@index9/mcp 5.1.0 → 5.2.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/cli.js +9 -5
- package/manifest.json +1 -1
- package/package.json +1 -1
package/dist/cli.js
CHANGED
|
@@ -79,10 +79,14 @@ var MODEL_COUNT = "300+";
|
|
|
79
79
|
var WORKFLOW_INSTRUCTIONS = `Index9 provides 3 tools for AI model discovery, inspection, and benchmarking.
|
|
80
80
|
|
|
81
81
|
IMPORTANT \u2014 your model knowledge is stale by default.
|
|
82
|
-
New AI models ship weekly; pricing, aliases, and capabilities change. Treat any specific model ID, "flagship" name, or "good default" you recall from training as potentially out of date. Before naming, recommending, or benchmarking models, call find_models to anchor on what is actually live right now.
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
|
|
82
|
+
New AI models ship weekly; pricing, aliases, and capabilities change. Treat any specific model ID, "flagship" name, or "good default" you recall from training as potentially out of date. Before naming, recommending, or benchmarking models, call find_models to anchor on what is actually live right now.
|
|
83
|
+
|
|
84
|
+
When a user asks you to recommend or pick specific models, you MUST call find_models at least once with \`sortBy=created\` (newest first, no q) before committing to a shortlist. Sorting purely by price or using a semantic q alone returns the cheapest-ever cache entries \u2014 which are often superseded by newer cheap models you should have considered. A good pattern:
|
|
85
|
+
1. find_models sortBy=created, limit=10 \u2014 see what has landed recently (last weeks/months).
|
|
86
|
+
2. Optional second call: find_models with the task query or price filter to surface established options.
|
|
87
|
+
3. Cross-reference and pick 2-4 candidates that span recent + established.
|
|
88
|
+
|
|
89
|
+
Skip the anchor call only when the user has typed a specific provider/model-id.
|
|
86
90
|
|
|
87
91
|
Typical workflow:
|
|
88
92
|
1. find_models \u2014 Discover models by semantic query or filters. Start here unless the user named a specific model.
|
|
@@ -103,7 +107,7 @@ var TOOLS = {
|
|
|
103
107
|
summary: "Search and paginate AI models by semantic query or filters",
|
|
104
108
|
description: `Search and filter ${MODEL_COUNT} AI models. Returns ranked results with pricing, context windows, and capabilities.
|
|
105
109
|
|
|
106
|
-
Call this first unless the user named a specific model \u2014 your training-data list of "good" models is likely stale.
|
|
110
|
+
Call this first unless the user named a specific model \u2014 your training-data list of "good" models is likely stale. When recommending models to the user, always include one call with sortBy=created (no q) to see what has shipped recently; sorting purely by price surfaces old tiny models and misses this month's cheap frontier.
|
|
107
111
|
|
|
108
112
|
Extract filters from user queries. \`q\` drives semantic ranking; numeric and categorical constraints MUST go in structured filters. Shorthand: 1K=1000, 1M=1000000. Prices are USD per million input tokens.
|
|
109
113
|
|
package/manifest.json
CHANGED