IA-QA — 152 QA & Dev Tools for AI Agents

llm_fit_finder

Read-onlyIdempotent

Shortlist LLMs on facts, no ranking: cloud models with the features you need within a monthly budget, cheapest first; or local models that fit your VRAM, largest first, with the ollama command. A shortlist is not a choice: only your own cases show which model fits.

Input Schema

Name	Required	Description
`mode`	No	cloud (API models) or local (Ollama/self-hosted). Default: cloud
`top_n`	No	Number of models to return (default: 5)
`vram_gb`	No	GPU VRAM in GB (only for mode=local). Default: 16
`features`	No	Required features: vision, function_calling, json_mode, streaming, reasoning
`use_case`	No	Only "reasoning" filters (requires the feature); chatbot \| code \| rag \| summarization \| classification \| agents \| multilingual rank nothing
`max_budget`	No	Maximum monthly budget in USD (based on tokens_per_day)
`quantization`	No	Quantization (only for mode=local): Q4_K_M \| Q8_0 \| FP16. Default: Q4_K_M
`tokens_per_day`	No	Estimated daily token volume (default: 100000)

Output Schema

Name	Required	Description	Default
`mode`	No
`note`	No
`order`	No
`results`	No
`vram_gb`	No
`use_case`	No
`prices_as_of`	No
`quantization`	No
`tokens_per_day`	No
`total_matching`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedNov 2, 2026

changedInput schema / properties / top_n / description

Previous value: -"Number of recommendations to return (default: 5)"New value: +"Number of models to return (default: 5)"

changedInput schema / properties / use_case / description

Previous value: -"Primary use case: chatbot | code | rag | summarization | classification | reasoning | agents | multilingual"New value: +"Only \"reasoning\" filters (requires the feature); chatbot | code | rag | summarization | classification | agents | multilingual rank nothing"

addedOutput schema / properties / note
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / order
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / prices_as_of
```
Added value: +{}
```

removedOutput schema / properties / score

Removed value: -{
-  "type": "number"
-}

Changed1 schema field changedOct 31, 2026

addedInput schema / examples

Added value: +[
+  {
+    "features": [
+      "vision"
+    ],
+    "top_n": 5,
+    "use_case": "chatbot"
+  }
+]

Changed1 schema field changedJun 21, 2026

addedOutput schema / properties

Added value: +{
+  "mode": {
+    "type": "string"
+  },
+  "quantization": {},
+  "results": {
+    "type": "array"
+  },
+  "score": {
+    "type": "number"
+  },
+  "tokens_per_day": {},
+  "total_matching": {
+    "type": "number"
+  },
+  "use_case": {},
+  "vram_gb": {}
+}

Changed1 schema field changedJun 10, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "type": "object"
+}

First observedMay 26, 2026

TDQS

Score is being calculated.

All IA-QA — 152 QA & Dev Tools for AI Agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.