MCPSentinel
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCPSENTINEL_MCP_JUDGE | No | Optional judge setting for MCP-native scans: 'heuristic' (default), 'openai', or 'auto'. | |
| MCPSENTINEL_RULES_PATH | No | Optional path to a custom rules JSON file. | |
| MCPSENTINEL_POLICY_PATH | No | Optional path to a policy JSON file. | |
| MCPSENTINEL_ALLOWED_HOSTS | Yes | Comma-separated allowlist of hosts (or host:port) that the MCP server is permitted to scan. HTTP targets not in this list are rejected. | |
| MCPSENTINEL_MCP_JUDGE_MODEL | No | Optional model name for the OpenAI judge, e.g., 'gpt-4o-mini'. | |
| MCPSENTINEL_MCP_BASELINE_DIR | No | Optional directory for baseline and judge cache storage. |
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
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_mcp_serverA | Enumerate metadata from an operator-allowlisted HTTP MCP server and return static, semantic, and baseline security findings. Dynamic tool invocation is never performed and baselines are never approved from this MCP-native interface. |
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 1 tool
With only a single tool, there is no possibility of confusion or misselection; scan_mcp_server has one unambiguous purpose.
The lone name follows a clean verb_noun convention (scan_mcp_server), establishing a predictable pattern that any future tools could follow.
A single tool is thin even for a narrow security-scanning scope; there is no companion tool for listing targets, retrieving past results, or managing baselines.
It covers enumeration and static/semantic/baseline scanning, but the description itself admits baseline approval is unavailable and there is no way to list servers or fetch prior results, leaving notable gaps.