ChEMBL MCP 伺服器 | PlugMCP
跳到正文
Unofficial ChEMBL MCP Server
A comprehensive Model Context Protocol (MCP) server providing advanced access to the ChEMBL chemical database. This server offers 22 specialized tools enabling AI assistants and MCP clients to perform sophisticated drug discovery research, chemical informatics analysis, and bioactivity investigations directly through ChEMBL's REST API.
A comprehensive Model Context Protocol (MCP) server providing advanced access to the ChEMBL chemical database.
把任意工具接入任意代理。面向非開發者的 MCP 伺服器目錄;閘道承載流量,n8n 承載應用。
產品
目錄
開發者
公司
Features
Core Chemical Search & Retrieval (5 tools)
Compound Search : Search the ChEMBL database by compound name, synonym, or identifier
Detailed Compound Info : Retrieve comprehensive compound information including structure, properties, and annotations
InChI-based Search : Find compounds by InChI key or InChI string
Structure Retrieval : Get chemical structure information in various formats (SMILES, InChI, MOL, SDF)
Similarity Search : Find chemically similar compounds using Tanimoto similarity
Target Analysis & Drug Discovery (5 tools)
Target Search : Search for biological targets by name or type
Detailed Target Info : Retrieve comprehensive target information and annotations
Target Compounds : Get compounds tested against specific targets
UniProt Integration : Find ChEMBL targets by UniProt accession numbers
Target Pathways : Associated biological pathways and mechanisms
Bioactivity & Assay Data (5 tools)
Activity Search : Search bioactivity measurements and assay results
Detailed Assay Info : Get comprehensive assay protocols and conditions
Activity Type Search : Find bioactivity data by specific activity type and value range
Dose-Response Analysis : Get dose-response data and activity profiles
Activity Comparison : Compare bioactivity data across multiple compounds or targets
Drug Development & Clinical Data (4 tools)
Drug Search : Search for approved drugs and clinical candidates
Drug Development Status : Get drug development status and clinical trial information
Therapeutic Indications : Search for therapeutic indications and disease areas
Mechanism of Action : Get mechanism of action and target interaction data
Chemical Property Analysis (4 tools)
ADMET Analysis : Analyze ADMET properties (Absorption, Distribution, Metabolism, Excretion, Toxicity)
Molecular Descriptors : Calculate molecular descriptors and physicochemical properties
Solubility Prediction : Predict aqueous solubility and permeability properties
Drug-Likeness Assessment : Assess drug-likeness using Lipinski Rule of Five and other metrics
Advanced Search & Cross-References (4 tools)
Substructure Search : Find compounds containing specific substructures
Batch Processing : Process multiple ChEMBL IDs efficiently
External References : Get links to external databases (PubChem, DrugBank, PDB, etc.)
Advanced Search : Complex queries with multiple chemical and biological filters
Resource Templates
Direct access to ChEMBL data via URI templates for seamless integration
Installation
Prerequisites
Node.js (v16 or higher)
npm or yarn
Setup git clone <repository-url>
cd chembl-server
Docker
Building the Docker Image docker build -t chembl-mcp-server .
Running with Docker docker run -i chembl-mcp-server
For MCP client integration, you can use the container directly:
{
"mcpServers": {
"chembl": {
"command": "docker",
"args": ["run", "-i", "chembl-mcp-server"],
"env": {}
}
}
}
Usage
As an MCP Server The server is designed to run as an MCP server that communicates via stdio:
Adding to MCP Client Configuration Add the server to your MCP client configuration (e.g., Claude Desktop):
{
"mcpServers": {
"chembl": {
"command": "node",
"args": ["/path/to/chembl-server/build/index.js"],
"env": {}
}
}
}
Available Tools
1. search_compounds Search the ChEMBL database for compounds by name, synonym, or identifier.
query (required): Search query (compound name, synonym, or identifier)
limit (optional): Number of results to return (1-1000, default: 25)
offset (optional): Number of results to skip (default: 0)
{
"query": "aspirin",
"limit": 10
}
2. get_compound_info Get detailed information for a specific compound by ChEMBL ID.
chembl_id (required): ChEMBL compound ID (e.g., CHEMBL25)
{
"chembl_id": "CHEMBL25"
}
3. search_targets Search for biological targets by name or type.
query (required): Target name or search query
target_type (optional): Target type filter (e.g., SINGLE PROTEIN, PROTEIN COMPLEX)
organism (optional): Organism filter
limit (optional): Number of results to return (1-1000, default: 25)
{
"query": "dopamine receptor",
"organism": "Homo sapiens",
"limit": 5
}
4. search_activities Search bioactivity measurements and assay results.
target_chembl_id (optional): ChEMBL target ID filter
assay_chembl_id (optional): ChEMBL assay ID filter
molecule_chembl_id (optional): ChEMBL compound ID filter
activity_type (optional): Activity type (e.g., IC50, Ki, EC50)
limit (optional): Number of results to return (1-1000, default: 25)
{
"target_chembl_id": "CHEMBL2095173",
"activity_type": "IC50",
"limit": 50
}
5. batch_compound_lookup Process multiple ChEMBL IDs efficiently.
chembl_ids (required): Array of ChEMBL compound IDs (1-50)
{
"chembl_ids": ["CHEMBL25", "CHEMBL59", "CHEMBL1642"]
}
Resource Templates The server provides direct access to ChEMBL data through URI templates:
1. Compound Information
URI : chembl://compound/{chembl_id}
Description : Complete compound information for a ChEMBL ID
Example : chembl://compound/CHEMBL25
2. Target Information
URI : chembl://target/{chembl_id}
Description : Complete target information for a ChEMBL target ID
Example : chembl://target/CHEMBL2095173
3. Assay Information
URI : chembl://assay/{chembl_id}
Description : Complete assay information for a ChEMBL assay ID
Example : chembl://assay/CHEMBL1217643
4. Activity Information
URI : chembl://activity/{activity_id}
Description : Bioactivity measurement data for an activity ID
Example : chembl://activity/12345678
5. Search Results
URI : chembl://search/{query}
Description : Search results for compounds matching the query
Example : chembl://search/aspirin
Examples
Basic Compound Search Search for aspirin-related compounds:
// Tool call
{
"tool": "search_compounds",
"arguments": {
"query": "aspirin",
"limit": 5
}
}
Get Detailed Compound Information Retrieve comprehensive information about aspirin:
// Tool call
{
"tool": "get_compound_info",
"arguments": {
"chembl_id": "CHEMBL25"
}
}
Target-based Search Find compounds tested against dopamine receptors:
// Tool call
{
"tool": "search_targets",
"arguments": {
"query": "dopamine receptor D2",
"organism": "Homo sapiens"
}
}
Bioactivity Analysis Search for IC50 data against a specific target:
// Tool call
{
"tool": "search_activities",
"arguments": {
"target_chembl_id": "CHEMBL2095173",
"activity_type": "IC50",
"limit": 100
}
}
Batch Processing Process multiple compounds efficiently:
// Tool call
{
"tool": "batch_compound_lookup",
"arguments": {
"chembl_ids": ["CHEMBL25", "CHEMBL59", "CHEMBL1642", "CHEMBL1201585"]
}
}
API Integration This server integrates with the ChEMBL REST API for programmatic access to chemical data. For more information about ChEMBL:
All API requests include:
User-Agent : ChEMBL-MCP-Server/1.0.0
Timeout : 30 seconds
Base URL : https://www.ebi.ac.uk/chembl/api/data
Error Handling The server includes comprehensive error handling:
Input Validation : All parameters are validated using type guards
API Errors : Network and API errors are caught and returned with descriptive messages
Timeout Handling : Requests timeout after 30 seconds
Graceful Degradation : Partial failures are handled appropriately
Development
Build the Project
Development Mode Run TypeScript compiler in watch mode:
Project Structure chembl-server/
├── src/
│ └── index.ts # Main server implementation
├── build/ # Compiled JavaScript output
├── package.json # Node.js dependencies and scripts
├── tsconfig.json # TypeScript configuration
└── README.md # This file
Dependencies
@modelcontextprotocol/sdk : Core MCP SDK for server implementation
axios : HTTP client for ChEMBL API requests
typescript : TypeScript compiler for development
License
Contributing
Fork the repository
Create a feature branch
Make your changes
Add tests if applicable
Submit a pull request
Support For issues and questions:
About Augmented Nature This comprehensive ChEMBL MCP Server is developed by Augmented Nature , a leading innovator in AI-powered bioinformatics and computational chemistry solutions. Augmented Nature specializes in creating advanced tools that bridge the gap between artificial intelligence and chemical research, enabling researchers to unlock deeper insights from chemical and biological data.
Complete Tool Reference
Core Chemical Search & Retrieval Tools
search_compounds - Search ChEMBL database by name, synonym, or identifier
get_compound_info - Get detailed compound information by ChEMBL ID
search_by_inchi - Find compounds by InChI key or InChI string
get_compound_structure - Retrieve chemical structures in various formats
search_similar_compounds - Find chemically similar compounds using Tanimoto similarity
Target Analysis & Drug Discovery Tools
search_targets - Search for biological targets by name or type
get_target_info - Get detailed target information by ChEMBL target ID
get_target_compounds - Get compounds tested against specific targets
search_by_uniprot - Find ChEMBL targets by UniProt accession
get_target_pathways - Get biological pathways associated with targets
Bioactivity & Assay Data Tools
search_activities - Search bioactivity measurements and assay results
get_assay_info - Get detailed assay information by ChEMBL assay ID
search_by_activity_type - Find bioactivity data by activity type and value range
get_dose_response - Get dose-response data and activity profiles
compare_activities - Compare bioactivity data across multiple compounds
Drug Development & Clinical Data Tools
search_drugs - Search for approved drugs and clinical candidates
get_drug_info - Get drug development status and clinical trial information
search_drug_indications - Search for therapeutic indications and disease areas
get_mechanism_of_action - Get mechanism of action and target interaction data
Chemical Property Analysis Tools
analyze_admet_properties - Analyze ADMET properties
calculate_descriptors - Calculate molecular descriptors and physicochemical properties
predict_solubility - Predict aqueous solubility and permeability properties
assess_drug_likeness - Assess drug-likeness using Lipinski Rule of Five
Advanced Search & Cross-Reference Tools
substructure_search - Find compounds containing specific substructures
batch_compound_lookup - Process multiple ChEMBL IDs efficiently
get_external_references - Get links to external databases
advanced_search - Complex queries with multiple chemical and biological filters
Changelog
v1.0.0 - Initial Release
Comprehensive Chemical Intelligence : 27 specialized tools for drug discovery
Core Functionality : Compound search, target analysis, bioactivity data
Advanced Features : Similarity search, batch processing, cross-references
Resource Templates : Direct URI-based access to ChEMBL data
Docker Support : Containerized deployment with security best practices
Professional Documentation : Complete tool reference and examples
Developed by Augmented Nature : Professional chemical informatics platform
Citation If you use this project in your research or publications, please cite it as follows:
author = {Moudather Chelbi},
title = {ChEMBL MCP Server},
year = {2025},
howpublished = {https://github.com/Augmented-Nature/ChEMBL-MCP-Server},
note = {Accessed: 2025-06-29}
Graphify Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, e Private Gpt Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more. Works with any OpenAI-compatible inference server. Scientific Agent Skills Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biolog Open Code Review Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, Codebase Memory Local code intelligence for developers and AI agents. Connect code, docs and infrastructure in a persistent graph, with CBM Lens, MCP tools, agent integrations and change-aware test selection. Orm The Prisma ORM: write your application in TypeScript with human-readable queries instead of SQL. Host your database on Prisma Postgres and your app on Prisma Compute. OpenViking Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. Context Mode Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OMP, OpenCode, Gemin Dbx 25 MB lightweight cross-platform database client for 100+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Dock Xerj AI search engine and MCP server for bots and agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory a Wasp The batteries-included full-stack framework for the AI era. Develop JS/TS web apps (React, Node.js, and Prisma) using declarative code that abstracts away complex full-stack features like auth, backgr WrenAI GenBI (Generative BI) for AI agents, an open-source, governed text-to-SQL through an open context layer that turns natural-language questions into trusted dashboards, charts, and SQL across 20+ data s Databases MCP 伺服器 最佳 Databases MCP 伺服器
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
如何安裝 ChEMBL? 在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
ChEMBL 需要 API 金鑰嗎? 這筆記錄未列出必要的環境變數。
ChEMBL 使用哪種傳輸方式? ChEMBL 透過 stdio 在本機執行。
ChEMBL 上次檢查是什麼時候? 上次檢查時間:2026-10-27。 A comprehensive Model Context Protocol (MCP) server providing advanced access to the ChEMBL chemical database.
工具
0 / 10