
querying
io.github.OPACTOR-DEV/querying
AI engine answers with sources, prompt research and GEO monitors for ChatGPT, Gemini, Perplexity.
Documentation
querying.ai plugins
Plugins that connect AI coding agents to querying.ai: answers and cited sources from ChatGPT, Gemini, Perplexity, Google AI Overviews, Copilot and other AI engines, prompt research, and GEO monitors.
Every client talks to the remote MCP server https://mcp.querying.ai/mcp. The first time the agent uses it, your browser opens the querying.ai sign-in page; approve the connection and the agent is connected to your account. You can see and disconnect connected apps at https://querying.ai/dashboard/keys.
Install
Claude Code:
claude plugin marketplace add OPACTOR-DEV/querying-plugins
claude plugin install querying@querying
Then run /mcp and choose Authenticate for querying.
Codex:
codex plugin marketplace add OPACTOR-DEV/querying-plugins
Then open the plugin directory in Codex and install querying.ai. If Codex does not open the sign-in page, run codex mcp login querying.
Cursor: add this repository as a plugin marketplace and install querying. Cursor shows a Connect button for the server.
Gemini CLI:
gemini extensions install https://github.com/OPACTOR-DEV/querying-plugins
Then run /mcp auth querying.
Any other MCP client: add a Streamable HTTP server at https://mcp.querying.ai/mcp. Clients that support MCP authorization sign in on their own. For a client without a browser, such as a CI job, send the header Authorization: Bearer <key> with an API key from https://querying.ai/dashboard/keys. Agents that read Agent Skills can use skills/querying/SKILL.md.
Layout
plugins/querying/: the plugin for Claude Code, Codex and Cursor (manifests, MCP config, skill, icons).gemini-extension.json,GEMINI.md: the Gemini CLI extension at the repository root.skills/querying/: the skill, copied intoplugins/querying/skills/bynode scripts/sync-skill.mjs.server.json: the MCP Registry entry.
Docs: https://docs.querying.ai. License: MIT.
No installation packages available.