Ls Search MCP Server

io.github.CalBearKen/ls-search

answering

Ls Search is answering right now. Last checked 3 min ago. It exposes 6 tools.

Disposable private vector search + semantic RAG for AI agents. x402 pay-per-call, no account.

The linked repository no longer exists on GitHub — it was deleted or made private.

Uptime history 39 hours of history

39 hours agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

93 ms

Response time

average over 24h

open, no key

Access

streamable-http

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add ls-search --transport http https://liangsearch.aioniq.ai/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "ls-search": {
      "url": "https://liangsearch.aioniq.ai/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.ls-search]
url = "https://liangsearch.aioniq.ai/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "ls-search": {
      "url": "https://liangsearch.aioniq.ai/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "ls-search": {
      "url": "https://liangsearch.aioniq.ai/mcp"
    }
  }
}

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

trace

trace_create_workspace

Create an isolated, disposable (ephemeral) vector-search workspace - your own sandboxed index/namespace for semantic retrieval and RAG. Prepays container time via x402 micropayment (USDC on Base, EIP-3009); no account, no signup. Call without x_payment to get the price + payment terms; with a signed x_payment it returns a one-time capability_token for the other tools.

trace_dispose_workspace

Dispose and permanently delete the workspace and its in-memory vector index/data (zero data retention); returns a cryptographically signed disposal receipt confirming the wipe.

trace_get_passage

Retrieve a single stored passage/document/item (content and metadata) from your workspace vector index by item id.

trace_get_usage

Get workspace usage and billing status for your disposable vector-search workspace: prepaid time/TTL remaining, total spend, ingest/search counts, and state.

trace_ingest_batch

Ingest and index documents, passages or text chunks into your workspace to build the searchable vector/embedding index for semantic search and RAG retrieval. Each document: {name, text OR content_b64, mime?}; supports text and binary (base64) content.

trace_search

Semantic vector search / similarity retrieval (nearest-neighbor, embedding-based) over your private disposable index - the core RAG retrieval call. Supports natural-language text queries, cross-modal text->image, and reverse-image search (image_b64). Returns ranked passages/hits with locators. Provide query OR image_b64.

Endpoints

URL	Transport	State	Latency	Checked
https://liangsearch.aioniq.ai/mcp	streamable-http	answering	113 ms	3 min ago

Ls Search — questions

Answers built from our own checks of this server.

What can Ls Search do?

It exposes 6 tools, read directly from the server on our last check. Among them: trace_create_workspace, trace_dispose_workspace, trace_get_passage, trace_get_usage, trace_ingest_batch, trace_search. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Ls Search working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 93 ms. The bar chart above shows every period we have measured.

Is Ls Search still maintained?

The linked repository no longer exists on GitHub — it was deleted or made private. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.

How do I connect Ls Search?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Ls Search need an API key?

No. Ls Search completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Ls Search?

It answers our handshake in 93 ms on average, which is faster than 85% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.