A lookup tool for ChEMBL, a public database of drug molecules and their biological activity. It retrieves information about drug targets, how strongly compounds bind, mechanisms of action, approved drugs, and ADMET properties—how a drug is absorbed, distributed, metabolised, and excreted.

Use it to look up molecules by name, identifier, or chemical structure; find targets by gene name; and retrieve drug-target, bioactivity, mechanism, and pharmacokinetic data.

It removes the need to manually search separate sources for links between drugs and biological targets or for measurements describing a compound's activity and behaviour in the body.

chembl-drug — Skill for Claude Code and Codex by beita6969

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 beita6969/ScienceClaw --skill chembl-drug

Clone the repo

git clone --depth 1 https://github.com/beita6969/ScienceClaw

Made for: Claude Code, Codex.

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/beita6969/scienceclaw/chembl-drug/github.svg)](https://agentmods.dev/skills/beita6969/scienceclaw/chembl-drug)

Your own site

<a href="https://agentmods.dev/skills/beita6969/scienceclaw/chembl-drug"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/chembl-drug/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/beita6969/scienceclaw/chembl-drug"><img src="https://agentmods.dev/badge/skills/beita6969/scienceclaw/chembl-drug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,575 The whole file, excluding the scripts and references it only reads on demand.

Security scan C 2 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	$0.00090	$0.01575
Opus 5	$0.00045	$0.00788
Sonnet 5	$0.00018	$0.00315
Haiku 4.5	$0.00009	$0.00158

Measured 12d ago against content hash ec24b010ba7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade C, and why

chembl-drug scanned grade C with 2 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 12d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -s "https://www.ebi.ac.uk/chembl/api/data/molecule/CHEMBL25.json" | python3 -c "import sys,json; [print(f'{k}: {v}') for k,v in json.load(sys.stdin).get('molecule_properties',{}).items()]"

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

metadata: { "openclaw": { "emoji": "\ud83d\udc8a", "requires": { "bins": ["curl"] } } }

skills/chembl-drug/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ChEMBL Drug & Bioactivity Lookup

Query the ChEMBL REST API to access curated drug-target interaction data, bioactivity measurements, drug mechanisms of action, and ADMET properties from the European Bioinformatics Institute.

API Base URL

https://www.ebi.ac.uk/chembl/api/data

All endpoints accept .json suffix and return JSON by default. Use format=json as a query parameter alternatively.

API Endpoints

Molecule Lookup

Retrieve molecule details by ChEMBL ID or search by name:

# Get molecule by ChEMBL ID
curl -s "https://www.ebi.ac.uk/chembl/api/data/molecule/CHEMBL25.json" | head -80

# Search molecules by name
curl -s "https://www.ebi.ac.uk/chembl/api/data/molecule/search.json?q=imatinib" | head -80

# Get molecule by canonical SMILES
curl -s "https://www.ebi.ac.uk/chembl/api/data/molecule.json?molecule_structures__canonical_smiles=CC(=O)Oc1ccccc1C(=O)O" | head -60

Target Lookup

Retrieve drug target information:

# Get target by ChEMBL ID
curl -s "https://www.ebi.ac.uk/chembl/api/data/target/CHEMBL2034.json" | head -60

# Search targets by gene name
curl -s "https://www.ebi.ac.uk/chembl/api/data/target/search.json?q=EGFR" | head -80

# Get target by UniProt accession
curl -s "https://www.ebi.ac.uk/chembl/api/data/target.json?target_components__accession=P00533" | head -60

Bioactivity Data

Retrieve binding affinity, IC50, Ki, and other activity measurements:

# Get activities for a molecule (with pagination)
curl -s "https://www.ebi.ac.uk/chembl/api/data/activity.json?molecule_chembl_id=CHEMBL25&limit=20" | head -100

# Get activities for a specific target
curl -s "https://www.ebi.ac.uk/chembl/api/data/activity.json?target_chembl_id=CHEMBL2034&limit=20" | head -100

# Filter by activity type (IC50, Ki, Kd, EC50)
curl -s "https://www.ebi.ac.uk/chembl/api/data/activity.json?molecule_chembl_id=CHEMBL941&standard_type=IC50&limit=10" | head -80

# Filter by potency threshold (pChEMBL value >= 6, i.e., activity <= 1 uM)
curl -s "https://www.ebi.ac.uk/chembl/api/data/activity.json?target_chembl_id=CHEMBL2034&pchembl_value__gte=6&limit=20" | head -80

Read the full file on GitHub · 129 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.

12d ago First seen · 129 lines · 90 tokens per session scan C ec24b010ba7e

Subscribe to this mod's changes

chembl-drug is a skill published in the GitHub repository beita6969/ScienceClaw (898 stars, last pushed 3mo ago), licensed MIT. It adds 90 tokens to every session and 1,575 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

LLM Scientific ai ai-agent bioinformatics literature-review mcp

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…

synthetic-sciences/openscience · 76 tokens

scanpy

Standard single-cell RNA-seq analysis pipeline. Use for QC, normalization, dimensionality reduction (PCA/UMAP/t-SNE), clustering, differential expression, and visualization. Best for exploratory scRNA-seq analysis with established workflows. For deep learning models use scvi-tools; for data format questions use…

synthetic-sciences/openscience · 68 tokens

structure-prediction

Protein structure prediction from sequence. ESMFold-based, single GPU, no MSA needed. Predicts 3D structures with pLDDT confidence scores for drug discovery targets.

synthetic-sciences/openscience · 42 tokens

biomcp

Search and retrieve biomedical data - genes, variants, clinical trials, diagnostic tests, articles, drugs, diseases, pathways, proteins, adverse events, pharmacogenomics, and phenotype-disease matching. Use for gene function, variant pathogenicity, trials, diagnostics, drug safety, pathway context, disease workups…

genomoncology/biomcp · 70 tokens

biomcp-research

Do biomedical literature and variant research with the BioMCP CLI, and file what you learn about the tool itself as issues in the biomcp repo.

genomoncology/biomcp · 36 tokens

biological-expert

Expert-level biology, biotechnology, genetics, bioinformatics, and computational biology. Use when the user mentions biology, biotechnology, genetics, bioinformatics, or genomics, or when the task involves Molecular Biology, Genomics & Bioinformatics, Systems Biology, or Data Analysis.

personamanagmentlayer/pcl · 59 tokens

chembl-drug