Embedding Search
Give your coding agent semantic search over embeddings while you add RAG, in-app search, or knowledge retrieval to your product.
Overview
io.github.lazymac2x/embedding-search is a Build-phase MCP server that exposes embedding search to your agent via Cloudflare Workers streamable HTTP.
What is this MCP server?
- embedding-search MCP served from https://api.lazy-mac.com/embedding-search/mcp
- Streamable-http remote MCP on Cloudflare Workers
- Version 1.0.0 with GitHub repo embedding-search-api
- Supports RAG and semantic lookup patterns in agent-driven development
- Complements build-phase backend and integrations work for search features
- Server version 1.0.0 in MCP manifest
- 1 streamable-http remote at api.lazy-mac.com/embedding-search/mcp
- Described as Cloudflare Workers MCP server
What problem does it solve?
You need semantic search in your app or RAG pipeline but do not want to context-switch away from the agent while prototyping retrieval.
Who is it for?
Indie builders adding RAG, doc search, or semantic product discovery who already use MCP in Claude Code or Cursor.
Skip if: Teams that require self-hosted only, strict data residency, or enterprise vector ops without reviewing the lazy-mac hosted API terms.
What do I get? / Deliverables
Your agent can invoke embedding-search MCP tools remotely so you prototype and integrate semantic lookup faster during the build.
- MCP-connected semantic search callable from the agent
- Faster iteration on RAG and search API design
- Link-out implementation details via embedding-search-api on GitHub
Recommended MCP Servers
Journey fit
Vector search is a build-time capability you wire into backends and agent tools, not a pre-build ideation exercise. Agent-tooling is the shelf for MCP servers that extend what the agent can query—not generic frontend polish.
How it compares
Hosted embedding-search MCP integration, not a local LanceDB skill or full vector platform UI.
Common Questions / FAQ
Who is io.github.lazymac2x/embedding-search for?
Developers building agent features or SaaS search who want MCP-accessible embedding search during implementation.
When should I use io.github.lazymac2x/embedding-search?
Use it while building retrieval, RAG, or in-app semantic search and you want the coding agent to query or test search behavior through MCP.
How do I add io.github.lazymac2x/embedding-search to my agent?
Add https://api.lazy-mac.com/embedding-search/mcp as a streamable-http MCP remote in your agent configuration, reload tools, and call from prompts that need semantic lookup.