FTIR.fun MCP Server
Enables analysis of FTIR spectra by accepting peak lists, natural-language descriptions, or base64-encoded spectrum files and returning spectral-library candidates from the FTIR.fun API.
README
FTIR.fun MCP Server
MCP wrapper for the hosted FTIR.fun spectral-library API.
This repository is intentionally small and public. It does not contain the private FTIR.fun web application, spectral-library data, API keys, user data, or institutional AI-only report-review logic.
What It Does
- Exposes one task-level MCP tool:
analyze_ftir_spectrum - Accepts FTIR peak lists, natural-language peak descriptions, or base64-encoded FTIR spectrum files
- Calls the hosted FTIR.fun API at
https://ftir.fun/ftir/analyze_spectrum - Returns ranked spectral-library candidates and evidence-oriented response fields from FTIR.fun
Configuration
Set one API key in the runtime environment:
export FTIRFUN_API_KEY="your-ftirfun-api-key"
Optional settings:
export FTIRFUN_API_BASE_URL="https://ftir.fun"
export FTIRFUN_API_TIMEOUT_SECONDS="120"
Run Locally
python -m venv .venv
. .venv/bin/activate
pip install .
ftirfun-mcp
Run Streamable HTTP
FTIRFUN_API_KEY="your-ftirfun-api-key" \
ftirfun-mcp --transport streamable-http --host 127.0.0.1 --port 8001
Docker
docker build -t ftirfun-mcp .
docker run --rm -p 8001:8001 -e FTIRFUN_API_KEY="your-ftirfun-api-key" ftirfun-mcp
For registry introspection, the server can start without an API key. Tool calls that require the hosted API return a structured api_key_required error until FTIRFUN_API_KEY is configured.
Tool Boundary
Use analyze_ftir_spectrum for FTIR spectral-library screening only.
Do not use this MCP server for:
- non-FTIR spectroscopy
- general chemistry Q&A
- institutional AI-only review of existing third-party reports
- accredited laboratory certification
Hosted MCP
FTIR.fun also provides a hosted MCP endpoint:
https://ftir.fun/mcp
The hosted endpoint is the canonical production service. This public repository is the small open-source MCP wrapper used for public MCP registries and self-hosted client installs.
Registry Links
- Smithery: https://smithery.ai/servers/hlin2097/ftirfun
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.