mcp-agent-enterprise-guard
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 |
|---|---|
| score_agent_reliability_toolA | Compute overall reliability score (0-100) from tool-call logs. Each log entry should contain: tool_name, success (bool), latency_ms (number), is_error (bool), content (string or null). |
| detect_silent_failures_toolB | Flag tool calls that returned empty or null content without an error flag. |
| evaluate_permission_toolC | Evaluate whether an agent action is allowed under the given policy rules. Returns decision (allow/deny), matched rules, and risk score. |
| generate_audit_report_toolA | Generate a markdown governance/audit report from logs (and optional pre-computed scores). |
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 4 tools
Each tool has a distinct purpose: detecting silent failures, scoring reliability, evaluating permissions, and generating audit reports. There is no overlap or ambiguity between them.
All tool names follow a consistent verb_noun_tool pattern (detect_silent_failures_tool, score_agent_reliability_tool, etc.), making the API predictable and easy to navigate.
With 4 tools, the server is well-scoped for its enterprise guard purpose. Each tool serves a distinct function without unnecessary bloat or a thin set.
The tools cover the full lifecycle of governance and monitoring: detection, scoring, permission evaluation, and reporting. No obvious gaps exist for the server's stated purpose.