failed_only

When true, gets logs for all failed jobs in the workflow run specified by run_id. Requires run_id to be provided. (boolean, optional)

SERVERGitHub SOURCEoci:ghcr.io/aifity/omnigit-mcp:0.5.0

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-aifity-omnigit-mcp/failed-only.md

WHAT IT DOES

What failed_only does on GitHub

AI agents call failed_only to retrieve information from GitHub without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why failed_only is rated Low

This appears to be a parameter/filter option rather than a standalone tool, but based on its described behavior it retrieves logs for failed jobs in a workflow run. This is a read-only operation with no side effects. Severity is low since it only reads log data. Confidence is reduced because this looks like a parameter descriptor rather than a full tool definition.

From the tool's definition 'gets logs for all failed jobs in the workflow run' - retrieves log data only

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs failed_only safely

PolicyLayer is an MCP gateway: it sits between your AI agents and GitHub, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For failed_only, this is the rule to start with:

failed_only Allowed

failed_only is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "failed_only": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect GitHub, apply this rule, and every failed_only call is checked against it from then on.

FAQ

Questions about failed_only

What does the failed_only tool do? +

When true, gets logs for all failed jobs in the workflow run specified by run_id. Requires run_id to be provided. (boolean, optional). It is categorised as a Read tool in the GitHub MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on failed_only? +

Register the GitHub MCP server in PolicyLayer and add a rule for failed_only: 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 GitHub. Nothing to install.

What risk level is failed_only? +

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

Can I rate-limit failed_only? +

Yes. Add a rate_limit block to the failed_only 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 failed_only completely? +

Set action: deny in the PolicyLayer policy for failed_only. 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 failed_only? +

failed_only is provided by the GitHub MCP server (oci:ghcr.io/aifity/omnigit-mcp:0.5.0). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on GitHub, and thousands of servers like it.

This server

All 245 GitHub tools →

Across the catalogue

The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →