RepoAI
Browse MCPs

ChEMBL Database

88TrustedShips scripts

Access bioactive molecule data, chemical structures, and assay results for drug research.

What it does

Integrating this skill equips your assistant with a direct interface for retrieving detailed pharmacology data. It manages the communication with the ChEMBL database, allowing the assistant to fetch specific compound details, target information, and standardized bioactivity metrics without manual searching.

The skill processes raw data through a dedicated utility, ensuring that queries are handled in accordance with API rate limits and data integrity standards. It transforms the assistant from a general information retriever into a technical partner capable of populating local files with structured chemical data for further analysis.

When it earns its place

Reach for it when…

Use this when your workflow requires empirical data for medicinal chemistry, such as identifying IC50 values for specific targets, comparing molecular properties, or downloading structural files for computational modeling and visualization.

Look elsewhere when…

Do not use this for general health advice, clinical trial information beyond bioactivity records, or proprietary molecular dynamics simulations, as it is strictly a retrieval tool for established database records.

What to say to use it

You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.

  • Find the IC50 values for EGFR inhibitors
  • What are the properties of CHEMBL25
  • Search for compounds targeting human insulin receptors
  • Download the chemical structure for aspirin in SDF format

Install it

Install for all your projects

Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.

bash
git clone --depth 1 --branch main https://github.com/google-deepmind/science-skills.git /tmp/science-skills
mkdir -p ~/.claude/skills
cp -r /tmp/science-skills/skills/chembl_database ~/.claude/skills/chembl-database

Install for one project only

Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.

bash
cp -r /tmp/science-skills/skills/chembl_database .claude/skills/chembl-database

If a skill of the same name exists in both places, the personal one wins.

Installing on Claude.ai or through the API instead? The full guide covers every surface.

Pair it with an MCP server

ChEMBL Database changes how the work is done. These servers change what Claude can reach while doing it.

How skills and MCP servers differ →