Skip to main content
Glama

mcp_server_review

Read-onlyIdempotent

Review another MCP server's tools/list JSON for tool-poisoning text, missing annotations, risky parameters, free-form schemas, name shadowing, and context cost before you connect.

Instructions

Heuristic safety review of ANOTHER MCP server from its tools/list output: tool-poisoning text, missing annotations, risky parameters, free-form schemas, name shadowing and context cost. Paste the JSON your client shows.

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": {
      "serverName": "<serverName>",
      "tools": "<tools>"
    },
    "name": "mcp_server_review"
  }
}

Input Schema

NameRequiredDescriptionDefault
toolsYes
serverNameYes

Output Schema

NameRequiredDescriptionDefault
kindNo
toolsNo
serverNo
sourcesNo
summaryNo
verdictNo
findingsNo
validatedNo
limitationNo
limitationsNo
approxContextTokensNo
recommendedAllowlistNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.0
    • removedInput schema / properties / tools / items / additionalProperties
      Removed value: -false
  2. First observedv0.4.1

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare the read-only, idempotent, non-destructive, closed-world profile, so the safety bar is met structurally. The description adds real context beyond them: it targets a DIFFERENT server than the one running the call, and the word "heuristic" correctly signals that findings are indicative, not authoritative.

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 purpose, then the enumerated checks, then the single actionable instruction. No filler sentences; every clause either scopes the tool or tells the agent what to supply.

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?

An output schema exists, so return values need no explanation, and the check list gives a good sense of what the review covers. Slight gap: nothing about behavior at the input limits (300 tools) or what happens with malformed input.

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 0% across both parameters, so the description must compensate. It does partially by clarifying that the tools payload is the tools/list output a client displays, but it says nothing about serverName's role, the 300-tool / 5000-character caps, or the required name field per tool entry.

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 (safety review), the exact resource (another MCP server, derived from its tools/list output), and enumerates the checks performed: tool poisoning, missing annotations, risky parameters, free-form schemas, name shadowing, context cost. An agent can tell this apart from mcp_config_review, which operates on configuration rather than tool manifests.

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?

"Paste the JSON your client shows" hints at the expected workflow and input source, but there is no explicit when-to-use versus when-not, and no pointer to the nearby sibling mcp_config_review or prompt_injection_checklist for adjacent concerns. Usage is implied rather than stated.

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