ChEMBL MCP Server

Community

Unofficial MCP server providing advanced access to the ChEMBL chemical database

How to install ↓ Compare GitHub source repository ↗

Category: Database #2 of 58
Stars: ★ 89 Popular
Transport: stdio (local process)
Runtime: Node.js 16+ · Docker
Credentials: No credential needed
License: Other / unspecified
Last commit: 10 months ago ⚠
Tools: 27

75FMRS · B

This server brings the ChEMBL chemical database into the MCP ecosystem with 27 tools and resource templates spanning compounds, targets, activities, drugs, and property analysis—well suited to drug discovery research. As an unofficial project, watch for licensing ambiguity, documentation inconsistencies, and dependence on the ChEMBL API; validate on a small scale before research use.

Strongest · Documentation 18/20 Weakest · Reliability 12/20

Reliability

12/20

Security and permissions

16/20

Maintenance

14/20

Documentation

18/20

Setup experience

15/20

Why each score

Reliability 12/20: The project is built on the MCP SDK and provides 27 specialized tools, but static code review cannot verify actual runtime behavior. No test files or CI workflows are visible, so reliability cannot exceed 12. While tool declarations align with README descriptions, there's insufficient evidence of error handling and edge case testing.
Security and permissions 16/20: The server communicates with the ChEMBL API via standard HTTP requests without apparent sensitive credential handling. It uses axios for API calls with a 30-second timeout, avoiding potential risks of long-running operations. No default confirmation mechanisms for dangerous operations are evident, but overall privilege and data boundary management appears sound.
Maintenance 14/20: The project has a clear MIT license but lacks a visible security response channel. GitHub shows 89 stars and 2 open issues, but commit frequency and dependency update status cannot be determined. While developed by Augmented Nature, there's insufficient evidence of version control and release history.
Documentation 18/20: The README is comprehensive, providing complete documentation on installation, usage, tool parameters, and examples. It includes Docker support and client configuration examples. Documentation discloses API limitations (like request timeouts) and error handling strategies, providing sufficient troubleshooting information.
Setup experience 15/20: Installation steps are clear, including Node.js dependencies and build process. Docker support is provided, simplifying deployment. Configuration examples for mainstream clients (like Claude Desktop) are included, but static review cannot verify these steps work in actual environments.

Static review · not runListed 2026-09-07

Read the FMRS scoring method →

Fit and risk

What it can accessUses the network

Best for

Drug discovery and computational chemistry researchers
Bioinformatics teams needing ChEMBL data through AI assistants
Developers comfortable with Node.js or Docker

Not for

Production settings requiring official ChEMBL support (this is unofficial)
Users without a Node.js or Docker environment
General database tasks unrelated to ChEMBL

Required permissions

Outbound network access to https://www.ebi.ac.uk/chembl/api/data
Read-only access to public API data; no authentication credentials required

Risks and side effects

Unofficial project with license marked NOASSERTION (README claims MIT); verify licensing yourself
Data accuracy depends on the ChEMBL REST API and the server's parsing may contain defects
30-second request timeouts may constrain large batch queries
README inconsistency on tool count (22 vs 27) raises documentation reliability concerns

Setup

Before you start

Runtime：Node.js 16+ · Docker

Clone the repository
Run npm install (requires Node.js v16+)
Run npm run build
Add {"mcpServers":{"chembl":{"command":"node","args":["/path/to/chembl-server/build/index.js"]}}} to your MCP client config
Alternatively use Docker: docker build -t chembl-mcp-server . then docker run -i chembl-mcp-server.

claude_desktop_config.json

{"mcpServers":{"chembl":{"command":"node","args":["/path/to/chembl-server/build/index.js"],"env":{}}}}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json

{
  "servers": {
    "chembl": {
      "command": "node",
      "args": [
        "/path/to/chembl-server/build/index.js"
      ],
      "env": {}
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal

claude mcp add chembl -- node /path/to/chembl-server/build/index.js

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

After starting the server, search_compounds and the other ChEMBL tools should appear in the client's tool list; calling search_compounds with query "aspirin" and getting results confirms the connection to ChEMBL's API works.

Troubleshooting

Confirm Node.js v16+ is installed and npm run build has completed
Check network connectivity and firewall rules for ebi.ac.uk
Verify ChEMBL ID format (e.g., CHEMBL25) is correct
Reduce limit or batch size if requests time out on large queries
Inspect MCP client logs for specific error messages

Things to try

Once connected, you can ask your AI assistant things like:

Search the ChEMBL database for aspirin and show the top 5 results
Get detailed information for CHEMBL25 including structure and properties
Find IC50 activity data for target CHEMBL2095173
Find compounds similar to CHEMBL25 using Tanimoto similarity

Tools 27

search_compounds read-only

Search the ChEMBL database by compound name, synonym, or identifier

get_compound_info read-only

Get detailed compound information by ChEMBL ID

search_by_inchi read-only

Find compounds by InChI key or InChI string

get_compound_structure read-only

Retrieve chemical structures in SMILES, InChI, MOL, SDF formats

search_similar_compounds read-only

Find chemically similar compounds using Tanimoto similarity

search_targets read-only

Search for biological targets by name or type

get_target_info read-only

Get detailed target information by ChEMBL target ID

get_target_compounds read-only

Get compounds tested against specific targets

Show 19 more tools

search_by_uniprot read-only

Find ChEMBL targets by UniProt accession

get_target_pathways read-only

Get biological pathways associated with targets

search_activities read-only

Search bioactivity measurements and assay results

get_assay_info read-only

Get detailed assay information by ChEMBL assay ID

search_by_activity_type read-only

Find bioactivity data by activity type and value range

get_dose_response read-only

Get dose-response data and activity profiles

compare_activities read-only

Compare bioactivity data across multiple compounds

search_drugs read-only

Search for approved drugs and clinical candidates

get_drug_info read-only

Get drug development status and clinical trial information

search_drug_indications read-only

Search for therapeutic indications and disease areas

get_mechanism_of_action read-only

Get mechanism of action and target interaction data

analyze_admet_properties read-only

Analyze ADMET (absorption, distribution, metabolism, excretion, toxicity) properties

calculate_descriptors read-only

Calculate molecular descriptors and physicochemical properties

predict_solubility read-only

Predict aqueous solubility and permeability properties

assess_drug_likeness read-only

Assess drug-likeness using Lipinski Rule of Five

substructure_search read-only

Find compounds containing specific substructures

batch_compound_lookup read-only

Process multiple ChEMBL IDs efficiently (1-50)

get_external_references read-only

Get links to external databases (PubChem, DrugBank, PDB, etc.)

advanced_search read-only

Complex queries with multiple chemical and biological filters

Use cases

Query compounds and their structures/properties by name or ChEMBL ID

Target analysis and retrieval of target-tested compounds

Searching and comparing bioactivity data such as IC50/Ki

Looking up approved drugs, indications, and mechanisms of action

Property analysis including ADMET, molecular descriptors, and drug-likeness

Similarity and substructure searches plus batch ID lookups

Supported clients

Claude DesktopPartial support

Listed from the project's documentation, not tested by this site.

Overview

An unofficial MCP server by Augmented Nature that wraps the ChEMBL REST API with 27 specialized tools covering compound retrieval, target analysis, bioactivity data, drug development information, and chemical property analysis, plus URI-template resource access to ChEMBL data. It communicates over stdio, requires Node.js v16+, and supports Docker deployment. Note: the README is inconsistent about tool count (22 in the intro, 27 in the changelog).

Similar servers

MCP ClickHouse 79 · B

Connect ClickHouse to your AI assistants

★ 889 · Tools 4 Compare with this →

MCP Toolbox for Databases 74 · B

Google's official database MCP toolbox — define AI-accessible database tools via config

★ 16.7k Compare with this →

DBHub 74 · B

Bytebase's official, minimalist two-tool database MCP server

★ 3.7k · Tools 2 Compare with this →

Supabase MCP Server 74 · B

Connect Supabase to your AI assistants

★ 3.0k Compare with this →

Compare with other MCP servers

Source revision 02782d76d731 Data synced 2026-10-19 Read the FMRS scoring method