agentmods.dev

chimerax-mcp

chimerax-mcp is a skill for Claude Code, Codex from CHENyiru3/AI-Skills-Collections. It costs 61 tokens per session (1,413 once invoked), scanned A, original, MIT.

A bridge for operating UCSF ChimeraX, a scientific application for viewing and analysing molecular structures. It connects an AI assistant to ChimeraX through a local service or command-line interface and supports molecular measurements and figure export.

In plain words
What is it for?
Use it to inspect molecular structures, analyse hydrogen bonds, salt bridges, molecular contacts, and electrostatic surfaces, manage sessions, or export requested figures.
Why use it?
It provides a documented connection to an existing ChimeraX installation instead of relying on mouse and keyboard automation. Its setup and troubleshooting instructions help diagnose missing software or connection problems.

Skill for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also agents/openai.yaml present. Also seen: mentions Codex.

Part of the compbio plugin — 38 skills shipped together

not rated 2repo changed 3d ago A scan 61 tokens original MIT

Good fit Use it to inspect molecular structures, analyse hydrogen bonds, salt bridges, molecular contacts, and electrostatic surfaces, manage sessions, or export requested figures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/chenyiru3/ai-skills-collections/chimerax-mcp
View source ↗ CHENyiru3/AI-Skills-Collections
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 CHENyiru3/AI-Skills-Collections --skill chimerax-mcp
Clone the repo
git clone --depth 1 https://github.com/CHENyiru3/AI-Skills-Collections

Made for: Claude Code, Codex.

Or install compbio, the plugin that ships this one along with the rest of its 38 skills.

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.

agentmods badge for chimerax-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/chimerax-mcp/github.svg)](https://agentmods.dev/skills/chenyiru3/ai-skills-collections/chimerax-mcp)
Your own site
<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/chimerax-mcp"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/chimerax-mcp/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.

agentmods 80×15 button for chimerax-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/chimerax-mcp"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/chimerax-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,413 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00061 $0.01413
Opus 5.5 $0.00024 $0.00565
Sonnet 5.5 $0.00012 $0.00283
Haiku 4.5 $0.00006 $0.00141

Measured 3d ago against content hash 14bab77c149f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chimerax-mcp 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/smoke_test.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-market/compbio/structural-biology/chimerax-mcp/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChimeraX MCP

Use the dovas-net/chimeraX-mcp bridge to operate a local UCSF ChimeraX application. The client launches a Python MCP server over STDIO; the server sends commands to ChimeraX over localhost HTTP. Installing this skill supplies instructions and a verification helper; the bridge and ChimeraX are separate installations.

Use MCP tools or documented CLI/API access only. Do not use Computer Use, mouse/keyboard automation, or accessibility-tree control. If a GUI has no REST endpoint, report the missing connection; use an isolated headless CLI process for calculations that do not require changing that GUI. Do not silently open a replacement window. An on-screen styling request does not imply export; honor an explicit no-export instruction for images, sessions, and reports.

Setup and troubleshooting

For installation, configuration, missing tools, or connection failures, read references/setup.md. Use an existing working installation when the task only requires operating ChimeraX.

The setup reference covers Python selection, Codex configuration, existing-window attachment, and scripts/smoke_test.py. That helper requires --allow-export: it starts a dedicated GUI session through the bridge and verifies PNG export. Use API/headless checks instead for no-export work.

Choose the session

  1. Discover the available tools and their current argument schemas. Use list_chimerax_instances and check_chimerax_status to identify responsive sessions.
  2. Inspect the intended session with list_models or get_session_info before changing it. Use its returned model IDs and chain names in later calls.
  3. Pass session_id explicitly when multiple instances exist or when working in a dedicated session. A session ID is the ChimeraX REST port, not a model ID or OS process ID.
  4. If the intended GUI is open without REST, attach it as described in the setup reference. An automatic launch can otherwise create a different window.

Read the full file on GitHub · 66 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

  1. 3d ago Changed · +2 lines 14bab77c149f
  2. 8d ago First seen · 64 lines · 61 tokens per session scan A bbd639351610

Subscribe to this mod's changes

chimerax-mcp is a skill published in the GitHub repository CHENyiru3/AI-Skills-Collections (2 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 1,413 once invoked, about $0.0002 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 2026-11-06.

ResearchScientific
Related

chimerax-mcp compared with skills from other repositories

chimerax-mcp next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
chimerax-mcpCHENyiru3/AI-Skills-CollectionsSkill23d agoMITA61Claude Code, Codex
instrument-data-to-allotropeanthropics/knowledge-work-pluginsSkill36kyesterdayApache-2.0A123Claude Code
matlabK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA44Claude Code
exploratory-data-analysisK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA83Claude Code
phylogeneticsK-Dense-AI/scientific-agent-skillsSkill57k5d agoMITA71Claude Code, Codex
research-engineerdavila7/claude-code-templatesSkill34ktodayMITA43Claude Code, Codex
mapping-to-snomedmaziyarpanahi/openmedSkill5.8kyesterdayApache-2.0A205Claude Code