Skip to main content
Glama
badchars

mcp-security-scanner

by badchars

rt_fuzz_tools

Fuzz-test MCP tools using edge-case inputs like empty strings, path traversal, command injection, SQL injection, and special characters. Dry-run analyzes schema; set confirm_execute to invoke tools and detect crashes.

Instructions

Fuzz-test MCP tools with edge-case inputs: empty strings, long strings, path traversal, command injection, SQL injection, special chars, type confusion. Dry-run by default (schema analysis only) — set confirm_execute=true to actually invoke tools via callTool(). Reports crashes, stack trace leaks, and unhandled errors.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
envNoAdditional environment variables for stdio
urlNoMCP server URL for HTTP/SSE transport (e.g. 'http://localhost:3000/mcp')
argsNoCommand arguments for stdio (e.g. ['run', 'server.js'])
commandNoServer command for stdio transport (e.g. 'node', 'bun', 'npx')
headersNoCustom HTTP headers (e.g. { 'Authorization': 'Bearer token' })
tool_nameNoFuzz only this tool (default: all tools)
categoriesNoFuzz categories: empty, long_string, path_traversal, command_injection, sql_injection, special_chars, type_confusion
timeout_msNoConnection timeout in milliseconds (default: 30000)
confirm_executeNoActually call tools with fuzz payloads (default: false — dry-run schema analysis only)
Behavior5/5

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

No annotations exist, so the description carries full burden. It clearly discloses the dry-run behavior, the opt-in nature of actual invocation, and the types of issues reported (crashes, stack trace leaks, unhandled errors). No contradictions with the schema or implied behavior.

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 composed of two concise, front-loaded sentences. Every word adds necessary information without redundancy.

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?

No output schema exists, but the description mentions the type of output (crashes, stack traces, errors). For a 9-parameter tool with no required params, this covers the essential context. Slightly higher score could be given with an enumeration of output format.

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

Parameters5/5

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

Schema coverage is 100% with descriptions for each of the 9 parameters. The description adds extra context beyond the schema, such as the confirmation toggle default and the categories list, making the parameter semantics fully clear.

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 uses a specific verb ('Fuzz-test') and names the resource ('MCP tools'), listing concrete edge-case inputs and the two modes (dry-run vs actual execution). It clearly distinguishes this tool from sibling security audit tools by its unique fuzzing focus.

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 explicitly explains the dry-run default and how to enable actual execution, along with what the tool reports. However, it does not directly contrast with sibling `rt_check_*` tools or state specific scenarios where fuzzing is preferred over static checks.

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/badchars/mcp-security-scanner'

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