加载中…
Text-blind context control plane for AI agents. Select high-utility context under token budgets.
Omneum 是 ChatHome Skills 收录的 MCP 条目,来源为 Official MCP Registry,质量分 56/100。 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。该条目暂无自动安装命令,请查阅仓库获取手动安装说明。 在将 Omneum 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。
查看来源文档运行此命令前,请先核对上游源码。
{
"_meta": {
"io.modelcontextprotocol.registry/official": {
"status": "active",
"isLatest": true,
"updatedAt": "2026-10-26T01:18:55.985349Z",
"publishedAt": "2026-10-26T01:18:55.985349Z",
"statusChangedAt": "2026-10-26T01:18:55.985349Z"
}
},
"server": {
"name": "io.github.cole-h06/omneum",
"_meta": {
"io.modelcontextprotocol.registry/publisher-provided": {
"installation": {
"runtime": "Host-provided Node.js >=18 for the MCPB launcher; Python 3.11–3.14 for Omneum.",
"instructions": "Using a Python 3.11–3.14 virtual environment, run python -m pip install 'omneum==1.1.0', then omneum install from your normal login account, without sudo. Approve administrator access when requested. Run command -v omneum-server. For direct stdio configuration, use that absolute executable path as the client's command. Alternatively, import the MCPB in a compatible host with Node.js >=18 and select that path. Use the same login account. Node.js is required only for the MCPB launcher. The published launcher bundle remains version 1.0.4; use these 1.1.0 installation instructions instead of its embedded 1.0.4 guidance. The connector requires the installed evaluator service and does not install the package or daemon.",
"setupCommand": "omneum install",
"pythonPackage": "omneum==1.1.0",
"stdioExecutable": "omneum-server",
"supportedPlatforms": [
"macOS arm64",
"macOS x86_64",
"Ubuntu 22.04+ x86_64"
],
"requiresExistingInstallation": true
}
}
},
"icons": [
{
"src": "https://raw.githubusercontent.com/cole-h06/omneum/main/assets/omneum-logomark-dark-bg.svg",
"sizes": [
"any"
],
"mimeType": "image/svg+xml"
}
],
"title": "Omneum",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "1.0.9",
"packages": [
{
"version": "1.0.4",
"transport": {
"type": "stdio"
},
"fileSha256": "0fe8b402628ac034b197034bf4c12682fd1e8640554580e561b65561e2b22a2d",
"identifier": "https://github.com/cole-h06/omneum/releases/download/v1.0.4/omneum-local-1.0.4.mcpb",
"registryType": "mcpb"
}
],
"repository": {
"url": "https://github.com/cole-h06/omneum",
"source": "github"
},
"websiteUrl": "https://github.com/cole-h06/omneum/blob/v1.1.0/docs/guides/installation.md",
"description": "Text-blind context control plane for AI agents. Select high-utility context under token budgets."
}
}