vector-mcp
Active·★ 16·MIT·Updated 2026-10-22
Vector Mcp is a production-grade Agent and Model Context Protocol (MCP) server designed to integrate RAG into AI agents and support multiple vector database technologies. It features consolidated, action-routed tools to optimize token usage and includes enterprise-grade security, an integrated graph agent, and native telemetry.
#Agent#Vector Database#RAG#LLM Tools#Model Context Protocol#API#Security#Telemetry
01
Features
01Consolidated Action-Routed MCP Tools: Minimizes token overhead and eliminates tool bloat in LLM contexts.
02Enterprise-Grade Security: Supports Eunomia policies, OIDC token delegation, and granular execution context tracking.
03Integrated Graph Agent: Built-in Pydantic AI agent supporting the Agent Control Protocol (ACP) and standard Web interfaces (AG-UI).
04Native Telemetry & Tracing: Out-of-the-box OpenTelemetry exports and native Langfuse tracing.
02
Compatibility
Python
Runtime
Verified via docs
Docker
Containerization
Verified via docs
Vector Databases
Integration
Verified via docs
OpenAI
LLM Provider
Verified via docs
OpenTelemetry
Telemetry
Verified via docs
Langfuse
Tracing
Verified via docs
03
Quick start
1
$ uv pip install vector-mcp[all]
04
Use cases
↳Integrating Retrieval Augmented Generation (RAG) into AI agents via an MCP server to provide external knowledge.
↳Building and managing AI agents with dynamic, optimized toolsets for complex tasks in production environments.
↳Securing agent operations with fine-grained access control, OIDC token delegation, and runtime security features like prompt injection defense.
↳Deploying and orchestrating multi-agent systems using Docker Compose, including Web UI and Terminal interfaces.
05
Alternatives
emotion_ai★ 13
The Aura Emotion AI system has chroma with a local embedding model, memvid qr code mp4 infinite memory, brainwave and neurochemical simulations, sociobiological reasoning, autonomous subsystem processing with a Gemini flash model so the main model is less taxed, is a MCP client with adaptive tool learning and MCP server.
itasca-mcp★ 219
MCP server connecting AI agents to ITASCA engines (PFC, FLAC, 3DEC, MPoint, MassFlow) — run numerical simulations through natural conversation
DuDuClaw★ 50
Open-source AI Agent platform — 80+ MCP tools, 7 channels (Slack/Discord/LINE/Telegram), Rust + Python. Self-hostable Claude/GPT alternative for production multi-LLM systems.
deer-flow★ 84.3k
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
tachyon★ 37
💫 Tachyon MCP Runtime for JVM - a Java Model Context Protocol server with Streamable HTTP, native Netty transports, tasks, resources, prompts, resumable sessions, and stateless deployment support.
Comments
Log in to leave a comment
No comments yet. Be the first!