Allows interaction with any REST API that provides a Swagger/OpenAPI specification, enabling natural language queries and commands against the API via MCP tools.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Agent-Cortex list my recent orders"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
快速把企业 API 编成私有化 Agent，策略约束下自动执行业务操作。
接上现有的 Swagger/OpenAPI，用自然语言在真实业务 API 上办事。业务逻辑仍在你的系统里；Hubloom 是可私有化的 Agent 服务，生产推荐经 企业后端（BFF） 转发接入（鉴权 / 限流放在后端内部）。流程用 Skill 约束，也可经 Events 事件驱动触发。
完整说明见 在线文档。
环境： Python 3.12+ · uv（推荐）· Redis（必填）· Node.js（仅演示前端）
uv sync
cp config/env.example.yaml config/env.yaml在 config/env.yaml 至少填写 llm.*、redis.url；启用 MCP 时再配 mcp.swagger_url / base_url。
业务 Bearer 由请求传入，不要写进配置文件。
# 产品 API（默认 :8765）
PYTHONPATH=src uv run python main.py
# 演示前端（另开终端）
cd examples/chat/web && npm install && npm run devcurl -s http://127.0.0.1:8765/v1/chat \
-H "Content-Type: application/json" \
-H "X-Session-Id: demo-session" \
-H "X-MCP-Token: your-business-token" \
-d '{"message":"你好，你能做什么？","stream":false,"wait_profile":"interactive"}'Related MCP server: Swagger MCP
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
MCP server for AI access to Swagger by SmartBear.
Operator-as-agent MCP hub. 6 tools. First $5 free, then $0.001/call.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Zhong-y-j/Hubloom'
If you have feedback or need assistance with the MCP directory API, please join our Discord server