Skill：metagraphed
Bittensor didn't ship with a map. We drew one — chain-direct block explorer, developer registry, and an agent toolkit built right in.
适用场景
招聘人事
适合角色
介绍
以下内容整理自开源仓库 `JSONbored/metagraphed` 的 README / SKILL.md 摘要： <div align="center"> <a href="https://metagraph.sh"><img src="https://raw.githubusercontent.com/JSONbored/metagraphed/main/public/brand/banner-readme-mint.png" alt="Metagraphed — Bittensor subnet operational layer · data hub · API" width="820"></a> ### Every subnet, metagraphed. **The open registry and block explorer for Bittensor.** All 128 subnets, the APIs and schemas each one publishes, whether those endpoints answered our last probe, and how to call them — as REST, GraphQL, MCP tools and CSV. Bittensor didn't ship with a map, so we drew one. Every health figure here is probe-derived on a 15-minute cycle; none of it is self-reported. [](https://metagraph.sh) [](https://api.metagraph.sh/mcp) [](https://registry.modelcontextprotocol.io/v0/servers?search=metagraphed) [](https://mcp.so/server/metagraphed---bittensor-subnet-registry/JSONbored) [](https://smithery.ai/servers/metagraphed/metagraphed) [](https://www.npmjs.com/package/@jsonbored/metagraphed) [](https://pypi.org/project/metagraphed/) [](./LICENSE) **[Website](https://metagraph.sh)** · [API](https://api.metagraph.sh) · [OpenAPI](https://api.metagraph.sh/metagraph/openapi.json) · [GraphQL](https://api.metagraph.sh/api/v1/graphql) · [MCP](https://api.metagraph.sh/mcp) · [Agent docs](https://api.metagraph.sh/llms.txt) · [Agent workflows](https://api.metagraph.sh/agent-workflows.md) · [Feeds](https://api.metagraph.sh/api/v1/feeds/registry) · [npm](https://www.npmjs.com/package/@jsonbored/metagraphed) · [PyPI](https://pypi.org/project/metagraphed/) </div> --- ## What it is The native Bittensor metagraph tells you what's happening at the protocol layer. Metagraphed adds the **builder-facing layer it lacks**: a chain-direct block explorer (its own Rust indexer, no third-party RPC dependency), a registry of every subnet's public interfaces, endpoint health, and machine-readable schemas, and an agent toolkit — 200+ MCP tools, paste-ready OpenAI/Anthropic specs, a drop-in skill — built for **integration developers**, often reached through their AI agents. A live read-only RPC/WSS proxy and n --- **说明**：内容由公开仓库整理，使用前请自行核对是否适合你的场景。
安装方式
1. 打开仓库：https://github.com/JSONbored/metagraphed 2. 查找 SKILL.md 或 README 中的安装章节 3. 克隆或下载所需 Skill 子目录到本地 skills 路径（如 `.cursor/skills/` 或 `.claude/skills/`） 4. 重启 / 重载 Agent 客户端 5. 用一条真实任务验证 Skill 是否被正确加载
适用平台
- Cursor
- Claude
- Codex