Borrowing it
Nothing to install: this file belongs to smaniches/alphafold-sovereign-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.
curl -O https://raw.githubusercontent.com/smaniches/alphafold-sovereign-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/smaniches/alphafold-sovereign-mcpWrote 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/smaniches/alphafold-sovereign-mcp/agents-md)<a href="https://agentmods.dev/instructions/smaniches/alphafold-sovereign-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/smaniches/alphafold-sovereign-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.
<a href="https://agentmods.dev/instructions/smaniches/alphafold-sovereign-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/smaniches/alphafold-sovereign-mcp/agents-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 | $0.00776 | $0.00776 |
| Opus 5.5 | $0.00310 | $0.00310 |
| Sonnet 5.5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
alphafold-sovereign-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 15d 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.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instructions for AI coding agents
This is an independently maintained, public research-oriented MCP server, not an AlphaFold prediction model or clinical decision-support product. Make minimal, reviewable changes with explicit evidence. No agent should self-approve, bypass branch protections, publish, or silently merge changes.
Canonical repository references
README.md: user-facing capabilities, installation, non-affiliation.ARCHITECTURE.md: shipped module and protocol boundaries.STATUS.mdandLIMITATIONS.md: actual validation and known gaps.docs/afdb-compatibility.md: AlphaFold DB field renames, isoform selection, fragment limitations, and experimental annotation boundaries.docs/tools/: documented tool arguments and usage..github/workflows/ci.ymlandrelease.yml: required checks and authenticated release workflow.
Prefer these files over older discussions or cached context. Update them when a code change modifies a published contract; avoid duplicated claims.
Safe development
- Inspect production modules and tests before modifying behavior.
- Keep the current 30 public MCP tools backwards compatible unless a deliberately versioned protocol change is justified.
- Preserve meaningful identifier provenance: UniProt accession and isoform, model entity, source release/version, publication, and residue numbering. Do not silently equate PDB, UniProt and predicted model residue indices.
- New upstream clients must validate remote hosts and schemas, respect timeouts/rate limits, and avoid uncontrolled egress in offline mode. An upstream error is not proof of biological absence.
- Use deterministic
respxfixtures, negative/edge cases, and regression tests; add a recorded or manually verified live API example when an upstream schema changes. Do not rely only on import smoke tests. - Verify lint, strict typing, security audit, unit/property and protocol tests, package build, release-path proof and relevant fuzz checks. Follow CI for the authoritative commands and platform matrix.
- Keep
pyproject.tomlanduv.lockin sync. Major library upgrades require protocol/client behavior tests, not just a green import. - Do not edit packaged distribution artifacts, claim a release happened,
or manufacture validation results. PyPI/GitHub signing and release
verification are handled by
.github/workflows/release.yml. - Never auto-merge bot PRs just because routine checks passed. Review API contracts and dependency behavior; use the protected PR workflow and preserve an auditable diff.
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.
- 15d ago Changed · +1 lines · +26 tokens per session ce193a9ae393
- 16d ago First seen · 71 lines · 750 tokens per session scan A f5fd99e4f3e8
alphafold-sovereign-mcp AGENTS.md is an instructions file published in the GitHub repository smaniches/alphafold-sovereign-mcp (4 stars, last pushed 2d ago), licensed Apache-2.0. It adds 776 tokens to every session, about $0.0031 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 2026-10-10.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.