What is descartes-mcp AGENTS.md?

Project instructions for a Java server that exposes development and monitoring tools through MCP, a protocol for connecting AI assistants to software tools.

Use them when changing the Java MCP server, its tools or resources, the example server, tests, or profiling and hot-reload systems.

They explain the repository structure, build commands, and how its server, hot reload, inspection, and profiling parts fit together.

How widoriezebos/descartes-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to widoriezebos/descartes-mcp. 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/widoriezebos/descartes-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/widoriezebos/descartes-mcp

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/widoriezebos/descartes-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/widoriezebos/descartes-mcp/agents-md)

Your own site

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

Per session 1,772 This file is loaded in full into every session.

When invoked 1,772 The same file — it is already loaded in full.

Security scan A 0 findings. 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	$0.01772	$0.01772
Opus 5	$0.00886	$0.00886
Sonnet 5	$0.00354	$0.00354
Haiku 4.5	$0.00177	$0.00177

Measured 9d ago against content hash 0edbbba5b88f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

descartes-mcp AGENTS.md scanned grade A with 0 findings 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 9d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

Canonical AI assistant instructions for this repository. Compatibility entry points (CLAUDE.md, GEMINI.md) should refer to this file rather than duplicate policy.

Project Structure & Module Organization

Production code lives in src/main/java/com/bitsapplied/descartes: tools/, resources/, util/, and the hotreload/ + profiler/ subsystems. example/SimpleMCPServerExample demonstrates full registration on port 9080. Mirror packages under src/test/java, keep fixtures in src/test/resources, and store adapter assets in config/mcp/.

Architecture Overview

MCPServer routes JSON-RPC requests and shares state through a Map<String,Object> context. Tools span JShell sessions, inspection, logging, hot reload, and JFR profiling, while resources expose classpath, metrics, thread dumps, and MBeans. Hot reload uses the agent plus HotReloadService; profiling manages recordings, hotspots, call trees, and flame graphs.

Build, Test & Development Commands

Build: mvn clean compile or mvn clean package for the shaded agent JAR (add -Peclipse-m2e when exporting to Eclipse).
Run (no agent): mvn exec:java on port 9080; append -Ddescartes.continuous=true for background mode.
Run (with agent): mvn compile exec:exec -Prun-with-agent, ./scripts/run-with-hotreload.sh, or java -javaagent:target/descartes-mcp-*-jar-with-dependencies.jar -jar ....
Test: mvn test skips concurrency and hot-reload suites; enable -Pconcurrency-tests, -Phot-reload-tests, or -Pall-tests when needed—the agent profiles assemble the shaded JAR first.
Adapter: node config/mcp/mcp-tcp-adapter.js starts the TCP adapter for Claude Code and other clients.
Remote debug target launch (required for agents): scripts/launch-managed-nontty.sh --name <name> -- <command>. Launch without a PTY (tty=false) and never run debug targets in foreground/TTY sessions.

Coding Style & Naming Conventions

Target Java 21 (min 16) with two-space indentation, UpperCamelCase types, lowerCamelCase members, and UPPER_SNAKE_CASE constants. Use var sparingly, group imports, favor parameterized Log4j calls, and extend MCPTool when adding features—register through MCPServer and use the shared context map.

Read the full file on GitHub · 61 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.

9d ago First seen · 61 lines · 1,772 tokens per session scan A 0edbbba5b88f

Subscribe to this mod's changes

descartes-mcp AGENTS.md is an instructions file published in the GitHub repository widoriezebos/descartes-mcp (7 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,772 tokens to every session, about $0.0089 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

descartes-mcp: Instructions file for Codex