Chemspace MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Chemspace MCP Server search for compounds similar to CC(=O)OC1=CC=CC=C1C(=O)O"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
chemspace-mcp
A Model Context Protocol (MCP) server that provides a wrapper for the Chemspace API, enabling AI agents to search for synthesizable building blocks and screening compounds through exact, substructure, and similarity searches.
Features
Exact Search: Find exact molecular matches by SMILES
Substructure Search: Find compounds containing a specific substructure
Similarity Search: Find structurally similar compounds by SMILES
Multiple Product Categories: Search across in-stock and make-on-demand compounds
Global Shipping: Specify shipping countries with ISO country codes
Related MCP server: PubChem MCP Server
Requirements
Python 3.13+
Chemspace API key
Installation
Prerequisites
Install uv:
# macOS
brew install uv
# Linux/WSL2
curl -LsSf https://astral.sh/uv/install.sh | shSetup
Clone the repository and navigate to the project directory
Set your Chemspace API key as an environment variable:
export CHEMSPACE_API_KEY="your-api-key-here"Install dependencies and run:
uv run chemspace-mcp
Configuration
For use with FastAgent
Configure example/fastagent.secrets.yaml. Environment variables set here will override the ones in your shell:
anthropic:
api_key: your-anthropic-api-key
mcp:
servers:
chemspace:
env:
CHEMSPACE_API_KEY: your-chemspace-api-keyThen run the example interface with FastAgent:
cd example
uv run --extra agent agent.pyUsage
The MCP server exposes the following tools:
search_exact
Searches for exact molecular matches by SMILES string.
Parameters:
smiles(string): The SMILES string to search forshipToCountry(string): Two-letter ISO country code (default: "US")count(integer): Maximum results per page (default: 10)page(integer): Page number for pagination (default: 1)categories(list): Product categories to search:CSSB: In-stock building blocksCSSS: In-stock screening compoundsCSMB: Make-on-demand building blocksCSMS: Make-on-demand screening compoundsCSCS: Custom requests
search_substructure
Searches for compounds containing a specific substructure.
Parameters: Same as search_exact
search_similarity
Searches for structurally similar compounds.
Parameters: Same as search_exact
Project Structure
chemspace-mcp/
├── src/
│ └── chemspace_mcp/
│ ├── __init__.py # Entry point and MCP server initialization
│ ├── tools.py # Tool definitions for chemical searches
│ └── tokenmanager.py # Token management for API authentication
├── example/
│ ├── agent.py # Example FastAgent integration
│ ├── fastagent.config.yaml # FastAgent configuration
│ └── fastagent.secrets.yaml # Secrets configuration (not in version control)
├── pyproject.toml # Project metadata and dependencies
└── README.md # This fileDevelopment
Dependencies
fastmcp>=2.13.1: Core MCP server frameworkfast-agent-mcp>=0.2.25: FastAgent integration
License
MIT License
Support
For issues or questions, please open an issue on the project repository.
Available Tools
3 toolssearch_exactC
Exact search by SMILES
Inputs: smiles (required), shipToCountry, count, page, +1 more.
search_similarityC
Similarity search by SMILES
Inputs: smiles (required), shipToCountry, count, page, +1 more.
search_substructureC
Substructure search by SMILES
Inputs: smiles (required), shipToCountry, count, page, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose with no ambiguity: exact search, similarity search, and substructure search are well-defined and non-overlapping operations in cheminformatics. The descriptions specify different search types, making it easy for an agent to select the correct tool based on the required search method.
All tool names follow a consistent verb_noun pattern with 'search_' as the prefix, followed by a descriptive term (exact, similarity, substructure). This uniformity makes the tool set predictable and easy to understand, with no deviations in naming conventions.
With 3 tools, the server is well-scoped for its purpose of chemical search operations. Each tool earns its place by covering distinct search methods, and the count is appropriate for the domain without being too thin or heavy, allowing focused functionality.
The tool set provides comprehensive coverage for search operations in cheminformatics, including exact, similarity, and substructure searches. A minor gap exists in the lack of tools for additional chemical data operations like property retrieval or filtering, but the core search workflows are complete and functional.
Maintenance
Related MCP Connectors
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
70+ pay-per-call tools for AI agents: web search, email verify, KYC, stocks, crypto, news, data
Web search, page reading, HTML to PDF, file upload and flight search for AI agents, paid in USDC.
Complete SEO and AI Search stack for your AI agents
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI agents and applications to search, retrieve, and analyze chemical compounds, substances, and bioassays from PubChem's vast chemical information database through comprehensive tools for chemical research and discovery.101,902 npm13Apache 2.0
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to search and retrieve chemical compound information, structures, and physical properties from the PubChem database. It supports querying via compound names, SMILES notation, or CIDs to provide detailed molecular data for chemical analysis.5-
- AlicenseNot gradedqualityDmaintenanceEnables interaction with Edison Scientific platform's AI agents for scientific research, chemistry, and literature search, supporting tasks like synthesis planning, literature reviews, and data analysis.6MIT
- AlicenseNot gradedqualityCmaintenanceProvides access to the NIH PubChem chemistry compound database, enabling queries for compound synonyms and other data through natural language.107 npmMIT