加载中…
Let your users work with their own data through an AI assistant, limited to what they can see.
Nhost 是 ChatHome Skills 收录的 MCP 条目，来源为 Official MCP Registry，质量分 73/100。 作为 Model Context Protocol 服务器，它向 Claude、Cursor、Copilot 等兼容 MCP 的 LLM 客户端暴露可直接调用的工具，让 agent 的能力超出模型内置范围。 该条目由 ChatHome Skills 的每日抓取从官方 registry 和 GitHub 发现查询中收录，每次运行都会重新核验仓库事实、新鲜度信号和安装元数据。 质量分综合了官方 registry 收录情况、可用安装命令、许可证完整性、仓库活跃度和 GitHub star 趋势，完整算法说明见来源页。安装命令已列于上方，可直接复制使用。 在将 Nhost 加入生产 agent 工作流前，请核对上方的最近更新日期和仓库状态——下方事实快照是最近一次抓取的时点值。
docker run -i --rm docker.io/nhost/mcp:0.3.0运行此命令前，请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-09-18T08:15:16.26472Z",
"publishedAt": "2026-09-18T08:15:16.26472Z",
"statusChangedAt": "2026-09-18T08:15:16.26472Z"
}
},
"server": {
"name": "io.github.nhost/mcp",
"icons": [
{
"src": "https://docs.nhost.io/favicon.svg",
"sizes": [
"any"
],
"mimeType": "image/svg+xml"
},
{
"src": "https://app.nhost.io/assets/favicon.png",
"sizes": [
"128x128"
],
"mimeType": "image/png"
}
],
"title": "Nhost",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "0.3.0",
"packages": [
{
"transport": {
"url": "http://localhost:3000/",
"type": "streamable-http"
},
"identifier": "docker.io/nhost/mcp:0.3.0",
"runtimeHint": "docker",
"registryType": "oci",
"runtimeArguments": [
{
"name": "-p",
"type": "named",
"value": "3000:3000"
}
],
"environmentVariables": [
{
"name": "MCP_GRAPHQL_ENDPOINT",
"isRequired": true,
"description": "GraphQL endpoint of the Nhost project the server exposes, e.g. http://hasura-service:8080/v1/graphql"
},
{
"name": "MCP_AUTH_URL",
"isRequired": true,
"description": "Nhost Auth URL used as the OAuth2 authorization server, e.g. https://SUBDOMAIN.auth.REGION.nhost.run/v1"
}
]
}
],
"repository": {
"id": "337414495",
"url": "https://github.com/nhost/nhost",
"source": "github",
"subfolder": "services/mcp"
},
"websiteUrl": "https://docs.nhost.io/products/ai/mcp",
"description": "Let your users work with their own data through an AI assistant, limited to what they can see."
}
}