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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.