How do I configure Backstage for authentication?
Enable static token-based external access in Backstage’s `appConfig` with the token and subject fields provided.
@evanshortiss
基本信息
A sample MCP Server and Agent that uses it to pull data from a Backstage instanace
工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
This repository demonstrates how to create a Model Context Protocol (MCP) server that provides tools for LLMs to communicate with a Backstage instance. It includes a sample agent built with the Bee Agent Framework to interact with the MCP server.
Configure Backstage with static token-based authentication. Then prepare and run the MCP server by navigating to server/, installing dependencies (npm i), copying .env.template to .env, editing with valid values, and starting with npm run build && npm start. In a separate terminal, run the agent by changing to agent/, copying .env.template, installing dependencies, and executing npm run build && npm start.
http://localhost:8080.Enable static token-based external access in Backstage’s `appConfig` with the token and subject fields provided.
Node.js and npm are needed. Install dependencies with `npm i` in the `server/` directory.
Copy `.env.template` to `.env` and edit the file with valid values for your Backstage instance.
The server listens on HTTP at `http://localhost:8080` by default.
No; the agent is designed to interact with the MCP server, which must be running first.

Give ears to Claude/Openclaw/Hermes/Codex/Grok Bot. Voibe turns recordings into text your AI agent can work with. Ask your agent to transcribe a meeting, interview, call, lecture, podcast episode or voice memo. The raw
Public docs + tool manifest for the GetIntel MCP connector (app.getintel.ai)

Timestamp and verify evidence on-chain. Let your agent prove what it saw and when. bsv.cx gives an AI agent verifiable memory. Timestamp a hash of any output, archive a web page as it looked, or fetch a URL with a recei

Search a registry of agent skills and MCP servers, run them for real (sandbox or remote MCP, no install, a trace on every run), and hire proven agents for USDC.
MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.
评论