An SRE agent platform that automates incident investigation and production infrastructure management using multi-agent workflows.
Also known as mezmo/aura
- Stars
- 412
- Tools
- —
- Downloads, 30 days
- —
- Latest version
- —
- Last commit
- Nov 12, 2026
- License
- Apache-2.0
What is AURA MCP?
AURA is an SRE agent platform that automates incident investigation and production infrastructure management using multi-agent workflows.
Summary generated from the project's README
About AURA MCP server
Automating incident investigation and production infrastructure management is what AURA enables through multi-agent workflows. Site reliability engineers can deploy this platform on Linux or macOS using an install script to run agents locally or as a webserver service. The system connects to various model providers including OpenAI, Anthropic, Bedrock, Gemini, Ollama, and OpenRouter, allowing teams to switch providers via configuration changes.
Users manage the entire agent system through reviewable TOML files that define specialist teams, prompts, and approval policies. The platform integrates with a wide range of tools such as Kubernetes, AWS, Datadog, Prometheus, and Slack to correlate logs, metrics, and traces. To ensure safety, sensitive actions can be placed behind human approval requirements via webhooks or in-conversation prompts. Every orchestration decision and tool call can be exported as OpenTelemetry traces for end-to-end investigation.
What you can do with it
- 1Correlate telemetry to find regressionsAn AI agent can investigate a payment failure by analyzing Mezmo traces, Prometheus latency, and Kubernetes deployment history to identify a specific service regression.
- 2Automate incident response workflowsYou can instruct an agent to investigate incidents, check on-call schedules in PagerDuty, and post updates to Slack channels.
- 3Manage infrastructure with human oversightDevelopers can set up policies that require explicit human approval before any sensitive tool calls are executed in production.
- 4Maintain operational runbooks with RAGAgents can ground their investigations by retrieving relevant runbooks from Confluence, Notion, or vector collections in Qdrant.
Written from the project's README. Every use case is checked against a quote from it.
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablemezmo/aura is public and reachablegithub.com/mezmo/aura ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-12github.com/mezmo/aura ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHub
Connect your stack through guided setup, and AURA's preconfigured team of agents starts investigating incidents using the models you already rely on. From there, customize existing agents or add new ones to fit your infrastructure and SRE workflows.
AURA handles the guardrails, APIs, state management, streaming, failure handling, and observability needed to connect AI models to production tools within operator-defined boundaries.
Proven in Production
AURA began as Mezmo’s internal harness for operating our own SaaS. Our engineering and SRE teams still use it for production operations today, and teams outside Mezmo run AURA in their own production environments.
AURA also powers thousands of agent sessions each month in Mezmo’s hosted observability platform.
Quick Start
Install AURA on Linux or macOS with the install script. It downloads published release artifacts and verifies their checksums.
curl -fsSL https://raw.githubusercontent.com/mezmo/aura/main/scripts/install.sh | bash
Create a ready-to-run local agent:
aura init # Choose an LLM provider and initial model, and write the initial config file
Start the agent:
aura
Why AURA
- Operate inside your own security boundary. Run AURA in your infrastructure, including air-gapped and highly regulated environments, with control over model, tool, storage, and telemetry destinations.
- Define the entire agent system in reviewable TOML. Keep models, specialist agent teams, per-agent prompts, tools, approval policies, and guardrails together in configuration that can be versioned and reviewed.
- Use different model providers without rebuilding workflows. Run OpenAI, Anthropic, Bedrock, Gemini, Ollama, or OpenRouter; switch providers with a configuration change or assign different models to different roles.
- Put sensitive actions behind human approval. Require webhook or in-conversation approval before configured tool calls execute, with denial, timeout, and transport failures handled fail-closed.
- Trace every model, tool, and orchestration decision. Export OpenTelemetry traces for requests, LLM turns, tool calls, and multi-agent execution so each result can be investigated end to end.
Extensible Runtime
- Connect tools and RAG. Discover tools from compatible MCP servers over Streamable HTTP, SSE, or STDIO, and ground agents through Qdrant or AWS Bedrock Knowledge Bases.
- Build multi-agent workflows. Coordinate specialist agent teams with dependency-aware task execution while parking oversized tool results on disk for selective retrieval.
- Add reusable Agent Skills. Load task-specific Agent Skills instructions and supporting files only when they are needed.
- Interoperate or embed. Connect AURA with other agents over A2A or embed its Rust core directly in your application.
- Use existing clients and SDKs. Serve agents through an OpenAI-compatible API so clients such as LibreChat and OpenWebUI work unchanged, or run them locally through the AURA CLI.
Production Safety
Production controls define an operator-managed boundary around AURA:
- Runs in your infrastructure, including air-gapped environments when model providers and MCP servers are locally reachable.
- AURA sends agent prompts and tool data to the model providers, MCP servers, approval services, storage backends, and tracing destinations you configure. Enabled client-side tools and STDIO processes can initiate additional network traffic unless system-level network policy prevents it. Mezmo CLI product telemetry is separately disclosed and controlled.
- Sensitive tool calls can require explicit human approval.
- Credentials supplied through environment variables or secret mounts remain outside prompts only when referenced from designated authentication fields; environment substitution in prompt-bearing fields places their values into model context.
- Tool, model, and orchestration activity can be exported as OpenTelemetry traces.
See the complete security and data-handling model, including telemetry defaults, permission boundaries, prompt-injection risks, and supply-chain verification.
Integrations
Through compatible MCP servers and built-in integrations, AURA agents can work with:
| Integration | What agents can do |
|---|---|
| Argo CD | Inspect applications, sync status, and hook logs, and re-run syncs |
| AWS | Inspect cloud resources, logs, metrics, and operational state |
| Azure | Inspect cloud resources, deployments, monitoring, and operational state |
| Checkly | Inspect synthetic check results and assets, re-run checks, and manage checks and check groups |
| ClickHouse | Query system tables for disk, merge, and replication health |
| Confluence | Search and maintain operational runbooks |
| Dash0 | Query hosted OpenTelemetry traces, metrics, and logs |
| Datadog | Query metrics, monitors, dashboards, and traces |
| Docker | Inspect containers, images, logs, and runtime state |
| GCP | Inspect cloud resources, logs, metrics, and operational state |
| GitHub | Search code and work with repositories, issues, and pull requests |
| GitLab | Search code and work with repositories, issues, merge requests, and pipelines |
| Grafana | Query dashboards, alert rules, logs, and metric data sources |
| Jira | Search and update issues, projects, and workflows |
| Kafka | Inspect clusters, topics, consumer groups, and message flows |
| Kubernetes | Inspect clusters, workloads, events, and logs |
| Linear | Search and update issues, projects, and cycles |
| Mezmo | Analyze logs, exports, and telemetry pipelines |
| New Relic | Query metrics, logs, traces, alerts, and dashboards |
| Notion | Search and maintain operational runbooks |
| PagerDuty | Investigate incidents, on-call schedules, and escalations |
| Prometheus | Query metrics and alert status |
| Qdrant | Retrieve runbooks and reference material from vector collections |
| Slack | Read incident channels and post investigation updates |
| Temporal | Run agent investigations as steps in durable workflows |
| Windows Server | Inspect services, drives, processes, and resource usage |
Ways to Run AURA
- As a local chat assistant. Run AURA interactively from your terminal.
- As a service. Run
aura webserveras a daemon and connect it to monitoring systems to trigger agent workflows. - As a container. Run the published
mezmo/auraDocker image. - As a Kubernetes workload. Deploy AURA with the included Helm chart.
- As a library. Embed AURA's Rust core directly in your own application.
Explore AURA
- Browse agent configurations and advanced quickstarts
- Browse the annotated configuration reference
- Run a Kubernetes SRE agent
- Learn the full AURA CLI
- Use AURA's streaming API
- Develop AURA or contribute
Community
Join the AURA Slack community to ask questions, share what you are building, and help shape the roadmap.
Package Hosting
Package repository hosting is graciously provided by Cloudsmith, the only fully hosted, cloud-native, universal package management solution — letting your organization create, store, and share packages in any format, to any place, with total confidence.
License
AURA is licensed under the Apache License, Version 2.0.
AURA MCP questions
How can I install AURA?
You can install AURA on Linux or macOS using a provided install script via curl.
Can I run AURA in an air-gapped environment?
Yes, AURA can run in air-gapped and highly regulated environments as long as your model providers and MCP servers are locally reachable.
What model providers does AURA support?
AURA supports various providers including OpenAI, Anthropic, Bedrock, Gemini, Ollama, and OpenRouter.
How does AURA handle sensitive actions?
You can require human approval via webhook or in-conversation before any configured tool calls are executed.