Convert chemical structure images to SMILES notation using DECIMER's deep learning model. For chemists, researchers, and developers building chemistry workflows that need automated structure recognition.
io.github.DocMinus/decimer-mcp-server
Local install
STDIO
No auth required
How models use it and what it is built for.
Convert chemical structure images to SMILES notation using DECIMER's deep learning model. For chemists, researchers, and developers building chemistry workflows that need automated structure recognition.
Local install — runs as a subprocess.
Where to find authoritative docs and source for DECIMER.
Paste any of these into Agent Studio after connecting DECIMER.
Common questions about connecting and running DECIMER.
What image formats does DECIMER-MCP support?
The server accepts chemical structure images and converts them to SMILES notation. Check the documentation for the complete list of supported image formats (typically JPG, PNG, and similar raster formats).
How do I install and run the DECIMER MCP server?
Install via `uvx decimer-mcp-server@0.1.4`. The server runs over stdio transport, making it compatible with any MCP client that supports standard input/output communication.
What is SMILES and why would I need it?
SMILES (Simplified Molecular Input Line Entry System) is a notation for representing chemical structures as text strings. It's essential for cheminformatics workflows, database storage, and computational chemistry applications.
How accurate is DECIMER at recognizing chemical structures?
DECIMER uses deep learning for structure recognition, but accuracy depends on image quality, complexity, and structure type. Refer to the DECIMER project documentation for benchmarks and known limitations.
Can I use this server offline or does it require an API key?
The server runs locally via stdio, so it does not require external API calls or internet connectivity. Check the installation documentation for any runtime dependencies or model files needed.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams