Acme

Built with
Ever Works
Ever Works

Connect with us

Stay Updated

Get the latest updates and exclusive content delivered to your inbox.

Product

  • Categories
  • Tags
  • Pricing
  • Help

Clients

  • Sign In
  • Register
  • Forgot password?

Company

  • About Us
  • Admin
  • Sitemap

Resources

  • Blog
  • Submit
  • API Documentation
All product names, logos, and brands are the property of their respective owners. All company, product, and service names used in this repository, related repositories, and associated websites are for identification purposes only. The use of these names, logos, and brands does not imply endorsement, affiliation, or sponsorship. This directory may include content generated by artificial intelligence.
Copyright © 2025 Acme. All rights reserved.·Terms of Service·Privacy Policy·Cookies
  1. Home
  2. Data Access & Integration Mcp Servers
  3. mcp-vector-search

mcp-vector-search

An MCP server providing semantic data search using embeddings and similarity matching. Facilitates AI-powered, context-aware data retrieval for development teams.

🌐Visit Website

About this tool

Surveys

Loading more......

Information

Websitegithub.com
PublishedMay 14, 2025

Categories

1 Item
Data Access & Integration Mcp Servers

Tags

5 Items
#mcp
#semantic-search
#vector-database
#ai-integration
#data-access

Similar Products

6 result(s)
chroma-mcp

A server providing data retrieval capabilities powered by the Chroma embedding database, enabling AI models to create and retrieve data collections using vector search, full text search, and metadata filtering.

mcp-pinecone

A Pinecone MCP server providing vector search capabilities over Pinecone through the Model Context Protocol.

Vector Search MCP Server

A purpose-built MCP server that enables semantic data retrieval via vector embeddings, allowing AI systems to perform meaning-based searches in large datasets. Qdrant is a leading example, offering standard protocols for vector operations.

directus-server

Bridges AI tools with Directus headless CMS, enabling content operations through automatically generated MCP-compatible tools based on the instance schema.

graphrag-mcp

Combines Neo4j and Qdrant databases for document search with semantic relevance and context, serving as a powerful MCP server for structured and vector search.

mcp-server-tavily

MCP server for accessing Tavily AI search API, offering advanced search within the MCP framework.

mcp-vector-search

Category: Data Access Integration MCP Servers
Tags: mcp, semantic-search, vector-database, ai-integration, data-access

Description

mcp-vector-search is a Model Context Protocol (MCP) server that enables semantic data search using vector embeddings and similarity matching. It facilitates AI-powered, context-aware data retrieval, specifically designed for querying transcript segments stored in a Turso database. Users can ask questions and receive relevant transcript segments, with results ranked by semantic similarity.

Features

  • Vector similarity search for transcript segments using embeddings
  • Relevance scoring based on cosine similarity
  • Transcript metadata in results (episode title, timestamps)
  • Configurable search parameters:
    • Limit number of results (default 5, max 50)
    • Minimum similarity score threshold (default 0.5, range 0-1)
  • Efficient database connection pooling for performance
  • Comprehensive error handling
  • Performance optimized for quick responses
  • API endpoint: search_embeddings for semantic search
  • Expects a Turso database with tables for embeddings and transcripts
  • Complete development workflow (clone, install, build, run dev, publish)

API Details

  • Endpoint: search_embeddings
    • Parameters:
      • question (string, required): Query text
      • limit (number, optional): Number of results
      • min_score (number, optional): Minimum similarity
    • Response: JSON array of results including episode title, segment text, start/end time, similarity score

Database Schema

Expects a Turso database with two tables:

  • embeddings: id, transcript_id, embedding (vector)
  • transcripts: id, episode_title, segment_text, start_time, end_time

Source Code

GitHub: spences10/mcp-embedding-search

Pricing

No pricing information provided; open source under MIT License.