Borrowing it
Nothing to install: this file belongs to rcsb/rcsb-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/rcsb/rcsb-mcp/master/AGENTS.mdgit clone --depth 1 https://github.com/rcsb/rcsb-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/rcsb/rcsb-mcp/agents-md)<a href="https://agentmods.dev/instructions/rcsb/rcsb-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rcsb/rcsb-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/rcsb/rcsb-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/rcsb/rcsb-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 | $0.04177 | $0.04177 |
| Opus 5.5 | $0.01671 | $0.01671 |
| Sonnet 5.5 | $0.00835 | $0.00835 |
| Haiku 4.5 | $0.00418 | $0.00418 |
Grade A, and why
rcsb-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 yesterday.
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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — working on the rcsb-mcp repo
Guidance for AI coding agents (and humans) modifying this repository. This is an MCP server that lets an LLM interrogate Protein Data Bank structures across three RCSB APIs: Search (REST), Data (GraphQL), and Sequence Coordinates (GraphQL).
The runtime assistant persona and output format are not here — they live in
src/rcsb_mcp/prompts/rcsb_search_assistant.md, served over MCP as thercsb_search_assistantprompt (see "Guidance channels" below). Keep that split.
Layout
src/rcsb_mcp/
server.py composition root: builds the FastMCP app, registers each tool
package, serves the prompt, mounts the report route
search.py rcsb_query_* builders, rcsb_query_composer, rcsb_search_request,
rcsb_list_pdb_search_attributes + local filter validation
data.py rcsb_get_* tools (one per Data API root field) + rcsb_describe_data_object
resolvers.py rcsb_find_* free-text -> ontology-id resolvers (EBI/UniProt backends)
seqcoord.py rcsb_seqcoord_* tools + rcsb_describe_seqcoord_object
landing.py the "how to connect" page a browser gets at / and /mcp (MCP
clients pass through to the transport)
report/ rcsb_render_report: models, render, link packing, routes, store
descriptions/ the model-facing ARGUMENT text, one module per tool, mirroring the
source modules (search/, data/, seqcoord/, resolvers/) — see below
queries.py PURE request-body builders (no network) + the DATA_OBJECTS registry
query_doc.py the query document passed between builders and rcsb_search_request
client.py endpoint URLs + HTTP (search POST, GraphQL POST)
graphql.py GraphQL execution, schema introspection/flatten, error enrichment
tooling.py shared tool-registration helpers
attribute_types.py SearchAttribute / operator / scope types shared by the catalogs
search_attributes.py SEARCH_ATTRIBUTES catalog (+ UNPOPULATED_/SPARSE_ lists)
— auto-generated (see scripts/)
chemical_search_attributes.py CHEMICAL_SEARCH_ATTRIBUTES — auto-generated (see scripts/)
attribute_scopes.py which object each attribute hangs off, + nested/repeating roots
— auto-generated (see scripts/)
feature_types.py Sequence Coordinates FeaturesType vocabulary + type -> sources
— auto-generated (see scripts/)
prompts/rcsb_search_assistant.md served as the `rcsb_search_assistant` MCP prompt (package data)
prompts/rcsb_mcp_guide.md NOT served; kept as a source to rescue prose from
tests/ 36 network-free test modules; see "Dev workflow"
scripts/ generate_search_attributes.py, generate_attribute_scopes.py,
generate_feature_types.py
evals/ end-to-end accuracy suite + tool_selection A/B probe harness
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.
- yesterday Changed · +11 lines · +224 tokens per session b656c20828f7
- 12d ago Changed · +6 lines · +143 tokens per session 61418a787f35
- 14d ago Changed · +62 lines · +1,292 tokens per session be2cd88bb751
- 19d ago Changed · +57 lines · +1,023 tokens per session 3d6d7e9e72b4
- 1mo ago First seen · 110 lines · 1,495 tokens per session scan A a42de66a1d4c
rcsb-mcp AGENTS.md is an instructions file published in the GitHub repository rcsb/rcsb-mcp (11 stars, last pushed yesterday), licensed MIT. It adds 4,177 tokens to every session, about $0.0167 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.
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.