FTIR.fun Spectral Search
Server Details
FTIR spectral search and material identification for AI agents via MCP.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.7/5 across 3 of 3 tools scored. Lowest: 4.1/5.
Each tool has a distinct purpose: library search for spectrum identification, public results search for community analyses, and fetch for retrieving full details. Descriptions clearly differentiate use cases, preventing confusion.
All tool names follow a consistent verb_noun pattern in snake_case (fetch_public_ftir_result, search_ftir_library, search_public_ftir_results), making the naming predictable and easy to understand.
With only 3 tools, the server is tightly scoped to its purpose: library search, public results search, and result detail retrieval. No unnecessary tools, and the count fits the domain well.
The tool set covers the full workflow: identify a spectrum via library search, find community examples, and fetch detailed information. No obvious gaps for the stated purpose of spectral search.
Available Tools
3 toolsfetch_public_ftir_resultARead-onlyIdempotentInspect
Fetch a specific public FTIR analysis result by ID.
USE WHEN:
- User provides a result ID (e.g., "result:12345" or "12345")
- Following up on search_public_ftir_results to get full details
- User shares a result number and wants details
DO NOT USE:
- For searching by keyword (use search_public_ftir_results)
- For analyzing new spectra (use search_ftir_library)
INPUT:
- id: result identifier in format "result:<number>" or just "<number>"
OUTPUT:
- id: canonical result ID
- url: direct link to result page
- title: result headline
- text: analysis summary
- report_view: detailed analysis data
- metadata: additional information
EXAMPLE:
>>> fetch_public_ftir_result(id="result:12345")
>>> fetch_public_ftir_result(id="12345")| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description adds context beyond annotations by detailing the output fields, input format, and example usage. No contradiction with annotations (readOnlyHint, idempotentHint).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with USE WHEN, DO NOT USE, INPUT, OUTPUT, EXAMPLE sections. Every sentence is essential and front-loaded with purpose. No redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter, the description covers input format, output fields, usage context, and examples. Annotations cover safety and idempotency. No missing information.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has 0% description coverage, but description compensates by explaining the id parameter format ('result:<number>' or just '<number>') and provides examples. This adds significant meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states 'Fetch a specific public FTIR analysis result by ID.' The verb 'fetch' and resource are specific, and it distinguishes from siblings like search_public_ftir_results and search_ftir_library.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit USE WHEN and DO NOT USE sections provide clear context: use when user provides an ID or follows up on search results, and do not use for keyword search or analyzing new spectra. Alternatives are named.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_ftir_libraryARead-onlyIdempotentInspect
Search the FTIR spectral library by peaks or full spectrum.
USE WHEN:
- User provides peak positions (e.g., "1736, 1084 cm-1")
- User uploads a spectrum file (.spc, .spa, .opus, .csv, .jdx, .xlsx, etc.)
- You need ranked library matches for material identification
DO NOT USE:
- For analyzing existing reports (use different tool)
- When you only need to parse file format without search
INPUT OPTIONS (provide at least one):
- peaks: list of wavenumber positions in cm⁻¹ (peak-only search, moderate accuracy)
- file_base64: base64-encoded spectrum file (full-spectrum search, highest accuracy)
Supported formats: CSV, TXT, Excel, SPC, SPA, OPUS, JCAMP-DX, JSON (28+ total)
- Both can be provided; file_base64 takes priority for higher accuracy
OUTPUT:
- success: true/false
- matches: ranked candidate materials with similarity scores and CAS numbers
- peak_explanations: functional group assignments from knowledge graph with DOI citations
- evidence: literature references for each peak assignment
- confidence: overall confidence score (0-1, higher is better)
- uncertainty: notes on result reliability and limitations
- summary: human-readable interpretation
EXAMPLE CALLS:
>>> search_ftir_library(peaks=[2915, 1715, 1450], top_k=5)
>>> search_ftir_library(file_base64="V2F2ZW51bWJlcixBYnNvcmJhbmNl...", filename="sample.spc")
>>> search_ftir_library(peaks=[1736, 1084], file_base64="...", top_k=10)| Name | Required | Description | Default |
|---|---|---|---|
| peaks | No | ||
| top_k | No | ||
| filename | No | spectrum.0 | |
| file_base64 | No | ||
| tolerance_cm1 | No |
Output Schema
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true and idempotentHint=true. The description adds value by detailing input options (e.g., file_base64 takes priority) and output structure, which goes beyond the annotations. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-organized with sections (USE WHEN, DO NOT USE, INPUT OPTIONS, OUTPUT, EXAMPLE CALLS). It is appropriately detailed without being verbose, though could be slightly more compact.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists, the description still covers the main scenarios, file formats, and output fields. With 5 parameters and 0 required, it provides sufficient context for most use cases, though a bit more detail on all parameters would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. It explains the two main parameters (peaks and file_base64) with usage details and priority, and mentions top_k in examples. However, it does not explain filename or tolerance_cm1, leaving gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states 'Search the FTIR spectral library by peaks or full spectrum,' which clearly indicates the verb and resource. However, it does not explicitly distinguish from sibling tools like 'fetch_public_ftir_result' or 'search_public_ftir_results,' though the mention of 'library' implies an internal database vs. public results.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description includes explicit 'USE WHEN' and 'DO NOT USE' sections, listing specific conditions for use (e.g., user provides peaks or uploads a spectrum file) and exclusions (e.g., analyzing existing reports or parsing without search). It provides clear context and alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
search_public_ftir_resultsARead-onlyIdempotentInspect
Search FTIR.fun public result pages (community-shared analyses).
USE WHEN:
- User asks "has anyone analyzed material X?"
- Looking for prior analysis examples or case studies
- Research community knowledge lookup
- Want to see how others interpreted similar spectra
DO NOT USE:
- For new spectrum analysis (use search_ftir_library instead)
- For library database search (use search_ftir_library instead)
- When user provides their own spectrum data
INPUT:
- query: search text (e.g., "polyethylene", "PET", "pharmaceutical")
OUTPUT:
- results: list of public result pages with:
* id: result identifier (use with fetch_public_ftir_result)
* url: direct link to result page
* title: result headline
* text: summary of analysis
* metadata: additional info (result_num, source)
EXAMPLE:
>>> search_public_ftir_results(query="polyethylene terephthalate")| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description adds behavioral context (public community-shared results, output structure) beyond annotations. No contradictions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Very well-structured with sections, front-loaded purpose, no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Complete for a simple search tool: explains input, output format, example, and how to use related tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one param 'query' with examples and clarification of free-text search, compensating for 0% schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'search' and resource 'public result pages'. Distinguishes from siblings by explicitly listing when to use each.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit USE WHEN and DO NOT USE sections, naming alternatives and concrete scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!