Integration
FTIR.fun MCP Server & REST API
Connect FTIR.fun to your AI assistant or automation pipeline. MCP server for Claude/Cursor/Codex. REST API for custom integrations. Same 130,000+ reference spectra and literature-backed AI interpretation across all methods.
MCP Server — Claude, Cursor, Codex
FTIR.fun's MCP (Model Context Protocol) server has been reviewed and officially listed on the Anthropic MCP Registry, Smithery, and MCP.so. It exposes FTIR spectral search, peak explanation with DOI-cited literature, and material identification as callable tools for any MCP-compatible client.
Quick Connect
# Claude Desktop / Claude Code
claude mcp add ftirfun https://ftir.fun/mcp
# Cursor
# Add to ~/.cursor/mcp.json:
{"mcpServers": {"ftirfun": {"url": "https://ftir.fun/mcp"}}}
# OpenAI Codex
codex mcp add ftirfun https://ftir.fun/mcp
Available Tools
| Tool | Description |
|---|---|
search_ftir_library | Search 130K+ reference spectra by peaks or uploaded file. Returns ranked matches with CAS numbers and similarity scores. |
search_public_ftir_results | Search community-shared analysis results by keyword. |
fetch_public_ftir_result | Fetch a specific public FTIR analysis result by ID for detailed review. |
Server Card & Registry Links
- Server Card (JSON) — standard MCP server discovery endpoint
- Anthropic MCP Registry — officially listed
- Smithery — reviewed and published
- MCP.so — listed
- PyPI (ftirfun-mcp) — Python package
Coze Plugin — Use Inside Doubao
Open Doubao → Plugin Store → search "FTIR" or "红外分析" → tap Add. No configuration needed. Doubao will automatically route infrared-related queries to our spectral search engine.
Search keywords: 红外分析, FTIR, infrared, 光谱检索, 物质识别
REST API
Library Search API
POST /v1/search
Spectral library search. Accepts a file (full-spectrum matching) or a peak list (peak-position matching). If both are provided, file search takes priority.
Authentication
X-API-Key: your-api-key
Request Body
| Field | Type | Required | Description |
|---|---|---|---|
| file_base64 | string | one of | Base64-encoded instrument file (supports CSV, SPA, OPUS, SPC, JCAMP-DX, and 15+ other formats) |
| filename | string | with file_base64 | Original filename including extension (e.g. sample.spa) |
| peaks | number[] | one of | List of peak wavenumbers in cm⁻¹ (e.g. [3026, 1601, 1493, 755]) |
| top_k | integer | no (default 10) | Number of results to return, max 50 |
| tolerance | integer | no (default 8) | Peak match tolerance in cm⁻¹, range 1–30 |
Response
{
"success": true,
"search_mode": "full_spectrum",
"n_matches": 10,
"matches": [
{
"rank": 1,
"name": "Polystyrene",
"cas": "25086-18-4",
"num": 326,
"similarity": 0.9586
}
],
"file_format": "Thermo SPA",
"n_points": 3601,
"error": null
}
Example — File Upload
import base64, requests
with open("sample.spa", "rb") as f:
b64 = base64.b64encode(f.read()).decode()
resp = requests.post(
"https://api.ftir.fun/v1/search",
headers={"X-API-Key": "your-key", "Content-Type": "application/json"},
json={"file_base64": b64, "filename": "sample.spa", "top_k": 5},
)
print(resp.json())
Example — Peak List
import requests
resp = requests.post(
"https://api.ftir.fun/v1/search",
headers={"X-API-Key": "your-key", "Content-Type": "application/json"},
json={"peaks": [3082, 3026, 2923, 1601, 1493, 1451, 1028, 906, 755, 699], "top_k": 5},
)
print(resp.json())
AI-Only Analysis for Existing Results
Use this endpoint only after a search result already exists. FTIR.fun first reads or OCRs the supplied report, extracts the reported candidates and sample peak table, then runs downstream KG and literature-backed analysis.
POST /ftir/analyze_existing_results
The report must contain both the reported search result list and the sample peak table. This endpoint does not perform spectral-library search by itself.
Authentication
X-API-Key: your-api-key
Request Body
| Field | Type | Required | Description |
|---|---|---|---|
| report_text | string | one of | Plain text copied from an existing instrument or library report. The text must include both the reported results and the sample peak table. |
| report_file_base64 | string | one of | Base64-encoded report file. Supported formats: PDF, DOC, DOCX, TXT, CSV, PNG, JPG, JPEG, WEBP, GIF, BMP, TIF, TIFF. |
| report_filename | string | with report_file_base64 | Original report filename including extension (for example report.pdf or report.docx). |
| user_background_text | string | no | Optional sample background. This is treated as soft context only and not as evidence. |
Hard Input Boundary
- Required element 1: at least one reported search result candidate, such as a Top1 hit or a Top15 list
- Required element 2: the sample peak list or peak table in cm-1 from the same report
- If either element is missing, the endpoint returns HTTP 422 and does not generate an analysis report
Success Response
{
"success": true,
"analysis_mode": "ai_only_existing_results",
"message": "AI-only analysis completed from the supplied existing results report.",
"input_requirements": {
"service_boundary": "AI-only analysis starts after a search result already exists.",
"required_inputs": [
"At least one reported search result candidate (Top1 or Top15).",
"The sample peak table or peak list in cm-1."
]
},
"missing_requirements": [],
"missing_requirement_messages": [],
"extracted_report": {
"source_kind": "pdf",
"used_ocr": true,
"peak_values_cm1": [1736, 1601, 1241],
"library_candidates": [
{"rank": 1, "name": "Polyethylene terephthalate", "cas_number": "25038-59-9", "raw_score_text": "856/1000", "normalized_similarity": 0.856}
]
},
"summary": "Reported library results rank Polyethylene terephthalate first.",
"report_view": {},
"final_decision": {},
"direct_evidence": {},
"related_literature": {}
}
Missing-Input Response
{
"detail": {
"success": false,
"analysis_mode": "ai_only_existing_results",
"error": "missing_required_report_elements",
"message": "AI-only analysis requires both reported library results and a sample peak table.",
"missing_requirements": ["sample_peak_table"],
"missing_requirement_messages": [
"Missing sample peak table. Provide the sample peak list or peak table in cm-1 from the same report."
],
"input_requirements": {
"failure_behavior": "If either the reported result list or the sample peak table is missing, the service stops and returns a 422 response."
},
"extracted_report": {
"report_has_library_results": true,
"report_has_peak_table": false
}
}
}
Example — Existing Report Text
import requests
report_text = """
Sample: PET fragment
Top1: Polyethylene terephthalate Score: 856/1000
Top2: Polyester resin Score: 801/1000
Peak table (cm-1): 3435, 2932, 1715, 1409, 1241, 1093, 1017, 872, 722
"""
resp = requests.post(
"https://api.ftir.fun/ftir/analyze_existing_results",
headers={"X-API-Key": "your-key", "Content-Type": "application/json"},
json={"report_text": report_text, "user_background_text": "consumer packaging fragment"},
)
print(resp.json())
Example — Existing Report File
import base64, requests
with open("instrument-report.pdf", "rb") as f:
b64 = base64.b64encode(f.read()).decode()
resp = requests.post(
"https://api.ftir.fun/ftir/analyze_existing_results",
headers={"X-API-Key": "your-key", "Content-Type": "application/json"},
json={
"report_file_base64": b64,
"report_filename": "instrument-report.pdf",
"user_background_text": "suspected packaging adhesive",
},
)
print(resp.json())
Error Codes
| HTTP Status | Meaning |
|---|---|
| 200 | Success |
| 401 | Missing or invalid API key |
| 422 | Invalid request body, unsupported report format, or missing required report elements |
| 500 | Server-side error |