OmniSeek is a Model Context Protocol (MCP) server: Your agent seeks what search can't find. A self-hosted perception MCP server. In practice that means any MCP-compatible AI assistant can call OmniSeek's tools directly — the model decides when to use them in a conversation or agent run.
It runs locally: the Python package omniseek (via uvx) speaks MCP over stdio on your machine. No credentials are required — it works out of the box. The current release is v0.2.0, published under the Apache-2.0 license, with source at Battam1111/omniseek on GitHub, where it has earned 47 stars.
OmniSeek is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain OmniSeek for Battam1111, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
▸PyPI package — omniseek · MCP over stdio
▸Docker image — ghcr.io/battam1111/omniseek:v0.2.0 · MCP over stdio