@agentutility/mcp-model-router - npm Package Compare versions

Comparing version 0.1.4 to 0.2.1

dist/tools.generated.js

 /** Auto-generated by scripts/generate-mcp-clusters.mjs. Do not edit by hand. */
 export const CLUSTER_SLUG = "model-router";
-export const VERSION = "0.1.4";
+export const VERSION = "0.2.1";
 export const TOOLS = [
     {
+        "name": "kimi-k3-agent-plan",
+        "http_name": "kimi-k3-agent-plan",
+        "description": "(0.08 USDC/call) Turn a goal into an execution-ready structured agent plan using Venice's exact Kimi K3 model. Send a goal plus optional context and constraints; receive objective, assumptions, dependency-ordered steps, acceptance tests, risks, and a first action as JSON. Input is bounded and the output is capped at 1,024 tokens. Use it for agent task decomposition, implementation plans, workflow planning, acceptance criteria, or a Kimi K3 planning API.",
+        "method": "POST",
+        "input_schema": {
+            "type": "object",
+            "properties": {
+                "goal": {
+                    "type": "string",
+                    "description": "Goal to turn into a plan, up to 2,000 characters."
+                },
+                "context": {
+                    "type": "string",
+                    "description": "Optional supporting context, up to 12,000 characters."
+                },
+                "constraints": {
+                    "type": "array",
+                    "items": {
+                        "type": "string"
+                    },
+                    "description": "Optional constraints, up to 12 strings of 500 characters each."
+                }
+            },
+            "required": [
+                "goal"
+            ]
+        }
+    },
+    {
+        "name": "kimi-k3-chat",
+        "http_name": "kimi-k3-chat",
+        "description": "(0.05 USDC/call) Call Venice's Kimi K3 model through a flat-price x402 endpoint with no Venice account or API key. Send a prompt plus an optional system message, temperature, and max_tokens. This endpoint invokes the exact kimi-k3 upstream model, caps prompts at 8,000 characters and output at 768 tokens, and returns the model name and token usage when supplied by Venice. Use it for Kimi K3 chat, bounded agent reasoning, coding questions, extraction, or a pay-per-call Kimi API.",
+        "method": "POST",
+        "input_schema": {
+            "type": "object",
+            "properties": {
+                "prompt": {
+                    "type": "string",
+                    "description": "User prompt, up to 8,000 characters."
+                },
+                "system": {
+                    "type": "string",
+                    "description": "Optional system instruction, up to 2,000 characters."
+                },
+                "max_tokens": {
+                    "type": "number",
+                    "description": "Maximum output tokens, 1-768. Default 512."
+                },
+                "temperature": {
+                    "type": "number",
+                    "description": "Sampling temperature from 0 to 1.5. Default 0.2."
+                }
+            },
+            "required": [
+                "prompt"
+            ]
+        }
+    },
+    {
         "name": "llm-cost-estimate",
@@ -7,0 +66,0 @@ "http_name": "llm-cost-estimate",

package.json

 {
   "name": "@agentutility/mcp-model-router",
   "mcpName": "ai.agentutility/mcp-model-router",
-  "version": "0.1.4",
+  "version": "0.2.1",
   "description": "MCP server for the @agentutility model-router cluster — pay-per-call x402 tools, no API keys, USDC on Base.",
@@ -6,0 +6,0 @@ "license": "MIT",

README.md

@@ -25,3 +25,3 @@ # @agentutility/mcp-model-router
 
-Restart Claude Desktop. 2 tools appear in the tool palette.
+Restart Claude Desktop. 4 tools appear in the tool palette.
 
@@ -50,6 +50,8 @@ ## Install — Cursor
 
-## Tools (2)
+## Tools (4)
 
 | Tool | Description |
 |---|---|
+| `kimi-k3-agent-plan` | (0.08 USDC/call) Turn a goal into an execution-ready structured agent plan using Venice's exact Kimi K3 model. Send a goal plus optional context and constraints; receive objective, assumptions, dependency-ordered steps, acceptance tests, risks, and a first action as JSON. Input is bounded and the output is capped at 1,024 tokens. Use it for agent task decomposition, implementation plans, workflow planning, acceptance criteria, or a Kimi K3 planning API. |
+| `kimi-k3-chat` | (0.05 USDC/call) Call Venice's Kimi K3 model through a flat-price x402 endpoint with no Venice account or API key. Send a prompt plus an optional system message, temperature, and max_tokens. This endpoint invokes the exact kimi-k3 upstream model, caps prompts at 8,000 characters and output at 768 tokens, and returns the model name and token usage when supplied by Venice. Use it for Kimi K3 chat, bounded agent reasoning, coding questions, extraction, or a pay-per-call Kimi API. |
 | `llm-cost-estimate` | (0.005 USDC/call) LLM cost estimate API, token cost estimate endpoint, and token cost calculator for comparing inference cost across models before you run a prompt. Send input_tokens and output_tokens (or raw text, auto-estimated at roughly 4 characters per token) plus a list of model names, and get a per-model price breakdown from a built-in snapshot price table, with the cheapest known model called out. Pass price_overrides to price your own negotiated rates or a model missing from the table instead of getting a guess. The table is stamped with an as_of date so you know how fresh the snapshot is. Use it as a token cost calculator, a model price compare tool, or a pre-flight budget check before an LLM run or agent workflow. |
@@ -60,4 +62,4 @@ | `model-route-recommend` | (0.01 USDC/call) Model routing API that answers 'which model should I use' from plain task requirements. Send a task description plus optional constraints (latency, budget, context length, modality) and get back a recommended model tier, 2-4 concrete candidate model names, the reasoning behind the pick, tradeoffs, and a cheaper fallback tier when quality can flex. Heuristic route recommendation grounded in general model-capability tiers, not a live benchmark or pricing feed, so candidate models come with a caveat to verify current pricing and capability before committing. Use it as a model selection API, an LLM routing advisor, or a pre-flight check before wiring a new task into an agent pipeline. |
 
-1. Agent calls a tool (e.g. `llm-cost-estimate`).
-2. MCP server POSTs to `https://x402.agentutility.ai/llm-cost-estimate`.
+1. Agent calls a tool (e.g. `kimi-k3-agent-plan`).
+2. MCP server POSTs to `https://x402.agentutility.ai/kimi-k3-agent-plan`.
 3. The endpoint responds **HTTP 402** with payment instructions.
@@ -78,2 +80,2 @@ 4. The MCP server signs an EIP-3009 USDC transfer authorization with `X402_PRIVATE_KEY` and retries.
 
-**Version:** 0.1.4 · **License:** MIT
+**Version:** 0.2.1 · **License:** MIT

New alerts

AI-detected potential code anomaly

Supply chain risk

AI has identified unusual behaviors that may pose a security risk.

Fixed alerts

AI-detected potential code anomaly

Supply chain risk

AI has identified unusual behaviors that may pose a security risk.

Improved metrics

Total package byte prevSize

16619

30.29%

Lines of code

212

40.4%

Number of lines in readme file

78

2.63%

No dependency changes