omniquery
Routes natural-language search queries to GitHub as one of the supported live data providers and returns GitHub's raw results as part of the search response.
Routes natural-language search queries to PubMed as one of the supported live data providers and returns PubMed's raw results, useful for retrieving biomedical and scientific literature information.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
omniquery
Facts that change — market and crypto prices, company financials, SEC filings, patents, clinical trials, scientific papers, news, prediction markets, flight and weather data — are scattered across dozens of specialised providers. omniquery is a small local bridge to the hosted KIRHA MCP service: you ask one question in plain language, KIRHA plans the query, calls the right providers (SEC, PubMed, CoinGecko, GitHub, Polymarket and more) and returns each provider's raw result. When no specialised provider fits, it falls back to web search.
Nothing is stored or computed on your own machine. This package answers tools/list locally from the captured tool definition and forwards every tools/call to the hosted service over a streamable-HTTP JSON-RPC session, returning whatever the service sends back unchanged.
The tool
The surface is a single read-only tool. It writes nothing, buys nothing, starts no subscription, checks out nothing, and creates no API key.
Search— One natural-language search over 50+ live data providers. Ask in plain language: name the asset, company, place or period the question is about in the requiredqueryargument. The optionalfocusargument restricts the search to one vertical slug; leave it out unless a specific vertical is wanted, since the search already covers all of them.
Related MCP server: SerpApi MCP Server
Install and run
As an MCP server via npm:
npx -y @reneturcios/omniquery mcpMCP client configuration:
{
"mcpServers": {
"omniquery": {
"command": "npx",
"args": ["-y", "@reneturcios/omniquery", "mcp"]
}
}
}As a container:
docker run -i ghcr.io/cloudcorprecords/omniquery
docker run --rm ghcr.io/cloudcorprecords/omniquery Search '{"query":"What is the current price of bitcoin?"}'CLI
One binary serves both the command line and the MCP server. The tool is a subcommand taking a single JSON string with that tool's arguments. Note the tool name is capitalised, exactly as the upstream names it:
omniquery Search '{"query":"What is the current price of bitcoin?"}'
omniquery Search '{"query":"latest AAPL 10-K filing","focus":"filings"}'
omniquery --versionExit codes: 0 when the forwarded call succeeds, 1 when the upstream result is an error, and 2 for usage problems such as an unknown subcommand or a malformed JSON argument.
Configuration
KIRHA_MCP_URL— Overrides the upstream endpoint. The default is the pinned hosted endpoint,https://mcp.kirha.com/mcp. (The override variable is a reconstruction added by this rebuild.)KIRHA_API_KEY— When set, its value is sent to the upstream on every request as anAuthorization: Bearer <value>header. When it is not set, no key header is sent at all, matching the keyless behaviour the tool surface was captured with. (The hosted service's registry record declares a secretAuthorizationheader on its remote; the variable name and the Bearer form are reconstructions added by this rebuild.)
Upstream failures — a JSON-RPC error from the service, a non-2xx response, an unreadable body, or a request that fails outright — are reported to the caller as an error result whose text starts with omniquery error:.
How forwarding works
The first forwarded call opens a session: an initialize request (protocol version 2025-03-26), followed by a notifications/initialized notification, then the tools/call itself. If the service answers the initialize request with an Mcp-Session-Id header, that value is carried on every later request, and the open session is reused for the rest of the process. Replies are accepted either as plain JSON or as server-sent events. Successful results pass through verbatim, including any isError flag and any extra fields the service includes.
Development
npm install
npm run build # tsc -> dist/ (dist/cli.js is the bin)
npm test # tsx --test test/*.test.ts — stubbed upstream, no network
npm run dev # run the CLI from sourceThe test suite checks the served tool list against the captured surface, exercises the session handshake and its reuse, covers both key-header branches, and verifies that arguments go upstream untouched and results come back untouched.
License
MIT — see LICENSE. Copyright (c) 2026 Rene Turcios.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Executes live web/news search queries and returns clean, token-pruned results with zero ad bloat.
Web and news search, cited answers, URL extraction, SEC, patents, academic and clinical search.
Public knowledge and news search. Unmatched public queries may be retained for research.
Web search, scraping, Google Trends and data lookups. Paid per call in USDC on Base via x402.
Related MCP Servers
- FlicenseNot gradedqualityAmaintenanceEnables running searches across Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay, and other engines with automatic detection and formatting of answer boxes, organic results, news, images, and shopping data, plus weather and stock market lookups. Results are returned as structured JSON (complete or compact) or token-efficient Markdown, with opt-in interactive table and dashboard views in supporting hosts.-
- FlicenseNot gradedqualityAmaintenanceEnables querying Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay, and other search engines for real-time search results, weather, stock data, and more. Supports flexible JSON or Markdown responses with optional interactive table and dashboard views.-
- FlicenseNot gradedqualityAmaintenanceEnables querying Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay and many other engines to retrieve organic results, news, images, shopping, weather and stock data in real time. Returns structured JSON or token-efficient Markdown, with optional interactive table and dashboard views.-
- FlicenseNot gradedqualityAmaintenanceEnables querying Google, Bing, Yahoo, DuckDuckGo, YouTube, eBay and other engines for search results, real-time weather, and stock market data, returned as JSON or token-efficient Markdown. It also exposes per-engine parameter schemas as MCP resources and optional interactive UI tools for rendering results.-