What is molmcp AGENTS.md?

Project instructions for molmcp, a local service that connects AI assistants to MolCrafts and related providers. They explain the repository layout, development workflow, and rules for changing the code.

Use them when developing molmcp, running its tests, updating documentation, or deciding how MCP tools and discovered Python science APIs should be organized.

They give the agent the project context needed to make consistent changes and avoid breaking important design decisions. They also clarify where source code, tests, documentation, notes, and settings belong.

How MolCrafts/molmcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to MolCrafts/molmcp. 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/MolCrafts/molmcp/master/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/MolCrafts/molmcp

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/molcrafts/molmcp/agents-md/github.svg)](https://agentmods.dev/instructions/molcrafts/molmcp/agents-md)

Your own site

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

Per session 1,272 This file is loaded in full into every session.

When invoked 1,272 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	$0.01272	$0.01272
Opus 5.5	$0.00509	$0.00509
Sonnet 5.5	$0.00254	$0.00254
Haiku 4.5	$0.00127	$0.00127

Measured 2mo ago against content hash 79119e97dcde, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

molmcp 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 2mo 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 · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

What this repo is

molmcp is FastMCP-composed MCP for MolCrafts: molmcp serve starts the molcrafts core (knowledge plus list_planes / route) and mounts enabled providers with official namespaces (molvis_open). molmcp init <host> installs the usage skill and one MCP entry. Science APIs are discovered via the core and never mirrored as MCP tools. Pure Python (>= 3.12), src/ layout, managed with uv.

Protocol: MCP 2026-07-28 via FastMCP 4.0.0b5 + MCP Python SDK v2 (mcp>=2). Do not pin FastMCP back to 3.x without an explicit decision.

Where things live

Source code: src/molmcp/
Tests: tests/
Public documentation: docs/ (zensical site; concepts / guides / reference)
Passive project knowledge (notes, decisions, blueprint): .claude/notes/
Active runtime specs (alive, deleted on completion): .claude/specs/
Codex runtime config: .Codex/settings.local.json

One knowledge tree, two runtimes: notes and specs live under .claude/ and are read by both. Only runtime config is per-runtime.

Default workflow

For non-trivial work, prefer:

plan (/mol:spec or write to .claude/notes/)
implement (/mol:impl or /mol:fix)
review (/mol:review)
capture decisions (/mol:note)

What must never change casually

The molmcp.providers entry-point group — external packages register providers against it.
The discovery cache on-disk format (graph.db schema, manifests); bump SCHEMA_VERSION / ANALYZER_VERSION in src/molmcp/discovery/schema.py on any breaking change. Renaming a cache file means adding the old name to LEGACY_EXTRACT_DB_NAMES so nobody is left with a stranded multi-gigabyte orphan.
Agent-facing hint and error strings name tools bare, as registered; tests/test_tool_hints.py enforces it.
No environment variables — tests/test_no_env_switches.py fails the build if a module reads one, with three listed exemptions.
CI parity: .pre-commit-config.yaml mirrors .github/workflows/ci.yml step-for-step; change both in the same commit.

Read the full file on GitHub · 119 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.

2mo ago First seen · 119 lines · 1,272 tokens per session scan A 79119e97dcde

Subscribe to this mod's changes

molmcp AGENTS.md is an instructions file published in the GitHub repository MolCrafts/molmcp (0 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 1,272 tokens to every session, about $0.0051 per session on Opus 5.5. 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.

molmcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
molmcp AGENTS.mdMolCrafts/molmcp	Instructions file	0	1mo ago	BSD-3-Clause	A	1,272	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 model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

molmcp: Instructions file for Codex