oomkill_detect

Detect pods that have been OOMKilled. Returns pods with OOMKill events, their current resource limits, and restart counts.

Server Git Steer ry-ops/git-steer
Category Read
Risk class Low
Parameters 00 required

What oomkill_detect does on Git Steer

AI agents call oomkill_detect to retrieve information from Git Steer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why oomkill_detect needs a policy

This tool queries and retrieves Kubernetes pod metrics and status information (OOMKill events, resource limits, restart counts) without making any changes to cluster state or resources. It is purely observational/diagnostic in nature. While the broader git-steer server manages repositories and workflows (potentially Write/Execute/Destructive operations), this specific tool only reads pod monitoring data.

From the tool's definition Tool description states it 'Detect pods that have been OOMKilled' and 'Returns pods with OOMKill events, their current resource limits, and restart counts.' The verbs 'Detect' and 'Returns' indicate read-only retrieval of pod status information without any…

Questions about oomkill_detect

What does the oomkill_detect tool do? +

Detect pods that have been OOMKilled. Returns pods with OOMKill events, their current resource limits, and restart counts. It is categorised as a Read tool in the Git Steer MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on oomkill_detect? +

Register the Git Steer MCP server in PolicyLayer and add a rule for oomkill_detect: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Git Steer. Nothing to install.

What risk level is oomkill_detect? +

oomkill_detect is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit oomkill_detect? +

Yes. Add a rate_limit block to the oomkill_detect rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block oomkill_detect completely? +

Set action: deny in the PolicyLayer policy for oomkill_detect. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides oomkill_detect? +

oomkill_detect is provided by the Git Steer MCP server (ry-ops/git-steer). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER SERVER

Every MCP server has a record like this.

Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.