What is nuxeo-mcp-server AGENTS.md?

An AGENTS.md instruction file for the nuxeo-mcp-server repository. Such files explain how coding agents should understand and work with a project.

Use it to guide agent work on nuxeo-mcp-server, including its structure, setup, and recommended development process.

It gives agents project-specific guidance for setup, repository layout, and development practices.

How nuxeo/nuxeo-mcp-server configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to nuxeo/nuxeo-mcp-server. 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/nuxeo/nuxeo-mcp-server/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/nuxeo/nuxeo-mcp-server

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nuxeo/nuxeo-mcp-server/agents-md/github.svg)](https://agentmods.dev/instructions/nuxeo/nuxeo-mcp-server/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/nuxeo/nuxeo-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/nuxeo/nuxeo-mcp-server/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nuxeo/nuxeo-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/nuxeo/nuxeo-mcp-server/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,048 This file is loaded in full into every session.

When invoked 5,048 The same file — it is already loaded in full.

Security scan C 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.

Model	Per session	Once invoked
Fable 5.1	$0.05048	$0.05048
Opus 5.5	$0.02019	$0.02019
Sonnet 5.5	$0.01010	$0.01010
Haiku 4.5	$0.00505	$0.00505

Measured 3d ago against content hash 585405263a18, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

nuxeo-mcp-server AGENTS.md scanned grade C 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 3d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

> environment cleanly: `rm -rf .venv && uv sync --frozen --extra dev`. A clean

AGENTS.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Nuxeo MCP Server

Guidance for AI coding agents working in this repository.

Project Overview

Nuxeo MCP Server is a Model Context Protocol (MCP) server that exposes Nuxeo Content Repository operations to AI assistants. It lets AI tools create, read, update, delete, search, and manage documents on a Nuxeo server through a standardised MCP interface.

Tech stack: FastMCP 4, Nuxeo Python client, FastAPI/Uvicorn, Docker.

Repository Layout

nuxeo-mcp-server/
├── src/nuxeo_mcp/          # Package source
│   ├── server.py           # MCP server entry-point & FastMCP setup
│   ├── tools.py            # All MCP tools
│   ├── resources.py        # MCP resources (nuxeo:// URIs)
│   ├── prompts.py          # MCP prompt templates
│   ├── es_passthrough.py   # Search-engine passthrough
│   ├── query_dsl.py        # Query DSL guardrails & field guides
│   ├── search_models.py    # Normalized search envelope
│   ├── annotations.py      # Tool safety annotations
│   ├── file_access.py      # file_path policy (local files the tools may upload)
│   ├── auth.py             # OAuth2 / Basic auth handlers
│   ├── middleware.py       # Authentication middleware
│   ├── config.py           # Configuration dataclasses & enums
│   ├── token_store.py      # OAuth2 token storage
│   ├── utility.py          # Document formatting helpers
│   ├── __main__.py         # CLI entry-point
│   └── guides/             # Markdown served by the nuxeo:// guide resources
├── tests/                  # pytest test suite
├── scripts/                # Tool reference generator
├── ci/docker/nuxeo/        # nuxeo-mcp-demo image (Nuxeo + embedded OpenSearch)
├── .github/workflows/      # GitHub Actions CI/CD
├── pyproject.toml          # Project metadata & dependencies
├── Dockerfile              # Container image (Dockerfile-entrypoint.sh: MCP_PORT, MCP_HOST)
├── docker-compose*.yml     # Nuxeo + MCP server; -demo uses nuxeo-mcp-demo
├── mcp_client.py           # Command-line client, used by the image smoke test
└── seed_nuxeo.py           # Test data seeding script

Read the full file on GitHub · 387 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.

3d ago Changed · +2 lines · +42 tokens per session 585405263a18
4d ago Changed · +9 tokens per session afdf551507d5
5d ago Changed · +4 lines · +308 tokens per session 72ae09fb5f70
9d ago Changed · +4 lines · +296 tokens per session f16655f34537
10d ago Changed · +1 lines · +576 tokens per session a22140ed81b8
2mo ago First seen · 376 lines · 3,817 tokens per session scan C 353c96a38099

Subscribe to this mod's changes

nuxeo-mcp-server AGENTS.md is an instructions file published in the GitHub repository nuxeo/nuxeo-mcp-server (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 5,048 tokens to every session, about $0.0202 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

nuxeo-engineering nuxeo-platform

nuxeo-mcp-server AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
nuxeo-mcp-server AGENTS.mdnuxeo/nuxeo-mcp-server	Instructions file	5	yesterday	Apache-2.0	C	5,048	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

nuxeo-mcp-server: Instructions file for Codex