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 skills add InternScience/MolClaw --skill molclaw-scp-servergit clone --depth 1 https://github.com/InternScience/MolClawWrote 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/skills/internscience/molclaw/molclaw-scp-server)<a href="https://agentmods.dev/skills/internscience/molclaw/molclaw-scp-server"><img src="https://agentmods.dev/badge/skills/internscience/molclaw/molclaw-scp-server/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/skills/internscience/molclaw/molclaw-scp-server"><img src="https://agentmods.dev/badge/skills/internscience/molclaw/molclaw-scp-server.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 21 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 24 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 46 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- low MCP Rug Pull · line 13 pip install without ==version installs the latest release, which could include malicious changes.Fix: Pin the version: pip install package==1.2.3
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 | $0.00030 | $0.01080 |
| Opus 5.5 | $0.00012 | $0.00432 |
| Sonnet 5.5 | $0.00006 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
molclaw-scp-server 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 1mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SCP (Science Context Protocol) is an open-source standard protocol designed to accelerate scientific discovery by building a global collaboration network for autonomous scientific agents, connecting heterogeneous scientific resources (software tools, AI models, datasets, workflow engines, lab instruments, etc.).
Claude MCP usage
The MolClaw Claude runner configures the molclaw-scp MCP client in each sample workspace. Call the tool names and parameter schemas exposed in Claude's live tool list; do not write a Python MCP client inside an agent answer merely to invoke a listed tool. The client keeps a long-running server job alive through polling and retries recoverable forwarding interruptions with the same job ID. It also supports local-path upload/download when the file-transfer tool schema advertises local_file_path; see molclaw-file-transfer. A server-side path is not a local file. The public SCP service retains its original Base64 API.
Before running Claude with skills, install the public client's JavaScript dependencies once with npm install --prefix molclaw_run/mcp_adapter, use Node 22.22 or newer, and export SCP_HUB_API_KEY in the runner's environment. The runner's per-sample MCP config inherits that credential without writing it to disk and limits local file access to that sample's workspace. MOLCLAW_NODE_BIN can select a different Node executable. --claude-mode non does not inject the MolClaw MCP client.
The Python examples below are for standalone scripts that connect directly to SCP. They bypass the Claude stdio client and its polling, recovery, and local-path extensions.
1. Server Definition
If MCP environment. is not installed, please run pip install mcp.
Configure the credential through the repository environment template. Never write an API key into a skill, source file, command example, or committed configuration file.
cd /path/to/MolClaw
cp .env.template .env
# Set SCP_HUB_API_KEY in .env, then load it into the current shell:
set -a
source .env
set +a
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.
- 1mo ago Changed · +8 lines · -8 tokens per session b3d173ab8a58
- 1mo ago First seen · 110 lines · 38 tokens per session scan A a76103d59b53
molclaw-scp-server is a skill published in the GitHub repository InternScience/MolClaw (38 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 1,080 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Performs bounded, local exploratory analysis of explicitly supported scientific files. Supports redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
presenting-conference-talks
Generates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral talks, spotlight presentations, or invited talks for ML and systems conferences.