Mcp Auditor

B 84 completed
Other
cli / python · small
64
Files
5,788
LOC
1
Frameworks
4
Languages

Pipeline State

completed
Run ID
#361645
Phase
done
Progress
1%
Started
Finished
2026-04-13 01:31:02
LLM tokens
0

Pipeline Metadata

Stage
Skipped
Decision
skip_scaffold_dup
Novelty
27.57
Framework unique
Isolation
Last stage change
2026-04-16 18:15:42
Deduplication group #47545
Member of a group with 1 similar repo(s) — canonical #99059 view group →
Top concepts (2)
Project DescriptionTesting
Provenance: Repobility (https://repobility.com) — every score reproducible from /scan/

AI Prompt

Create a command-line tool, similar to `mcp-auditor`, designed for security auditing of services exposed via an MCP protocol. The tool should automatically discover all available tools from a target server. For each tool, it needs to generate adversarial payloads across five categories: input validation, error handling, injection, information leakage, and resource abuse, using an LLM. The tool must then execute these payloads against the real server and use an LLM-as-a-judge to classify the response as PASS or FAIL, providing a justification and severity rating. The CLI should support running the audit, generating reports in JSON and Markdown formats, and should ideally follow a hexagonal architecture pattern.
python cli security fuzzing llm agentic mcp testing command-line
Generated by gemma4:latest

Catalog Information

Agentic QA & fuzzing CLI for MCP servers.

Description

Agentic QA & fuzzing CLI for MCP servers.

Novelty

3/10

Tags

python cli security fuzzing llm agentic mcp testing command-line

Technologies

anthropic langchain pydantic

Claude Models

claude-opus-4-6

Quality Score

B
84.1/100
Structure
91
Code Quality
100
Documentation
54
Testing
85
Practices
67
Security
100
Dependencies
60

Strengths

  • CI/CD pipeline configured (github_actions)
  • Good test coverage (121% test-to-source ratio)
  • Code linting configured (ruff (possible))
  • Consistent naming conventions (snake_case)
  • Good security practices \u2014 no major issues detected
  • Properly licensed project

Security & Health

4.1h
Tech Debt (B)
A
OWASP (100%)
PASS
Quality Gate
A
Risk (2)
Repobility — the code-quality scanner for AI-generated software · https://repobility.com
MIT
License
2.0%
Duplication
Full Security Report AI Fix Prompts SARIF SBOM

Languages

python
49.4%
markdown
48.9%
toml
1.1%
yaml
0.6%

Frameworks

pytest

Concepts (2)

Findings produced by Repobility · scan your repo at https://repobility.com/scan/
CategoryNameDescriptionConfidence
Source: Repobility analyzer · https://repobility.com
auto_descriptionProject DescriptionAgentic QA & fuzzing CLI for MCP servers.80%
auto_categoryTestingtesting70%

Quality Timeline

1 quality score recorded.

View File Metrics

Embed Badge

Add to your README:

![Quality](https://repos.aljefra.com/badge/85799.svg)
Quality BadgeSecurity Badge
Export Quality CSVDownload SBOMExport Findings CSV