off before continuing — especially when the next step has multiple valid approaches, irreversible side effects, or significant trade-offs. Behavior:
Cross-tool compatibility:
Note: this function is not the MCP registration site itself; R25.2: 函数体首行 R44 FastMCP 最佳实践: |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Server Info | Self-information for ai-intervention-agent MCP server. Returns version, transport, runtime details, middleware chain, accumulated error stats, Web UI runtime status, and task-queue snapshot as JSON. |
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap. The tool's purpose of collecting interactive human feedback is clearly defined and easily distinguishable from any potential future tools.
The single tool name 'interactive_feedback' follows a clear, descriptive snake_case convention. Consistency is trivially maintained since there are no other tools to compare, and the name accurately reflects its function.
A single tool feels thin for an 'AI Intervention Agent', even if the scope is narrow. It is borderline on the lower end of the tool-count spectrum, but the tool is non-trivial and well-defined, so it is not severely inappropriate.
For its stated purpose of collecting interactive feedback from a human user, the tool covers the full lifecycle: requesting input, providing options, handling timeouts/retries, and returning results. There are no obvious missing operations within this narrow domain.