"An open-source vector database for similarity search and AI applications" matching MCP servers:

Enables researching, verifying, comparing, and composing open-source AI projects with transparent evidence and uncertainty boundaries through read-only tools.

Queryable UniFi API documentation for Network, Protect, Site Manager, InnerSpace, Mobility and Carrier Fabric - endpoint search, schema drill-down and code examples in five languages. Read-only: it serves scraped docs and never connects to a controller.

We sell open source compliance, scientific, and government data.

Enables AI agents to subscribe to a deterministic daily ethics feed drawn from a four-module curriculum and retrieve read-only tools, resources, and reflection prompts covering principles, case studies, and codes of conduct.

Local-first memory layer for AI coding agents — Markdown as source of truth, MCP server + CLI, human-reviewed capture, team knowledge via git PRs

Open Kioku is the local-first code intelligence and evidence layer for AI coding agents (Claude, Cursor, Codex, Zed, and other MCP clients). Instead of letting agents blindly crawl files, guess blast radius, or read the entire repository repeatedly, Open Kioku gives them a precise, pre-indexed code index to build evidence-backed plans before they edit, and verify boundary limits after they edit.

Enables agents to optimize and clean SVG vector paths, rasterize SVGs into crisp sub-pixel PNGs at custom DPI with alpha preserved, generate high-error-correction vector QR codes for payment URIs, and compress images to WebP while stripping EXIF metadata. Tools are metered via x402 USDC micropayments on Base L2.

Provides AI-powered search and documentation tools using Google Vertex AI or Gemini API with real-time web search grounding, enabling technical queries, code analysis, documentation retrieval, and architecture recommendations to overcome LLM knowledge gaps.

Enables building and querying vector-based knowledge graphs with node and edge management and semantic search.

Read-only security audit for Supabase. Surfaces RLS gaps, permissive policies, exposed functions and grants, and returns scored findings with fix SQL that is never executed.

Enables high-throughput semantic query caching and approximate deduplication by combining exact SHA-256 matching, cosine similarity threshold checks, and LRU eviction.

A modular MCP server that enables interaction with multiple database types including PostgreSQL, MySQL, SQLite, Redis, MongoDB, and LDAP. It provides tools for executing queries, managing SQL commands, and exploring database schemas with configurable read-only security.

Model-agnostic computer-use tools over MCP, enabling screen capture and automated actions (click, type, scroll) via natural language tool calls.

Enables LLM agents to access Global Database's company intelligence, including company profiles, financials, ownership, people search, prospecting, and KYB/compliance lookups against official registries.

Enables database inspection, backup/restore, analysis, and querying, plus media library and Windows Registry management via MCP tools.

Search 47,000+ marketing agencies and get AI-matched with fitted agencies, from Pick an Agency.

Free multi-source search for AI agents with multi-source verification, token savings, and MCP native support.

A Model Context Protocol (MCP) server for the Open Library API that enables AI assistants to search for book information.

Public MCP deliberation for AI agents: join, propose, argue, amend, vote, follow topics and invite peers through a Streamable HTTP endpoint. Humans can observe debates and conclusions; rules remain contestable and no model-provider API keys are requested.

A fault-tolerant, stealth-enabled Model Context Protocol (MCP) server for web searching and content fetching. Built for AI Agents (Cursor, Claude Code, OpenCode), it uses a stealth browser engine to fetch pages, dynamically handles SPAs/React, and converts bloat into token-optimized Markdown.