Borrowing it
Nothing to install: this file belongs to eljefedelrodeodeljefe/inventree-mcp-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/eljefedelrodeodeljefe/inventree-mcp-plugin/main/CLAUDE.mdgit clone --depth 1 https://github.com/eljefedelrodeodeljefe/inventree-mcp-pluginWrote 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.
[](https://agentmods.dev/instructions/eljefedelrodeodeljefe/inventree-mcp-plugin/claude-md)<a href="https://agentmods.dev/instructions/eljefedelrodeodeljefe/inventree-mcp-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/eljefedelrodeodeljefe/inventree-mcp-plugin/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.
<a href="https://agentmods.dev/instructions/eljefedelrodeodeljefe/inventree-mcp-plugin/claude-md"><img src="https://agentmods.dev/badge/instructions/eljefedelrodeodeljefe/inventree-mcp-plugin/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01539 | $0.01539 |
| Opus 5 | $0.00770 | $0.00770 |
| Sonnet 5 | $0.00308 | $0.00308 |
| Haiku 4.5 | $0.00154 | $0.00154 |
Grade A, and why
inventree-mcp-plugin 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 10d 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.
An `inventree` MCP server is configured in `.mcp.json` and points to the local integration test stack (`http://localhost:8000`). When the stack is running, the following tools are available directly — use them instead of How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Project
MCP (Model Context Protocol) server plugin for InvenTree. Runs inside InvenTree as a Django plugin; exposes inventory data via stateless Streamable HTTP to MCP clients (Claude, etc.).
Commands
# Setup
uv sync --dev
prek install # install git hooks
# Lint
uv run ruff check .
uv run ruff format --check .
uv run mypy inventree_mcp_plugin
# Unit tests (no InvenTree required — all deps are mocked)
uv run pytest -v
# Integration tests (requires Docker)
./scripts/integration-test.sh up # start stack, seed data, create MCP users
./scripts/integration-test.sh smoke # run authenticated end-to-end smoke tests
./scripts/integration-test.sh token # print mcp-service API token
./scripts/integration-test.sh down # tear down + delete volumes
Architecture
HTTP request (MCP client)
→ Django URL router
→ MCPView (mcp_transport.py) — auth check, ASGI scope construction
→ StreamableHTTPSessionManager
→ FastMCP server (mcp_server.py) — stateless, JSON responses
→ @mcp.tool() functions (tools/) — Django ORM queries
→ JSON-RPC response
Key files:
| File | Purpose |
|---|---|
inventree_mcp_plugin/core.py |
Plugin entry point, URL registration, REQUIRE_AUTH setting |
inventree_mcp_plugin/mcp_server.py |
FastMCP instance, imports all tool modules to register them |
inventree_mcp_plugin/mcp_transport.py |
MCPView — bridges Django HTTP ↔ MCP ASGI |
inventree_mcp_plugin/tools/simple/ |
One module per domain (parts, stock, locations, categories, orders, bom, builds) |
inventree_mcp_plugin/tools/combinatory/ |
Tools that compose multiple simple operations (empty — add new tools here) |
inventree_mcp_plugin/tools/complex/ |
Multi-step orchestration tools (empty — add new tools here) |
tests/conftest.py |
Stubs Django/InvenTree modules so tools can be imported without InvenTree |
Conventions
- Tools: each tool is a standalone function decorated with
@mcp.tool(). Docstrings drive MCP schema generation — keep them accurate. - ORM access: tools query InvenTree models directly (not via the REST API).
request.userauth is handled upstream inMCPView. - Types: strict mypy. All parameters and return types must be annotated.
- Line length: 120 characters (ruff).
- Python: 3.11+ only. No backcompat shims.
- Dependencies:
mcp>=1.9is the only production dependency. Django and InvenTree are provided by the plugin host environment — do not add them topyproject.toml. - Unit tests: mock the entire InvenTree/Django module tree via
conftest.py. Tests must run withuv run pytestand no InvenTree instance. - Tool list sync: when adding, removing, or renaming tools, always update the tool list in both
README.mdand the "Working with the live InvenTree instance" section of this file.
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.
- 10d ago First seen · 123 lines · 1,539 tokens per session scan A a6227ab5a645
inventree-mcp-plugin CLAUDE.md is an instructions file published in the GitHub repository eljefedelrodeodeljefe/inventree-mcp-plugin (5 stars, last pushed 6mo ago), licensed MIT. It adds 1,539 tokens to every session, about $0.0077 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.
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.
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.
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).
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.
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).
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.