mcp-defectdojo: Instructions file for Claude Code

CLAUDE.md

mcp-defectdojo CLAUDE.md is an instructions file for Claude Code from inspicere/mcp-defectdojo. It costs 825 tokens per session, scanned A, original, MIT.

A set of project instructions for Claude Code, an AI coding assistant, describing the structure and conventions of an MCP server for DefectDojo. DefectDojo is a system for managing security vulnerabilities, and MCP is a way for AI assistants to call tools.

In plain words
What is it for?
Use it when developing or maintaining this Python server, including running tests, checking dependencies, and understanding responsibilities for API clients, access control, validation, and audit logs.
Why use it?
It gives the coding assistant project-specific context about modules, tests, security controls, and development commands. That reduces the need to explain the repository's architecture and conventions in each session.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is inspicere/mcp-defectdojo's own configuration. It tells Claude Code how to work on mcp-defectdojo itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-defectdojo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to inspicere/mcp-defectdojo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/inspicere/mcp-defectdojo/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/inspicere/mcp-defectdojo

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-defectdojo CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/inspicere/mcp-defectdojo/claude-md/github.svg)](https://agentmods.dev/instructions/inspicere/mcp-defectdojo/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/inspicere/mcp-defectdojo/claude-md"><img src="https://agentmods.dev/badge/instructions/inspicere/mcp-defectdojo/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-defectdojo CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/inspicere/mcp-defectdojo/claude-md"><img src="https://agentmods.dev/badge/instructions/inspicere/mcp-defectdojo/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 825 This file is loaded in full into every session.
When invoked 825 The same file — it is already loaded in full.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00825 $0.00825
Opus 5 $0.00413 $0.00413
Sonnet 5 $0.00165 $0.00165
Haiku 4.5 $0.00082 $0.00082

Measured 8d ago against content hash 44d93bf698d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-defectdojo CLAUDE.md scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

**MCP Registry publish** — `mcp-publisher 1.7.9` at `/usr/local/bin/mcp-publisher` (Linux amd64, installed via curl one-liner — no Homebrew). The login step is **mandatory before every publish** — see JWT-is-one-use gotc
CLAUDE.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Loaded automatically by Claude Code at the start of every session.

Project

mcp-defectdojo — MCP server for DefectDojo vulnerability management.

  • Python 3.12+, FastMCP framework, httpx async HTTP client
  • 24 MCP tools with RBAC (4 roles, 6 permission groups)
  • Structured JSON audit logging with HMAC integrity chain

Architecture

Module Responsibility
server.py FastMCP tool definitions, input validation, response formatting
client.py httpx async client, dual API key routing, error sanitization
models.py Pydantic response models (strict validation)
rbac.py Role-based access control, token-role binding
security.py Rate limiting, field length validation
audit_logging.py Structured JSON logging, HMAC chain, secret redaction, SIEM forwarding

Development

uv sync                              # Install with dev dependencies
uv run pytest --tb=short -q --cov    # Run tests with coverage
uv run pip-audit                     # Dependency vulnerability scan

Conventions

  • Tests live in tests/ — one test file per source module plus feature-focused files
  • All tools use _format_response() for Pydantic-validated JSON output
  • Write tools are rate-limited via MutationRateLimiter
  • Error messages to MCP clients are sanitized — never expose internal field names
  • Secrets are redacted from all log output via RedactingFilter

Releases (PyPI + MCP Registry)

Public package: mcp-defectdojo on PyPI (since v3.2.6, 2026-05-21). Registry server: io.github.inspicere/mcp-defectdojo.

PyPI publish — token in Vault at secret/pypi (project-scoped, named after the project). Use the pipe pattern; never inline:

uv build
twine check dist/*
vault kv get -field=token secret/pypi | UV_PUBLISH_TOKEN=$(cat) uv publish

MCP Registry publishmcp-publisher 1.7.9 at /usr/local/bin/mcp-publisher (Linux amd64, installed via curl one-liner — no Homebrew). The login step is mandatory before every publish — see JWT-is-one-use gotcha below. Login is interactive device-code OAuth and cannot be cached or automated:

Read the full file on GitHub · 65 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 65 lines · 825 tokens per session scan A 44d93bf698d3

Subscribe to this mod's changes

mcp-defectdojo CLAUDE.md is an instructions file published in the GitHub repository inspicere/mcp-defectdojo (0 stars, last pushed 2mo ago), licensed MIT. It adds 825 tokens to every session, about $0.0041 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens