Embedding Search

io.github.lazymac2xPublished by GitHub account lazymac2xv1.0.0Updated Oct 24, 2026

Cloudflare Workers MCP server: embedding-search

VerifiedStreamable HTTPWeb executableAI & ML

Overview

AI-generated overview

Remote MCP server that lets an assistant generate text embeddings, rank documents by semantic search, and score similarity between two texts.

What you can do
Generate 768-dimension vector embeddings for one or more texts using Cloudflare Workers AI (bge-base-en-v1.5). Rank a list of documents against a query by cosine similarity, returning the top-k matches with scores. Compute cosine similarity between two texts, with a score from -1 to 1. Useful for deduplication and judging relatedness.
When to use it
Use it when you need quick text vectors, semantic ranking over a small set of documents, or a similarity score to spot duplicates and related texts. It suits prototyping and light retrieval rather than self-hosted models or large-scale indexing.
Requirements
Network access to the remote endpoint at embeddings are produced by Cloudflare Workers AI, so no local package or runtime is needed.
Before you install
Text you send is passed to a third-party remote service (Cloudflare Workers AI) for embedding and comparison, so avoid confidential or personal content. No authentication is declared, so consider who can see the traffic.

Installation

In SourceWeft

  1. Open Embedding Search in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.lazymac2x%2Fembedding-search/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "embedding-search": {
      "type": "http",
      "url": "https://api.lazy-mac.com/embedding-search/mcp"
    }
  }
}

README

This repository has no README.

Tools

3

generate_embeddings

Generate vector embeddings for one or more texts using Cloudflare Workers AI (bge-base-en-v1.5, 768-dim).

Parameterstextrequiredmodel

compute_similarity

Compute cosine similarity between two texts. Returns score in [-1,1]. Useful for dedup and relatedness.

Parametersmodeltext_arequiredtext_brequired

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.