mcp-assistant

# MCP Assistant MCP Assistant provides access to **100+ MCP servers** like GitHub, Notion, Zapier, Supabase, etc. * **Connect & Manage Integrations**: You can configure and connect these integrations/connectors directly from the [MCP Assistant Dashboard](https://mcp-assistant.in/mcp). * **Advanced Features**: It exposes **meta-tools for dynamic MCP discovery** and a **CodeMode tool** that executes programs inside a secure sandbox for programmatic tool calling, workflow execution, and result processing, avoiding expensive LLM tool-calling loops. ## Endpoint Use this URL with your Assistant such as (OpenCode, Cursor, Codex, ClaudeCode, Antigravity etc.): ```text https://api.mcp-assistant.in/mcp ``` --- ## Key Features * **Unified Gateway**: Access 100+ third-party integrations (GitHub, Notion, Zapier, Slack, Discord, Supabase) through a single endpoint. * **Dynamic Tool Discovery**: Run semantic searches across all connected tool schemas. * **CodeMode Sandbox**: Execute JavaScript/TypeScript scripts on the server side using the `@mcp-ts/codemode` secure sandbox. Run multi-step programmatic workflows or batch actions directly from a single LLM request to avoid expensive round-trips. * **Standard OAuth Authentication**: Fully compatible with client-side OAuth handlers—log in securely via your browser to authorize access to your integrations. --- ## Primary Tools Provided | Tool | Description | | :--- | :--- | | `search_mcp_tools` | Performs a semantic/phrase search across all your connected tools and returns normalized discovery results. | | `get_mcp_tool_schema` | Retrieves the exact input/output JSON schemas and execution helper details for any tool. | | `codemode_run` | Instantly executes a script inside the CodeMode sandbox to chain multiple tool calls, format outputs, or filter large responses. | | `list_mcp_servers` | Lists all connected MCP servers and the number of tools each provides. | --- ## Client Configuration ### VS Code Add the server connection to your VS Code settings: ```json { "servers": { "mcp-assistant": { "type": "http", "url": "https://api.mcp-assistant.in/mcp" } } } ``` ### Cursor / Antigravity / Claude Desktop Add to your client configuration file: ```json { "mcpServers": { "mcp-assistant": { "url": "https://api.mcp-assistant.in/mcp" } } } ```

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://mcp_assistant--zonlabs.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "mcp-assistant": {
      "url": "https://mcp_assistant--zonlabs.run.tools"
    }
  }
}

能力清单

工具	说明
list_mcp_servers	List all connected MCP servers and the number of tools each provides. Use this when `search_mcp_tools` returns no response or irrelevant results, to see if there is an active/connected server that might be relevant.
search_mcp_tools	Search connected MCP tools for the authenticated user and return normalized discovery results. Use this to find candidate MCP tools before execution. Next, pass the chosen result to `get_mcp_tool_schema` to inspect the exact schema, then call the tool from `codemode_run` or a saved workflow script.
get_mcp_tool_schema	Retrieve a normalized schema payload for a connected MCP tool. Use this to inspect the exact input schema, output schema when available, and the CodeMode result extraction hint. Then call that MCP tool from `codemode_run` or a saved workflow script once the args match the schema.
codemode_run	Execute a JavaScript/TypeScript-like script in the CodeMode sandbox with connected MCP tool servers. No queue, workflow, or schedule required. Use this when `search_mcp_tools` or `get_mcp_tool_schema` identified an MCP tool, or when any equivalent MCP tool-discovery and schema-inspection tools identified one, and you want to inspect its output or validate its schema usage quickly without creating a saved workflow. This is also the right tool for chaining multiple MCP tool calls in one script, avoiding repeated agent loops and context reduction, handling batch processing, or transforming, filtering, or summarizing large tool call results before returning them. Recommended flow: First search for the right MCP tool with `search_mcp_tools`. Then inspect that tool's schema with `get_mcp_tool_schema`, or use any equivalent search/schema tools provided by the current MCP client. Finally execute the real MCP call from this script once the args match the schema. When using `callTool(serverId, toolName, args)` or namespaced helpers, the sandbox returns the normalized tool result directly. Use raw helpers only when you explicitly need the MCP envelope.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。