Omniboard MCP
MCP server that exposes actionable Omniboard checks for the current project to a local agent.
README
Omniboard.dev MCP
MCP server that exposes actionable Omniboard checks for the current project to a local agent.
The server resolves the current project name using the same project-resolution
approach as @omniboard/analyzer, retrieves Omniboard settings, then asks the
API for actionable check results for that project.
Environment
OMNIBOARD_API_KEY_MCP is required and should be passed through the MCP client
configuration, not assumed from the shell that starts the agent.
Optional
OMNIBOARD_API_URL is optional and defaults to https://api.omniboard.dev
OMNIBOARD_API_KEY is optional. Provide it only when agents should be allowed
to run @omniboard/analyzer during the actionable-check validation prompt.
Registering The MCP Server
The server uses the standard MCP stdio transport. Configure your agent to run
the package with npx and pass OMNIBOARD_API_KEY_MCP in the MCP server env.
Claude Desktop, Cursor, and other JSONC clients
Use this shape for clients that accept MCP server JSONC configuration, including Claude Desktop and Cursor:
{
"mcpServers": {
"omniboard": {
"command": "npx",
"args": ["-y", "@omniboard/mcp"],
"env": {
"OMNIBOARD_API_KEY_MCP": "your-api-key",
"OMNIBOARD_API_KEY": "your-api-key" // optional, enables analyzer validation
}
}
}
}
Codex config.toml
Add this to ~/.codex/config.toml:
[mcp_servers.omniboard]
command = "npx"
args = ["-y", "@omniboard/mcp"]
startup_timeout_sec = 30
[mcp_servers.omniboard.env]
OMNIBOARD_API_KEY_MCP = "your-api-key"
OMNIBOARD_API_KEY = "your-api-key" # optional, enables analyzer validation
Tools
omniboard_list_actionable_checks
Returns the actionable checks that currently have results for the resolved project.
omniboard_get_actionable_check_results
Returns the result context for the check. The API owns the result DTO, so the
MCP passes it through as result. The response also includes agentContext,
which tells the agent to use all returned context to resolve the actionable
check, run relevant local verification, and optionally validate with the
omniboard_validate_actionable_check_fix tool when OMNIBOARD_API_KEY is
available.
omniboard_validate_actionable_check_fix
Optionally validates whether an attempted fix resolved an actionable check. When
OMNIBOARD_API_KEY is not available, the tool returns a skipped result and does
not run validation.
When the key is available, the tool runs:
npx @omniboard/analyzer --ak <OMNIBOARD_API_KEY> --cp <check-name> --json
It then inspects the generated JSON at ./dist/omniboard.json, returns whether
the check is resolved or still matches, and removes the generated JSON file
before completing.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。