Enterprise DNA Enterprise DNA
M MCP Servers Developer low

Battam1111/omniseek

by Various

Your agent seeks what search can't find. A self-hosted perception MCP server that transcribes speech, reads behind logins, sees images and video frames, crosses languages, and reme

MCP

Battam1111/omniseek

Added 8 Sept 2026

#agents #ai-agents #deep-research #knowledge-graph #llm #mcp #mcp-server #model-context-protocol

Overview

A self-hosted perception MCP server that provides agents with capabilities beyond typical web search. It transcribes speech, reads content behind logins, interprets images and video frames, translates across languages, and retains context. The project is written in Python and is available on GitHub.

Best for

Best for
Developers building self-hosted agents that need multimodal perception and login-gated access.

Use cases

  • Give an agent access to audio or video content for transcription and analysis
  • Retrieve information from authenticated pages where standard search fails
  • Let an agent work across languages and remember prior context in a session

How to use

Tools exposed

  • omniseek_search
  • omniseek_read
  • omniseek_view
  • omniseek_transcribe
  • omniseek_field_skeleton
  • omniseek_resolve_identity
  • omniseek_coauthors
  • omniseek_institution_cohort
  • omniseek_paper_enrich
  • omniseek_paper_recommend
  • omniseek_graph
  • omniseek_sensor
  • omniseek_ruling
  • omniseek_statement
  • omniseek_curator_act
  • omniseek_curator_view
  • omniseek_gather
  • omniseek_sources

Tested with

Claude Code

Notes

A self-hosted perception MCP server that provides agents with capabilities beyond typical web search. It transcribes speech, reads content behind logins, interprets images and video frames, translates across languages, and retains context. The project is written in Python and is available on GitHub.

49 stars on GitHub. Last updated 2026-09-07. Licensed Apache-2.0.

Use cases

  • Give an agent access to audio or video content for transcription and analysis
  • Retrieve information from authenticated pages where standard search fails
  • Let an agent work across languages and remember prior context in a session

Pros

  • Self-hosted, so data and credentials stay under your control
  • Broad perception stack in one MCP server: audio, visual, multilingual
  • Tightly integrated as an MCP server for agent workflows

Cons

  • Small project with 49 stars, so limited community validation
  • Requires self-hosting and configuration for each capability
  • Documented features exceed what the repo README explicitly confirms

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Self-hosted, so data and credentials stay under your control
  • Broad perception stack in one MCP server: audio, visual, multilingual
  • Tightly integrated as an MCP server for agent workflows

Cons

  • Small project with 49 stars, so limited community validation
  • Requires self-hosting and configuration for each capability
  • Documented features exceed what the repo README explicitly confirms

Open-source & AI alternatives

Swap-in tools that solve the same job. Weigh the trade-offs before you commit.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks