This record as markdown: /tools/io-github-dave-london-git/run-rerun.md
What run-rerun does on Git
AI agents invoke run-rerun to trigger actions in Git. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why run-rerun is rated High
This tool executes a workflow/CI pipeline, which is an external operation with side effects that depend on user-supplied arguments (the run ID and optional job filters). While the effects are typically reversible (workflows can be cancelled or re-run), the execution of potentially arbitrary pipeline logic qualifies as Execute rather than Write.
From the tool's definition "Re-runs a workflow run by ID" indicates triggering external CI/CD operations whose effects depend on the run ID argument provided.
Attacks that exploit this kind of access
The rule that runs run-rerun safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Git, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For run-rerun, this is the rule to start with:
run-rerun stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Git, apply this rule, and every run-rerun call is checked against it from then on.
Questions about run-rerun
Re-runs a workflow run by ID. Optionally re-runs only failed jobs or a specific job. Returns structured result with run ID, status, and URL. It is categorised as a Execute tool in the Git MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Git MCP server in PolicyLayer and add a rule for run-rerun: 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. Nothing to install.
run-rerun is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the run-rerun 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.
Set action: deny in the PolicyLayer policy for run-rerun. 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.
run-rerun is provided by the Git MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Git, and thousands of servers like it.
This server
Across the catalogue