Skip to main content
Glama
io.github.kushvinth/crowbar

io.github.kushvinth/crowbar

cb_poc

Find public GitHub proof-of-concept repositories by CVE, language, or minimum stars, and rank CVEs by PoC count without executing code.

Instructions

Public GitHub PoC repositories (PoC-in-GitHub metadata). Never executed. Filter by CVE, language or minimum stars, or list the CVEs with the most PoCs.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "cb_poc"
  }
}

Input Schema

NameRequiredDescriptionDefault
cveNo
topNoCVEs ranked by PoC count
limitNo
queryNo
languageNo
min_starsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.5

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations present, the description carries the full burden, and it does disclose two meaningful traits: the data source is public GitHub PoC metadata and nothing is executed. It says nothing about read-only semantics, pagination, rate limits, or what a result record contains, so an agent still lacks behavioral detail for a 6-parameter tool.

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?

Three short sentences, front-loaded with the resource identity, then the non-execution caveat, then the filtering modes. No filler, no repetition of the tool name, and each clause carries information.

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

Completeness3/5

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

For a read-only lookup tool with no output schema, six parameters, and 17% schema coverage, the description is the minimum viable: it covers the main entry points but omits the meaning of 'query' and 'limit' and gives no sense of result shape. Adequate but with clear gaps.

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 only 17% (only 'top' is documented), and the description names four of six parameters implicitly (cve, language, min_stars, top) while adding no format or value guidance beyond the names themselves. 'query' and 'limit' are left entirely to an undocumented schema, so the description does not fully compensate for the coverage gap. It adds marginal meaning over the schema.

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

Purpose4/5

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

The description names a specific resource (public GitHub PoC repositories backed by PoC-in-GitHub metadata) and a clear capability set (filter by CVE/language/stars or rank CVEs by PoC count). The 'Never executed' clause usefully clarifies this is metadata lookup rather than exploit execution, implicitly separating it from things like cb_exploit. It stops short of naming a sibling alternative, so it is clear but not fully differentiated.

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?

Three usage modes are enumerated (filter by CVE, filter by language/stars, rank by PoC count), which tells an agent roughly how to drive the tool. There is no explicit when-to-use vs. when-not guidance and no pointer to alternatives such as cb_exploit or cb_cve when a caller actually wants executable exploit content.

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