目录 / MCPHero Meta-MCP Generator
MCPHero Meta-MCP Generator
# MCPHero Meta-MCP Let your agent build its own tools. MCPHero Meta-MCP exposes an AI-powered wizard pipeline as MCP tools — describe what you need in plain English, and the agent generates, deploys, and hosts a production MCP server with the exact tools required. Once built, the agent calls those tools on every future run instead of re-generating context from scratch. **Why it matters:** Every time an agent calls an API, parses a database, or runs a calculation, it burns tokens on schemas, error handling, and output parsing. MCPHero flips this — a 50,000-token integration becomes a 50-token tool call on every subsequent run. Your agent doesn't just *use* tools, it *creates* them and keeps them forever. ## What you get - **15 MCP tools** covering the full lifecycle: create sessions, describe requirements in natural language, review AI-suggested tools, configure env vars, set auth, generate code, and deploy — all from inside your agent - **Self-hosted MCP servers** with bearer token auth, ready to connect to any MCP client - **No CLI required** — works entirely through the MCP protocol (OAuth 2.1 handled by your client) ## Quick start Add to your MCP client config: ```json { "mcpServers": { "mcphero": { "url": "https://api.mcphero.app/mcp/meta/mcp" } } } ``` Then ask your agent: *"Build me an MCP server for my PostgreSQL database"* ## Tools | Tool | What it does | |------|-------------| | `wizard_create_session` | Start a new server build session | | `wizard_chat` | Describe requirements in natural language | | `wizard_start` | Begin AI tool suggestion | | `wizard_list_tools` | Review suggested tools | | `wizard_refine_tools` | Iterate on tool definitions | | `wizard_submit_tools` | Confirm tool selection | | `wizard_suggest_env_vars` | Get env var suggestions | | `wizard_list_env_vars` | Review suggested env vars | | `wizard_refine_env_vars` | Iterate on env vars | | `wizard_submit_env_vars` | Submit env var values | | `wizard_set_auth` | Generate bearer token | | `wizard_generate_code` | Generate server code | | `wizard_regenerate_tool_code` | Regenerate a single tool | | `wizard_deploy` | Deploy and get server URL | | `wizard_state` | Poll async operation status | ## Learn more - [Documentation](https://mcphero.app/docs/meta-mcp) - [GitHub](https://github.com/arterialist/mcphero-skills) - [Agent Skills for MCPHero MCP Server](https://github.com/arterialist/mcphero-skills/tree/main/skills/meta-mcp-wizard) — use with Claude Code, OpenCode, Cursor, and more
接入信息
- 传输形态
- http
- 鉴权方式
- 鉴权未知
- 端点
https://meta--mcphero.run.tools
{
"mcpServers": {
"MCPHero Meta-MCP Generator": {
"url": "https://meta--mcphero.run.tools"
}
}
}
能力清单
| 工具 | 说明 |
|---|---|
| wizard_create_session | Create a new wizard session to start gathering requirements. Creates an MCP server in gathering_requirements status with an empty chat history. Use wizard_chat to iterate on requirements with the AI, then call wizard_start once the AI indicates readiness. Args: customer_id: Optional customer UUID (for org API keys with multiple customers). |
| wizard_chat | Send a message in the wizard requirements-gathering chat. Iterate on server requirements with the AI until it indicates readiness (is_ready=True). Then call wizard_start with the server_id to kick off tool suggestion. Args: server_id: Server UUID (from wizard_create_session). message: Your message to the AI. |
| wizard_start | Transition from requirements gathering to tool suggestion. The server must be in gathering_requirements state and the AI must have indicated readiness (wizard_chat returned is_ready=True). Tool suggestion runs in the background – poll with wizard_state to check progress. Args: server_id: Server UUID (from wizard_create_session). description: Optional description override (uses chat-derived value if omitted). technical_details: Optional technical details override. |
| wizard_list_tools | List current tools for a server in the wizard. Args: server_id: Server UUID. |
| wizard_refine_tools | Refine suggested tools with feedback. Triggers LLM refinement in the background. Poll wizard_state for progress. Args: server_id: Server UUID. feedback: Feedback for the LLM to refine tools. tool_ids: Optional list of tool UUIDs to refine. Omit to refine all. |
| wizard_submit_tools | Submit the selected tools to proceed to env vars step. Unselected tools will be deleted. Args: server_id: Server UUID. selected_tool_ids: List of tool UUIDs to keep. |
| wizard_suggest_env_vars | Trigger environment variable suggestion via LLM. Args: server_id: Server UUID. |
| wizard_list_env_vars | List current environment variables for a server. Args: server_id: Server UUID. |
| wizard_refine_env_vars | Refine suggested environment variables with feedback. Triggers LLM refinement in the background. Args: server_id: Server UUID. feedback: Feedback for the LLM to refine env vars. |
| wizard_submit_env_vars | Submit environment variable values. Provide values as a mapping of variable UUID to its value. Args: server_id: Server UUID. values: Dict of env var UUID -> value, e.g. {"uuid1": "sk-abc123"}. |
| wizard_set_auth | Set up bearer token authentication for the server. Generates and returns a Bearer token. Args: server_id: Server UUID. |
| wizard_generate_code | Trigger code generation for all tools. Runs in the background. Poll wizard_state to check progress. Args: server_id: Server UUID. |
| wizard_regenerate_tool_code | Regenerate code for a single tool (synchronous, waits for LLM). Args: server_id: Server UUID. tool_id: Tool UUID to regenerate code for. |
| wizard_deploy | Deploy the MCP server to the shared runtime. Args: server_id: Server UUID. |
| wizard_state | Get the current wizard state for a server. Use this to poll for background operation completion (tool suggestion, code generation, etc.). Args: server_id: Server UUID. |
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。