What is protein-guide?

A skill guide for using protein-structure and protein-information tools. It explains identifiers such as PDB entries, UniProt accessions, AlphaFold models, ligand IDs, and the relationships between them.

Use it when searching protein structures, reading metadata or coordinates, finding ligands and binding sites, comparing structures, or looking up UniProt features. It also helps choose the right identifier for experimental structures, computed models, and predicted models.

Protein databases use several different identifiers for structures, sequences, genes, and ligands, so using the wrong one can produce an invalid query or misleading result. The guide states which identifier each tool expects and what the tools do not cover.

protein-guide — Skill for Claude Code by cyanheads/protein-mcp-server

Install

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.

Any agent

npx skills add cyanheads/protein-mcp-server --skill protein-guide

Clone the repo

git clone --depth 1 https://github.com/cyanheads/protein-mcp-server

Made for: Claude Code.

Or install protein-mcp-server, the plugin that ships this one along with the rest of its 35 skills, 1 MCP server.

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/skills/cyanheads/protein-mcp-server/protein-guide/github.svg)](https://agentmods.dev/skills/cyanheads/protein-mcp-server/protein-guide)

Your own site

<a href="https://agentmods.dev/skills/cyanheads/protein-mcp-server/protein-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/protein-mcp-server/protein-guide/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/skills/cyanheads/protein-mcp-server/protein-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/protein-mcp-server/protein-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,066 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00095	$0.03066
Opus 5.5	$0.00038	$0.01226
Sonnet 5.5	$0.00019	$0.00613
Haiku 4.5	$0.00010	$0.00307

Measured 4d ago against content hash e2d43d8a0345, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

protein-guide 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 4d 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.

skills/protein-guide/SKILL.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope

Protein structure and function, keyless: search, metadata, coordinates, and corpus counts over experimental PDB entries and the computed models RCSB indexes; ligands and binding-site residues in experimental entries; AlphaFold DB and 3D-Beacons models by UniProt accession; Foldseek fold search; RCSB structural alignment; UniProt features and variants with InterPro memberships.

Not here: fetching a protein's sequence, resolving a gene or protein name to a UniProt accession, and binding affinities. Pair with a UniProt server for sequences and accessions, and a bioactivity server for affinities.

Identifiers

ID	Example	Comes from	Goes to
Polymer entity	`4HHB_1`	`entityId` on sequence hits; `polymerEntities[]`; `hostEntities[]`; `queryEntityId`	Not an input. The row's `id` is the entry; find the entity in that entry's `polymerEntities` for its chains
RCSB computed model	`AF_AFP69905F1`, `MA_…`	predicted hits from `protein_search_structures`	`protein_get_structure` with source `experimental`; it returns as `predicted`, with polymer entities. `protein_compare_structures` takes the `AF_` form as `pdb_id`
AlphaFold DB entry	`AF-P69905-F1`, `AF-P04637-2-F1`	`af://` `entryId`	`protein_get_structure` with source `predicted` or `best_available`; `af://`
UniProt accession	`P69905`; isoform `P04637-2`	`uniprotAccession` on AlphaFold search and Foldseek hits; `accession` from `protein_get_annotations`	`protein_get_structure` (`predicted`, `best_available`), `af://`, `protein_find_similar`; `protein_get_annotations` takes the canonical form only
UniProtKB entry name	`HBA_HUMAN`	a UniProt server	`protein_find_similar` only, which resolves it to its entry's accession; every other tool takes the accession
Picked PDB entry	`pdbId`	`best_available` records	`protein_get_structure` with source `experimental`, for entities, chains, and ligands
Chemical component	`STI`, `HEM`	`find_ligand` `compId`; `ligands[].compId`	`structures_with_ligand`, `binding_site`, the ligand filter of `protein_search_structures`

Read the full file on GitHub · 70 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.

4d ago First seen · 70 lines · 95 tokens per session scan A e2d43d8a0345

Subscribe to this mod's changes

protein-guide is a skill published in the GitHub repository cyanheads/protein-mcp-server (6 stars, last pushed 5d ago), licensed Apache-2.0. It adds 95 tokens to every session and 3,066 once invoked, about $0.0004 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 2026-11-04.

PDB Research Scientific bioinformatics cyanheads mcp mcp-server protein-structure

protein-guide next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
protein-guidecyanheads/protein-mcp-server	Skill	6	5d ago	Apache-2.0	A	95	Claude Code
biopythonsynthetic-sciences/openscience	Skill	4.4k	today	Apache-2.0	A	76	Claude Code, Codex
structure-predictionsynthetic-sciences/openscience	Skill	4.4k	today	Apache-2.0	A	42	Claude Code, Codex
pubchem-guidecyanheads/pubchem-mcp-server	Skill	13	11d ago	Apache-2.0	A	87	Claude Code
usgs-water-guidecyanheads/usgs-water-mcp-server	Skill	3	11d ago	Apache-2.0	A	99	Claude Code
ensembl-guidecyanheads/ensembl-mcp-server	Skill	3	10d ago	Apache-2.0	A	95	Claude Code
uniprot-guidecyanheads/uniprot-mcp-server	Skill	2	5d ago	Apache-2.0	A	56	Claude Code