This record as markdown: /tools/dkeeno-github-mcp-server/github-rerun-workflow.md
What github_rerun_workflow does on Github
AI agents invoke github_rerun_workflow to trigger actions in Github. 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 github_rerun_workflow is rated High
Re-running a workflow executes potentially arbitrary code defined in GitHub Actions (shell commands, scripts, deployments, API calls, etc.). While the workflow definition itself is fixed and not controlled by this tool invocation, the action still triggers external operations that can have side effects on systems, repositories, and infrastructure.
From the tool's definition Tool name: 'github_rerun_workflow'; description: 'Re-run a workflow.' The tool triggers the execution of a GitHub Actions workflow, which runs code/scripts whose effects depend on the workflow definition and external systems.
Attacks that exploit this kind of access
The rule that runs github_rerun_workflow 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 github_rerun_workflow, this is the rule to start with:
github_rerun_workflow 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 Github, apply this rule, and every github_rerun_workflow call is checked against it from then on.
Questions about github_rerun_workflow
Re-run a workflow. It is categorised as a Execute tool in the Github MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Github MCP server in PolicyLayer and add a rule for github_rerun_workflow: 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.
github_rerun_workflow 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 github_rerun_workflow 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 github_rerun_workflow. 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.
github_rerun_workflow is provided by the Github MCP server (dkeeno/github-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Github, and thousands of servers like it.
Across the catalogue