Skip to main content
Glama

check_mcp_server_security

Read-only

Run a read-only security check on a remote MCP server to detect HTTPS, authentication, CORS, HSTS, version-leak, and risky tool-configuration issues without calling tools.

Instructions

Run a read-only security check of a remote MCP server (Streamable HTTP).

Checks HTTPS and the certificate, whether login is required, OAuth discovery and PKCE support, CORS, HSTS and version leaks. For open servers it also lists tools (it never calls them) and flags risky tools without safety hints, tool-poisoning phrases and missing Origin checks. Only check servers you own or are allowed to test. Example input: "https://mcp.example.com/mcp".

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "server_url": "<server_url>"
    },
    "name": "check_mcp_server_security"
  }
}

Input Schema

NameRequiredDescriptionDefault
server_urlYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Goes far beyond the readOnlyHint/openWorldHint annotations by enumerating exactly what is inspected (HTTPS/cert, login requirement, OAuth discovery, PKCE, CORS, HSTS, version leaks), stating that tools are listed but never called, and disclosing the authorization expectation. That is a detailed behavioral contract an agent can rely on before invoking.

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?

Front-loaded with the core action, then the checklist, then the safety caveat and example. No filler; each clause carries distinct information.

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

Completeness4/5

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

For a single-parameter tool with no output schema, the description covers what is examined, the non-destructive guarantee, and the authorization prerequisite. The only gap is that it doesn't hint at the structure of the report returned, which matters slightly more given the absence of an output schema.

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

Parameters4/5

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

Schema coverage is 0% for the single server_url parameter, so the description carries the burden; the example input 'https://mcp.example.com/mcp' implicitly conveys that a full MCP endpoint URL (including path) is expected rather than a bare host. It falls short of explicitly describing the parameter's format or validation rules.

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?

States a specific verb and resource ('Run a read-only security check of a remote MCP server (Streamable HTTP)') with clear scope. The target domain is unmistakably different from the sibling check_llms_txt without needing to name it.

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?

Gives a clear operational constraint ('Only check servers you own or are allowed to test') and an example invocation, which sets the context for when to reach for it. It stops short of explicitly stating when not to use it or naming an alternative, so it doesn't reach the top band.

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

Deploy Server

Other Tools