@blockrun/mcp 0.6.1 → 0.6.3

package/README.md

@@ -5,7 +5,7 @@
 [![npm version](https://img.shields.io/npm/v/@blockrun/mcp)](https://www.npmjs.com/package/@blockrun/mcp)
 [![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)
 
-BlockRun MCP is a Model Context Protocol server that gives Claude Code (and any MCP-compatible agent) access to real-time web search, neural research, prediction markets, crypto DEX data, X/Twitter intelligence, and 41 LLM models — all paid via x402 micropayments in USDC. No API keys. No subscriptions. No accounts.
+BlockRun MCP gives your AI agent access to live data it can't get on its own — real-time web search, neural research, prediction markets, crypto DEX prices, and X/Twitter intelligence. All paid via x402 micropayments in USDC. No API keys. No subscriptions. No accounts.
 
 ---
 
@@ -39,7 +39,7 @@ No Node.js. No npm. Works from any MCP client. Pass your wallet key via `X-Walle
 | `blockrun_markets` | Prediction markets — Polymarket, Kalshi | $0.001/call |
 | `blockrun_dex` | Real-time DEX prices and liquidity via DexScreener | FREE |
 | `blockrun_image` | Image generation and editing (DALL-E 3, Flux) | $0.02–0.08 |
-| `blockrun_chat` | 41 AI models — get a second opinion or use a specialized model | per token |
+| `blockrun_chat` | Second opinion from another model (GPT, Gemini, DeepSeek, etc.) | per token |
 | `blockrun_wallet` | Wallet balance, agent budgets, spending reports | FREE |
 | `blockrun_models` | List all models with pricing | FREE |
 
@@ -94,7 +94,7 @@ Wallet resolution order:
 
 - **Website:** [blockrun.ai](https://blockrun.ai)
 - **npm:** [@blockrun/mcp](https://www.npmjs.com/package/@blockrun/mcp)
-- **Hosted MCP:** [mcp.blockrun.ai](https://mcp.blockrun.ai)
+- **Hosted MCP:** [mcp.blockrun.ai/mcp](https://mcp.blockrun.ai/mcp)
 - **GitHub:** [github.com/blockrunai/blockrun-mcp](https://github.com/blockrunai/blockrun-mcp)
 - **Telegram:** [t.me/+mroQv4-4hGgzOGUx](https://t.me/+mroQv4-4hGgzOGUx)
 - **X:** [@BlockRunAI](https://x.com/BlockRunAI)

package/dist/index.js

@@ -433,35 +433,13 @@ function registerChatTool(server, budget) {
   server.registerTool(
     "blockrun_chat",
     {
-      description: `Chat with 41 AI models from 7 providers via BlockRun micropayments. No API keys needed.
-Recommended for agents: use routing: "smart" to auto-select the optimal model via ClawRouter.
-routing_profile: "free" (zero cost NVIDIA), "eco" (budget), "auto" (balanced, default), "premium" (best quality)
+      description: `Get a second opinion from another AI model, or use a specialized model for a specific task. Useful when you want to cross-check analysis, use a reasoning model (o3, DeepSeek Reasoner) for hard problems, or use a free NVIDIA model for bulk tasks.
 
-Three ways to use:
-1. ClawRouter (recommended): routing: "smart" \u2014 auto-selects optimal model via 14-dimension AI routing
-2. Direct model: model: "openai/gpt-5.4"
-3. Smart routing: mode: "fast"|"balanced"|"powerful"|"cheap"|"reasoning"|"free"|"coding"
-4. Multi-turn: pass messages[] array (conversation history) \u2014 "message" is appended as the final user turn
+Use routing:"smart" to auto-select the best model, or pick directly: model:"openai/o3", model:"deepseek/deepseek-reasoner", model:"nvidia/deepseek-v3.2" (free).
 
-All providers (format: provider/model-id):
-\u2022 OpenAI (13): gpt-5.4, gpt-5.4-pro, gpt-5.3, gpt-5.2, gpt-5.4-mini, gpt-5-mini, gpt-5.4-nano, gpt-5.2-pro, gpt-5.3-codex, o1, o1-mini, o3, o3-mini
-\u2022 Anthropic (4): claude-haiku-4.5, claude-sonnet-4.6, claude-opus-4.5, claude-opus-4.6
-\u2022 Google (7): gemini-3.1-pro, gemini-3-pro-preview, gemini-3-flash-preview, gemini-2.5-pro, gemini-2.5-flash, gemini-3.1-flash-lite, gemini-2.5-flash-lite
-\u2022 DeepSeek (2): deepseek-chat, deepseek-reasoner
-\u2022 NVIDIA (12, most FREE*): gpt-oss-120b*, gpt-oss-20b*, kimi-k2.5, nemotron-ultra-253b*, nemotron-3-super-120b*, nemotron-super-49b*, deepseek-v3.2*, mistral-large-3-675b*, qwen3-coder-480b*, devstral-2-123b*, glm-4.7*, llama-4-maverick*
-\u2022 ZAI (2): glm-5, glm-5-turbo
-\u2022 MiniMax (1): minimax-m2.7
+Prefer blockrun_search or blockrun_exa for research \u2014 they're purpose-built for that.
 
-Smart routing modes:
-- fast: Gemini Flash, GPT-5 Mini (lowest latency)
-- balanced: GPT-5.4, Claude Sonnet 4.6, Gemini Pro (best default)
-- powerful: GPT-5.4-Pro, Claude Opus 4.6 (highest quality)
-- cheap: NVIDIA free + DeepSeek (lowest cost)
-- reasoning: o3, o1, DeepSeek Reasoner (complex logic)
-- free: All free NVIDIA models (zero cost)
-- coding: GPT-5.3-Codex, Qwen3-Coder, Devstral (code tasks)
-
-Run blockrun_models for live pricing.`,
+Run blockrun_models to see all available models with pricing.`,
       inputSchema: {
         message: z2.string().describe("Your message to the AI"),
         model: z2.string().optional().describe("Specific model ID (e.g., 'openai/gpt-4o')"),
@@ -1048,12 +1026,12 @@ function initializeMcpServer(server) {
 async function main() {
   const server = new McpServer({
     name: "blockrun-mcp",
-    version: "0.6.0"
+    version: "0.6.2"
   });
   initializeMcpServer(server);
   const transport = new StdioServerTransport();
   await server.connect(transport);
-  console.error("BlockRun MCP Server started (v0.6.0) \u2014 stdio transport");
+  console.error("BlockRun MCP Server started (v0.6.2) \u2014 stdio transport");
 }
 main().catch((error) => {
   console.error("Fatal error:", error);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@blockrun/mcp",
-  "version": "0.6.1",
+  "version": "0.6.3",
   "mcpName": "io.github.BlockRunAI/blockrun-mcp",
   "description": "BlockRun MCP Server - Give your AI agent web search, deep research, prediction markets, crypto data, X/Twitter intelligence. Paid via x402 micropayments.",
   "type": "module",