MCP Catalogs
Home

aura

by mezmo·63·Score 46

A production-ready AI agent framework with MCP tool integration, RAG pipelines, and OpenAI-compatible API.

ai-llmdeveloper-toolsproductivity
12
Forks
39
Open issues
this month
Last commit
2d ago
Indexed

Overview

Aura is a Rust-based framework for building and composing AI agents from declarative TOML configuration files. It provides MCP tool discovery across multiple transport protocols (HTTP, SSE, STDIO), automatic schema sanitization for OpenAI compatibility, and RAG pipeline integration with both in-memory and external vector stores. The framework supports multi-agent orchestration with a coordinator/worker architecture that enables dependency-aware, parallel execution with iterative re-planning capabilities.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Building multi-agent AI systems with specialized worker agents
you:Creating production-ready chat applications with MCP tool integration
you:Implementing RAG pipelines for knowledge-augmented AI assistants
you:How do I add MCP tools to my agent?
you:Can I use client-side tools?

When to choose this

Choose Aura when you need to build production-ready multi-agent systems with tool calling, RAG integration, and an OpenAI-compatible API.

When NOT to choose this

Don't choose Aura if you need simple single-agent deployments, have limited Rust expertise, or require extensive client-side tooling without accepting security risks.

Tools this server exposes

6 tools extracted from the README (low confidence)
  • query_postgres

    Query a PostgreSQL database

  • create_github_issue

    Create a new GitHub issue

  • list_files

    List files in a directory

  • read

    Read the contents of a file

  • find

    Find files matching a pattern

  • get_current_time

    Get the current time

Note: Tool names were inferred from the documentation about client-side tools and examples. The README doesn't clearly document the specific MCP tools exposed by the server, only that it supports MCP tool discovery.

Comparable tools

rigmcp-serverlanggraphcrewaiautogen

Installation

Installation

  1. Install Rust:
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
  1. Clone and configure:
git clone https://github.com/mezmo/aura
cd aura
cp examples/reference.toml config.toml
  1. Set required environment variables:
export OPENAI_API_KEY="your-api-key"
  1. Build:
cargo build --release
  1. Run the web server:
cargo run --bin aura-web-server

FAQ

How do I add MCP tools to my agent?
Configure tools in your TOML config file using the `tools` section. Aura supports dynamic MCP tool discovery across HTTP, SSE, and STDIO transports.
Can I use client-side tools?
Yes, but with caution. Set `enable_client_tools = true` in your agent configuration and optionally specify a `client_tool_filter` to limit available tools. This requires trusting the model and clients with local execution privileges.

Compare aura with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.