Give AI agents the ability to monitor your infrastructure.
Levirge DevOps lets AI agents such as Claude check databases, logs, Docker containers, model servers and message buses behind your firewalls, over MCP. A small client, devops-client, connects outward, so nothing needs an inbound port or VPN. Agents are read-only unless you grant a writer role, and every agent action is audited.
One MCP connection, every system
An incident spans systems: a slow query, an error in the logs, a container out of memory. The agent checks each of them in one session, wherever devops-client runs.
Databases
Schema and queries on PostgreSQL, MySQL, SQLite, MongoDB, InfluxDB and Redis.
get_sql_schema · run_query
Logs
Tail, search and page through log files and whole directories, without SSH.
log_tail · log_search · log_read
Containers
List Docker containers, read their logs and take a CPU, memory, network and disk snapshot.
docker_get_logs · docker_get_stats
Message bus
Streams, consumer lag and server health on message bus servers.
overview · streams · consumers
Model servers
Which model a llama.cpp server has loaded, how busy its slots are and how fast it generates.
llama_read
The right connection
Turns a name like “checkout” into the connection to use, with close matches when there’s no exact one.
find_connection
From “checkout is slow” to the cause
Built-in prompts start the agent on a common job; it picks the next tool from what it finds.
| Step | The agent calls | What it learns |
|---|---|---|
| 1 | find_connection"checkout" | The checkout database, its log directory and the Docker host |
| 2 | log_searchpattern: "timeout" | Timeouts started at 09:40, all on one endpoint |
| 3 | docker_get_statscheckout-api | CPU and memory are normal, so it isn't the container |
| 4 | run_queryEXPLAIN ANALYZE … | A sequential scan on orders since an index was dropped |
Illustrative investigation with made-up names and results. Read-only database access, in detail →
| Ready-made prompt | What the agent reviews |
|---|---|
| container_health_check | Resource use, and any unhealthy or stopped containers. |
| find_slow_queries | Slow queries in the logs above a threshold. |
| explain_query | A query plan explained with EXPLAIN ANALYZE. |
| redis_memory_analysis | Keyspace spread, large keys, eviction and fragmentation. |
| message bus audit | Streams and consumer lag. |
Give agents read-only access to critical infrastructure
Let an agent look at production without handing it the keys. It can read what it's granted; changing anything needs a role you give it.
No inbound port or VPN
devops-client connects outward through a message bus.
Read-only unless you say otherwise
Writes need a writer role, checked at Levirge DevOps and again at devops-client. A connection can also be set read-only.
Credentials stay on the host
Passwords, connection strings, hosts and file paths aren’t sent over the message bus.
Every agent action on record
The audit log marks what an agent did apart from what a person did.
Errors that say what to do next
A failed call returns a code and, where there is one, the next tool to call.
People can look too
The same systems are in the web UI for people and the REST API for scripts.
One connection, or a server and a way in for each system
One MCP server per system
- A way in to each network
- One server per database, log host and Docker host
- Credentials copied to wherever each server runs
- Audit varies by server
Levirge DevOps
- Outbound-only: no inbound port or VPN
- One MCP connection for all of them
- Credentials stay on the host
- One audit log, agent actions marked
Agents and your infrastructure
Can an AI agent monitor my infrastructure without a VPN or inbound port?
Yes. devops-client runs next to each system and connects outward through a message bus to Levirge DevOps. The agent connects to Levirge DevOps over MCP, so nothing behind your firewall needs an inbound port or VPN.
Is it safe to give an AI agent access to production systems?
Agents are read-only unless you grant a writer role. Writes are checked twice, at Levirge DevOps and again at devops-client, and a connection can also be set read-only. Credentials stay on the host, and the audit log marks what an agent did apart from what a person did.
Can I give an AI agent read-only access to critical infrastructure?
Yes, and it is the default. An agent can read the databases, logs, containers and message buses it is granted, but cannot change them unless you give it a writer role. You can also set a connection read-only, which blocks writes for everyone, agents included.
Which AI agents work with Levirge DevOps?
Claude or any other MCP client. The agent gets one MCP connection that covers every system where devops-client runs.
What can the agent check?
PostgreSQL, MySQL/MariaDB, SQLite, MongoDB, InfluxDB and Redis/Valkey; log files and log directories; Docker containers, logs and stats; message bus streams and consumer lag; and llama.cpp model servers. Each plugin page lists its MCP tools.
How is this different from the Datadog or Grafana MCP servers?
Those let an agent query telemetry you have already sent to that platform. Levirge DevOps reaches the systems themselves, so an agent can run a query, tail a log file or read container stats directly. The two can sit side by side.
Can I install it today?
Not yet. Levirge DevOps is in private testing and devops-client has no public download. Join the waitlist for one email when it is ready to install.
Be first to let your agents into your infrastructure
devops-client has no public download yet. Join the waitlist and we'll email you when it does.
Check your inbox
Confirm the subscription from the email we just sent and you're on the list.