Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/processqualitysolutions/qcdatabase_mcp/claude-mdgit clone --depth 1 https://github.com/ProcessQualitySolutions/qcdatabase_mcpWhat 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 | $0.00474 | $0.00474 |
| Opus 5 | $0.00237 | $0.00237 |
| Sonnet 5 | $0.00095 | $0.00095 |
| Haiku 4.5 | $0.00047 | $0.00047 |
Grade A, and why
qcdatabase_mcp CLAUDE.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 2d 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.
What it actually says
Contributing to qcdatabase-mcp
An open-source MCP server that connects AI assistants to QCDatabase.AI. It runs
in two modes: stdio (local, single user) and hosted HTTP (multi-user
OAuth resource server — see src/qcdatabase_mcp/hosted.py).
Filesystem-safety invariant (do not break)
The server must never modify its own files and never leak credentials. Concretely, for any change you make here:
- No tool may read or write the server's own source/installation directory.
This prevents self-modification. All local file access goes through
_open_file/_read_bytes/_save_bytesinserver.py, which call_guard_local_path. Route any new local file access through those helpers — never callopen()/Path.write_*/Path.read_*directly in a tool. A module that needs file content (e.g.zipmap.py) takes bytes from a tool rather than reading the disk itself; archives are read in memory, never extracted. - No tool may read or write the credential store (the per-user config dir
from
config.config_dir()). Tokens must stay out of any repo checkout; the store lives in the OS config dir andstore.jsonis.gitignored. - In hosted mode the server touches no local filesystem at all — the disk is
the server's, not the remote user's.
_guard_local_pathenforces this. - Never write credentials, tokens, or
store.jsoninto the repo, and never add them to commits, logs, tests, or fixtures.
If a feature seems to need local file access on the server in hosted mode, it needs a client-side file channel instead — raise it in review rather than weakening the guard.
Working here
- Package:
src/qcdatabase_mcp/. Entry point + CLI:__main__.py. - Keep stdio behavior unchanged unless the task is explicitly about it.
- Quick check:
python -m py_compile src/qcdatabase_mcp/*.py.
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.
- 2d ago First seen · 37 lines · 474 tokens per session scan A 096f720bb13e
qcdatabase_mcp CLAUDE.md is an instructions file published in the GitHub repository ProcessQualitySolutions/qcdatabase_mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 474 tokens to every session, about $0.0024 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.
Other instructions, from other repositories
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.