# ls-search MCP server

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

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-calbearken-ls-search
- Repository: https://github.com/CalBearKen/TRACE
- Website: https://liangsearch.aioniq.ai

## Install
- Endpoint: https://liangsearch.aioniq.ai/mcp
- Auth: Not captured

## Setup notes
- Remote endpoint: https://liangsearch.aioniq.ai/mcp

## Tools
- 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. Endpoint: https://liangsearch.aioniq.ai/mcp
- 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. Endpoint: https://liangsearch.aioniq.ai/mcp
- 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. Endpoint: https://liangsearch.aioniq.ai/mcp
- trace_get_passage - Retrieve a single stored passage/document/item (content and metadata) from your workspace vector index by item id. Endpoint: https://liangsearch.aioniq.ai/mcp
- 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. Endpoint: https://liangsearch.aioniq.ai/mcp
- 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. Endpoint: https://liangsearch.aioniq.ai/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.CalBearKen
- Version: 1.0.1
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 24, 2026
- Source: https://registry.modelcontextprotocol.io