@toolsdk.ai/registry 1.0.169 → 1.0.171

package/README.md

@@ -12,14 +12,14 @@
 <a href="https://github.com/toolsdk-ai/toolsdk-mcp-registry/actions/workflows/test.yaml">
   <img src="https://github.com/toolsdk-ai/toolsdk-mcp-registry/actions/workflows/test.yaml/badge.svg" alt="Build Status" />
 </a>
-<img src="https://img.shields.io/badge/MCP_Servers-4547-blue?style=flat-square" alt="MCP Servers Count" />
+<img src="https://img.shields.io/badge/MCP_Servers-4548-blue?style=flat-square" alt="MCP Servers Count" />
 <img src="https://img.shields.io/badge/LICENSE-MIT-ff69b4?style=flat-square" alt="License" />
 <br />
 <a href="https://www.producthunt.com/products/toolsdk-ai">
   <img src="https://api.producthunt.com/widgets/embed-image/v1/top-post-badge.svg?post_id=997428&theme=light&period=daily" alt="Product Hunt" height="40" />
 </a>
 
-<a href="#mcp-servers">🔍 <b>Browse 4547+ Tools</b></a>
+<a href="#mcp-servers">🔍 <b>Browse 4548+ Tools</b></a>
 &nbsp;&nbsp;•&nbsp;&nbsp;
 <a href="#quick-start">🐳 <b>Self-hosted</b></a>
 &nbsp;&nbsp;•&nbsp;&nbsp;
@@ -75,7 +75,7 @@ docker compose up -d
 - *See [Configuration Guide](./docs/DEVELOPMENT.md) for full details.*
 
 > [!TIP]
-> **Tip for Private Deployment**: This registry contains 4547+ public MCP servers. If you only need a specific subset for your private environment, you can prune the `packages/` directory.
+> **Tip for Private Deployment**: This registry contains 4548+ public MCP servers. If you only need a specific subset for your private environment, you can prune the `packages/` directory.
 > 📖 See [Package Management Guide](./docs/DEVELOPMENT.md#5--package-management-for-private-deployment) for details.
 
 That's it! Your self-hosted MCP registry is now running with:
@@ -87,7 +87,7 @@ That's it! Your self-hosted MCP registry is now running with:
 
 - 🌐 **Local Web Interface**: http://localhost:3003
 - 📚 **Swagger API Docs**: http://localhost:3003/swagger  
-- 🔍 **Search & Execute** 4547+ MCP Servers remotely
+- 🔍 **Search & Execute** 4548+ MCP Servers remotely
 - 🤖 **Integrate** with your AI agents, chatbots, and LLM applications
 
 #### 🌐 Remote Tool Execution Example
@@ -107,6 +107,28 @@ curl -X POST http://localhost:3003/api/v1/packages/run \
   }'
 ```
 
+#### 🔌 MCP Gateway (Streamable HTTP Proxy)
+
+The registry also acts as an **MCP Gateway** — any registered package can be accessed as a standard [Streamable HTTP](https://modelcontextprotocol.io/specification/2025-03-26/basic/transports#streamable-http) endpoint, even if the original server is STDIO-only.
+
+**Endpoint:** `POST /mcp/<packageName>`
+
+Pass environment variables via `x-mcp-env-*` headers:
+
+```bash
+curl -X POST http://localhost:3003/mcp/@modelcontextprotocol/server-github \
+  -H "Content-Type: application/json" \
+  -H "x-mcp-env-GITHUB_PERSONAL_ACCESS_TOKEN: ghp_your_token" \
+  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
+```
+
+The server returns a `mcp-session-id` header — include it in subsequent requests to reuse the session (sessions expire after 30 min).
+
+This is useful for:
+- **Protocol Bridging** — Expose local STDIO servers as remote HTTP endpoints
+- **Centralized Access** — Give AI agents a single HTTP gateway to all MCP tools
+- **Client Compatibility** — Connect from any MCP client that supports Streamable HTTP
+
 <details>
 <summary><strong>Alternative: Use as Registry SDK (Data Only)</strong></summary>
 
@@ -221,7 +243,7 @@ graph TD
 
 This open-source project provides:
 
-- **Structured Registry** - 4547+ MCP servers with metadata
+- **Structured Registry** - 4548+ MCP servers with metadata
 - **Unified Gateway** - HTTP API to query and execute tools remotely
 - **Auto-Generated Docs** - Always up-to-date README and API documentation
 
@@ -274,58 +296,22 @@ const searchTool = await searchMCP.getAISDKTool('tavily-search');
 
 ## Contribute Your MCP Server
 
-Help grow the ecosystem! Share your AI tools, plugins, and integrations with the community.
-
-### Quick Submission
+Want to add your MCP server to the registry? Check out our [Contributing Guide](./docs/CONTRIBUTING.md) for the full submission process, JSON schema reference, and examples (including remote servers and OAuth 2.1).
 
 [![Watch the video](https://img.youtube.com/vi/J_oaDtCoVVo/hqdefault.jpg)](https://www.youtube.com/watch?v=J_oaDtCoVVo)
 
-1. [Fork this repository](https://github.com/toolsdk-ai/toolsdk-mcp-registry/fork)
-2. Create `your-mcp-server.json` in [packages/uncategorized](./packages/uncategorized) (or the best matching category folder)
-3. Submit a PR
-
-Config Example:
-
-```json
-{
-  "type": "mcp-server",
-  "name": "Github",
-  "packageName": "@modelcontextprotocol/server-github",
-  "description": "MCP server for using the GitHub API",
-  "url": "https://github.com/modelcontextprotocol/servers/blob/main/src/github",
-  "runtime": "node",
-  "license": "MIT",
-  "env": {
-    "GITHUB_PERSONAL_ACCESS_TOKEN": {
-      "description": "Personal access token for GitHub API access",
-      "required": true
-    }
-  }
-}
-```
-
-Your MCP server will be:
-- ✅ Listed in the registry
-- 🔍 Searchable via REST API
-- 📦 Available in npm package
-- 🌐 Featured on [ToolSDK.ai](https://toolsdk.ai)
-
-📖 **Source of truth (schema, fields, remotes, OAuth)**: [CONTRIBUTING.md](./CONTRIBUTING.md)
-
-📚 Additional docs: [docs/guide.md](./docs/guide.md)
-
 ---
 
 <a id="mcp-servers"></a>
 
 ## MCP Servers Directory
 
-**4547+ AI Agent Tools, LLM Integrations & Automation Servers**
+**4548+ AI Agent Tools, LLM Integrations & Automation Servers**
 
 > [!NOTE]
 > ⭐ **Featured below**: Hand-picked, production-ready MCP servers verified by our team.
 >
-> 📚 **Looking for all 4547+ servers?** Check out [**All MCP Servers**](./docs/ALL-MCP-SERVERS.md) for the complete list.
+> 📚 **Looking for all 4548+ servers?** Check out [**All MCP Servers**](./docs/ALL-MCP-SERVERS.md) for the complete list.
 
 > [!TIP]
 > If a package is marked as `validated: true` in the index, you can usually wire it up in minutes via ToolSDK (e.g. `getAISDKTool(toolKey)`).
@@ -642,6 +628,7 @@ Run code securely, perfect for coding agents and AI-driven programming tasks.
 AI tools that can autonomously read, write, and execute code to solve programming tasks.
 
 - [✅ @steipete/claude-code-mcp](https://github.com/steipete/claude-code-mcp): Provides a streamlined interface for executing complex coding tasks including file operations, Git commands, and web searches without permission interruptions by automatically bypassing constraints.  (1 tools) (node) 
+- [✅ @toolsdk-remote/roundtable-mcp](https://github.com/deadpixel/roundtable-dashboard): Multi-model AI debate platform — consult GPT-4o, Claude, Gemini & 200+ models that discuss your problem, then synthesize a unified insight. Tools: consult_council, review_code, debug_issue, design_architecture, plan_implementation, assess_tradeoffs.  (13 tools) (node) 
 - [✅ mcp-coco](https://github.com/disdjj/mcp-coco): MCP-Coco provides a pair programming tool that guides technical discussions by transforming code snippets into structured frameworks for critical inquiry about performance, security, and maintainability.  (1 tools) (node) 
 - [✅ mcp-neovim-server](https://github.com/bigcodegen/mcp-neovim-server): Integrates Claude Desktop with Neovim, enabling AI-enhanced coding assistance within the familiar Vim environment through direct interaction with buffers and commands.  (19 tools) (node) 
 - [✅ mcp-server-code-assist](https://github.com/abhishekbhakat/mcp_server_code_assist): Enables code modification and generation tasks through file operations, search-and-replace, and version control integration for automated refactoring and codebase maintenance.  (17 tools) (python) 

package/indexes/categories-list.json

@@ -1252,6 +1252,7 @@
       "dafny-verifier",
       "systemprompt-coding-agent",
       "kodit",
+      "@toolsdk-remote/roundtable-mcp",
       "mcp-server-code-assist",
       "crewai-(near-intents)",
       "codeforces",

package/indexes/packages-list.json

@@ -56732,5 +56732,64 @@
     "path": "search-data-extraction/xquik.json",
     "validated": false,
     "tools": {}
+  },
+  "@toolsdk-remote/roundtable-mcp": {
+    "path": "coding-agents/roundtable.json",
+    "category": "coding-agents",
+    "tools": {
+      "list-models": {
+        "name": "list-models",
+        "description": "List available AI models grouped by thinking level (low/medium/high). Shows default models, credit costs, capabilities for each tier. Use this before consult to understand model options."
+      },
+      "list-sessions": {
+        "name": "list-sessions",
+        "description": "List your previous MCP tool sessions. Returns session metadata including prompt, tool used, quality score, and credits consumed. Useful for reviewing past council discussions."
+      },
+      "get-session": {
+        "name": "get-session",
+        "description": "Get full details of a previous MCP session by ID. Returns the complete result including participant responses and moderator synthesis. Use list-sessions first to find session IDs."
+      },
+      "get-logs": {
+        "name": "get-logs",
+        "description": "Query structured logs from your MCP tool executions. Filter by session, severity level, event type, and time range. Useful for debugging and monitoring tool usage."
+      },
+      "check-usage": {
+        "name": "check-usage",
+        "description": "Check your remaining credits, usage limits, and plan info"
+      },
+      "get-thread-link": {
+        "name": "get-thread-link",
+        "description": "Get the dashboard URL for a previous debate session. Returns the thread link and public URL if the thread is public."
+      },
+      "set-thread-visibility": {
+        "name": "set-thread-visibility",
+        "description": "Set a thread as public or private. Public threads can be shared via URL. Use session_id from a previous debate session."
+      },
+      "consult-council": {
+        "name": "consult-council",
+        "description": "Consult the AI coding council — multiple models discuss your engineering question sequentially (each sees prior responses), then a moderator synthesizes. Auto-mode by default — AI picks optimal models, roles, and conversation mode from your prompt. Provide explicit models to override (manual mode). Fully configurable: mode, format, roles, models, thinking level."
+      },
+      "design-architecture": {
+        "name": "design-architecture",
+        "description": "Architecture design council. Systems Architect, Infrastructure Engineer, and DX Advocate evaluate your system design. Always uses high thinking for maximum depth. Output as ADR."
+      },
+      "review-code": {
+        "name": "review-code",
+        "description": "Code review council. Senior Engineer, Security Reviewer, and Performance Analyst analyze your code and a moderator synthesizes their findings."
+      },
+      "plan-implementation": {
+        "name": "plan-implementation",
+        "description": "Implementation planning council. Tech Lead, Senior Engineer, and QA Strategist break down a feature into actionable steps, identify risks, and define acceptance criteria. Output as ADR."
+      },
+      "debug-issue": {
+        "name": "debug-issue",
+        "description": "Debugging council. Root Cause Analyst, Systems Engineer, and Edge Case Investigator collaboratively diagnose bugs, analyze errors, and propose fixes."
+      },
+      "assess-tradeoffs": {
+        "name": "assess-tradeoffs",
+        "description": "Tradeoff assessment council. Pragmatist, Skeptic, and Futurist evaluate options from different angles — short-term vs long-term, risk vs reward, simplicity vs flexibility. Output as pros-cons."
+      }
+    },
+    "validated": true
   }
 }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@toolsdk.ai/registry",
-  "version": "1.0.169",
+  "version": "1.0.171",
   "description": "An Open, Structured, and Standard Registry for MCP Servers and Packages.",
   "keywords": [
     "mcp",

package/packages/coding-agents/roundtable.json

@@ -0,0 +1,19 @@
+{
+  "type": "mcp-server",
+  "name": "Roundtable",
+  "packageName": "@toolsdk-remote/roundtable-mcp",
+  "description": "Multi-model AI debate platform — consult GPT-4o, Claude, Gemini & 200+ models that discuss your problem, then synthesize a unified insight. Tools: consult_council, review_code, debug_issue, design_architecture, plan_implementation, assess_tradeoffs.",
+  "url": "https://github.com/deadpixel/roundtable-dashboard",
+  "runtime": "node",
+  "license": "MIT",
+  "env": {},
+  "remotes": [
+    {
+      "type": "streamable-http",
+      "url": "https://mcp.roundtable.now/mcp",
+      "auth": {
+        "type": "oauth2"
+      }
+    }
+  ]
+}