Skip to main content
Glama
Sign In

tech-risk

by io.github.rezearcher
OverviewDiscussionsAdmin

scan_mcp_server

Security-audit a target MCP server for prompt-injection / tool-poisoning. Fetches the server's advertised tools and statically analyzes each for hidden instructions, data-exfiltration hints, dangerous capabilities, cross-tool shadowing, and invisible-unicode payloads (OWASP LLM01/LLM08). Returns findings + a 0-100 risk score + verdict (clear/review/block). Cost: $0.005 USDC per scan via x402 (GET /scan/mcp HTTP variant is $0.05).

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": {
      "url": "<url>"
    },
    "name": "scan_mcp_server"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYesTarget MCP server endpoint URL to audit

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden and does it well: it explains the fetch-then-static-analyze behavior, the return shape (findings, 0-100 risk score, verdict), and the payment requirement (x402, $0.005 USDC). It omits edge cases such as unreachable targets or timeouts, so it stops short of 5.

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

Conciseness4/5

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

Front-loads the purpose in the first sentence, then layers analysis categories, return values, and cost. Dense and mostly waste-free, though the parenthetical OWASP codes and dual-pricing clause add some load for marginal benefit.

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 no output schema, the description correctly compensates by explaining the return values (findings + risk score + verdict). The single input is documented in the schema, and the payment model is disclosed, leaving nothing an agent needs to invoke it correctly.

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?

Only one parameter (url) with 100% schema description coverage, so the schema already documents its meaning fully. The description adds no syntax, format, or constraint details beyond what the schema provides, warranting the baseline 3.

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 (Security-audit) and resource (target MCP server) with a scope enumeration: prompt-injection/tool-poisoning plus the five static analysis categories. An agent immediately knows this is a security-scanning tool, distinguishing it from the chain_*/crypto_*/defi_* siblings.

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

Usage Guidelines3/5

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

Pricing context (x402 at $0.005/scan vs. $0.05 HTTP variant) implies a cost-based selection condition, but it never states when to choose this over the obvious sibling scan_mcp_preview or names any alternative. Usage is implied rather than prescribed.

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

All tech-risk toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources