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 agentmods add skills/molcrafts/molmcp/skillnpx skills add MolCrafts/molmcp --skill skillgit clone --depth 1 https://github.com/MolCrafts/molmcpWrote 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/molcrafts/molmcp/skill)<a href="https://agentmods.dev/skills/molcrafts/molmcp/skill"><img src="https://agentmods.dev/badge/skills/molcrafts/molmcp/skill.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.00663 |
| Opus 5 | $0.00029 | $0.00331 |
| Sonnet 5 | $0.00012 | $0.00133 |
| Haiku 4.5 | $0.00006 | $0.00066 |
Grade A, and why
molcrafts 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.
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.
What it actually says
MolCrafts usage
Managed by molmcp init. Do not edit this file.
The model loads this skill; the user should not have to invoke it. If it loaded, use the molcrafts MCP connection.
If molcrafts tools are missing
Stop. Tell the user to install or start molmcp:
pip install molcrafts-molmcp
molmcp init <host> # grok | claude | cursor | codex
Then enable the molcrafts MCP server in the host. Do not hand-roll science
code while the connection is down.
Find the capability, then call it
Science methods are not MCP tools. Discover them, then call them in agent
Python (or molvis_exec on the composed server).
packages— pick sources from summaries.outline(source=…)— module tree.open(ref)— signature, docstring, examples. Do this before coding.compose/search/suggest— index helpers only.
route(task) says which provider namespace a session needs (draw →
molvis, jobs → molq, workspace → molexp). Default molmcp serve mounts
those onto this same connection with FastMCP namespaces: molvis_open,
molq_list_jobs, molexp_list_projects. Core tools stay bare (packages,
open, route).
Use the package that owns the role (structure / IO / analysis → molpy, packing → molpack, plots → molplot). Do not reimplement RDF, trajectory IO, packing, or writers.
Missing API is a product gap
ok=false / SYMBOL_NOT_FOUND / no public API for the step means the
capability is not there. Stop. Report three lines:
- Which step is missing.
- Which package or ref you opened.
- What came back.
Then wait. The user may name another package — run outline / open on
that source; do not skip discovery. Or they may ask to file an issue: use
gh against that science package's tracker (not molmcp), body = the
three lines. Do not add a workaround unless they explicitly ask.
What ships with it
1 file 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.
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.
- 3d ago First seen · 72 lines · 58 tokens per session scan A d4acca1b5b29
molcrafts is a skill published in the GitHub repository MolCrafts/molmcp (0 stars, last pushed 6d ago), licensed BSD-3-Clause. It adds 58 tokens to every session and 663 once invoked, about $0.0003 per session on Opus 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 skills, from other repositories
biopython
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for 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…
nature-statistics
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…
evaluating-with-leakage-gates
Evaluate an OpenMed de-identification or clinical NER model against the leakage-first release gates G1a through G8, which gate releases on residual PHI leakage rather than on F1. Use when the user wants to run the OpenMed eval harness on a synthetic golden set, decide whether a de-id model is RELEASABLE or…
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
mixed-precision
Use FP16/BF16 mixed precision to accelerate training and reduce memory. Use when optimizing GPU performance.