Skip to main content
Glama
pasihaka

MCP Sentinel

by pasihaka
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

audit_mcp_server

Read-only

Run automated synthetic checks on any remote MCP server to verify reachability, protocol compliance, JSON Schema validity, and exposed credentials, returning a detailed diagnostic report.

Instructions

Performs an automated synthetic health, protocol compliance, schema validation, and credential security audit on any remote Model Context Protocol (MCP) server. Use this tool when you need to comprehensively verify whether an external MCP server is reachable, measure round-trip latency, validate tool schemas against JSON Schema draft-07/2020-12 specifications, detect broken parameter definitions, and check for exposed API tokens or credentials. Returns a detailed markdown diagnostic report and structured status flags.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
authHeaderNoOptional HTTP Authorization header value (e.g. "Bearer <token>" or custom token) if the remote MCP server requires authentication.
endpointUrlYesThe public HTTP or SSE endpoint URL of the target remote MCP server to audit (e.g. "https://api.example.com/mcp" or "https://example.com/sse"). Must include http:// or https:// protocol scheme.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
contentYesFormatted diagnostic audit report and performance findings.
isErrorYesTrue if the remote MCP server experienced downtime, failed the JSON-RPC handshake, or exposed leaked credentials.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed13 schema fields changedv0.1.2
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / authHeader / description
      Previous value: -"Optional Authorization header value (e.g. \"Bearer sk_...\" or custom token) if the remote server requires authentication"New value: +"Optional HTTP Authorization header value (e.g. \"Bearer <token>\" or custom token) if the remote MCP server requires authentication."
    • addedInput schema / properties / authHeader / examples
      Added value: +[
+  "Bearer sample_token_abc123"
+]
    • changedInput schema / properties / endpointUrl / description
      Previous value: -"The remote MCP server HTTP or SSE URL to test (e.g. https://api.example.com/mcp or https://example.com/sse)"New value: +"The public HTTP or SSE endpoint URL of the target remote MCP server to audit (e.g. \"https://api.example.com/mcp\" or \"https://example.com/sse\"). Must include http:// or https:// protocol scheme."
    • addedInput schema / properties / endpointUrl / examples
      Added value: +[
+  "https://mcp-sentinel.pasihakamaki.workers.dev/mcp",
+  "https://mcp.deepwiki.com/sse"
+]
    • addedInput schema / properties / endpointUrl / format
      Added value: +"uri"
    • addedInput schema / properties / endpointUrl / minLength
      Added value: +1
    • addedOutput schema / additionalProperties
      Added value: +false
    • addedOutput schema / properties / content / description
      Added value: +"Formatted diagnostic audit report and performance findings."
    • changedOutput schema / properties / content / items / properties / text / description
      Previous value: -"Diagnostic audit report"New value: +"Diagnostic audit report with latency, tools count, schema validity, and security status."
    • changedOutput schema / properties / content / items / properties / type / description
      Previous value: -"Content MIME type"New value: +"MIME type of output content (text/plain)."
    • changedOutput schema / properties / isError / description
      Previous value: -"Whether the audit detected downtime or failure"New value: +"True if the remote MCP server experienced downtime, failed the JSON-RPC handshake, or exposed leaked credentials."
    • changedOutput schema / required
      Previous value: -[
-  "content"
-]New value: +[
+  "content",
+  "isError"
+]
  2. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, so the description only needs to add contextual behavior. It adds that the audit is 'synthetic', enumerates the checks performed, and discloses the return format (markdown diagnostic report and structured status flags). This is useful, non-redundant behavioral context with no annotation contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three dense sentences: purpose, trigger conditions, and output. It is front-loaded with the core action, avoids filler, and does not restate the input schema. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With only two fully documented parameters, an output schema, and readOnly annotations, the description covers the tool's scope, when to use it, and what it returns. An agent has enough information to select and invoke the tool correctly without missing critical context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and both parameters already have clear descriptions, formats, and examples. The tool description adds no parameter-specific semantics beyond what the schema provides, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Performs') and precise resource ('audit on any remote MCP server'), then enumerates the audit dimensions: health, protocol compliance, schema validation, and credential security. Although sibling tools are not named, the comprehensive-audit framing clearly distinguishes this tool from verify_mcp_protocol and get_monitor_badge.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description includes an explicit 'Use this tool when you need to...' clause listing concrete use cases such as checking reachability, latency, schema compliance, broken parameters, and exposed credentials. It lacks when-not-to-use guidance or explicit alternative routing, so it does not reach a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/pasihaka/mcp-sentinel'

If you have feedback or need assistance with the MCP directory API, please join our Discord server