Wet MCP vs OmniSeek — MCP Server Comparison | AllMCPs
Side-by-Side Model Context Protocol Comparison
Wet MCP vs OmniSeek
In-depth architectural comparison of the Wet MCP and OmniSeek MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
Wet MCP
Search & Data Extraction · Local stdio
Quality: 59/100 (Good) | Auth: No auth required
OmniSeek
Search & Data Extraction · Remote HTTP/SSE
Quality: 55/100 (Good) | Auth: No auth required
Verdict Summary: Choose Wet MCP if you need specialized Search & Data Extraction tools running via a local process. Choose OmniSeek if your workspace requires Search & Data Extraction integration with remote web transport. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose Wet MCP when:
You need dedicated capabilities in the Search & Data Extraction domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Web search (embedded SearXNG), content extraction, and library docs indexing with hybrid search (FTS5 + semantic). Built-in Qwen3 embedding, no API keys required.
Your agent seeks what search can't find. A self-hosted perception MCP server.
Wet MCP is categorized under Search & Data Extraction and uses a local stdio subprocess. In contrast, OmniSeek belongs to Search & Data Extraction using remote streaming HTTP/SSE transport. Select Wet MCP when you need capabilities focused on search & data extraction and OmniSeek when you require tools for search & data extraction.
Re-trigger the zero-config relay setup flow (prints a fresh relay URL for the browser form). Registered via `mcp-core`'s `register_open_relay_tool` so an LLM can restart setup without a manual restart.
OmniSeek Tools (18)
omniseek_search
Fan out across the whole catalog, deduplicate, rank. Cross-lingual (semantic + lexical).
omniseek_read
Normalize any URL or document (web page, PDF, arXiv) into clean text.
omniseek_view
Read images, document figures, video frames with vision.
omniseek_transcribe
Transcribe audio/video locally. Bilingual ASR, sliceable by timestamp.
omniseek_field_skeleton
Map a research field's citation neighborhood: foundational core vs. frontier.
omniseek_resolve_identity
Resolve a person's name to candidate author IDs across databases.
omniseek_coauthors
Map a researcher's collaboration network by joint-paper count.
omniseek_institution_cohort
List who actively publishes at a lab, scoped to a field.
omniseek_paper_enrich
Open-access PDF, retraction/integrity status, citation count for a paper.
omniseek_paper_recommend
Semantically similar papers (SPECTER embeddings) that keyword search misses.
omniseek_graph
Query the accumulated evidence graph: find, neighborhood, between, since, similar.
omniseek_sensor
Standing queries with novelty detection. Only tells you what is new.