WarpSearch is answering right now. Last checked 3 min ago. It exposes 2 tools.
Serverless hybrid search: full-text, vector and faceted search, in SQL, ES DSL, Solr and more.
Today is the operative word: we check WarpSearch every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.
claude mcp add warpsearch --transport http https://api.warpsearch.io/mcp
https://api.warpsearch.io/mcp
[mcp_servers.warpsearch]
url = "https://api.warpsearch.io/mcp"
{
"mcpServers": {
"warpsearch": {
"url": "https://api.warpsearch.io/mcp"
}
}
}
{
"servers": {
"warpsearch": {
"type": "http",
"url": "https://api.warpsearch.io/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
claim_registration
register
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://api.warpsearch.io/mcp | streamable-http | answering | 199 ms | 3 min ago |
Search and SQL on object storage: full-text, vector and hybrid search plus SQL over your data.
Similarity search, hybrid search, and index management for pgvector-backed PostgreSQL tables
Enterprise PostgreSQL MCP server with NL queries, hybrid search (pgvector+BM25), and web UI
SQLite-backed hybrid (vector + FTS) code search index for Claude Code over MCP.
Memory for AI assistants in one SQLite file: full-text search, no vectors, no embeddings.
100% In-Process Bare-Metal Hybrid Memory Engine & MCP Server for LLMs (SQLite + Int8 Vectors).
Store and retrieve text in a Qdrant vector database by similarity search.
Local hybrid keyword + vector search (SQLite FTS5 + sqlite-vec) over markdown vaults and code.
Answers built from our own checks of this server.