Cancel a workflow run
AI agents invoke cancel_workflow_run to trigger actions in GitHub Actions MCP Server. 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.
Cancelling a workflow run is an external operational action that interrupts running processes. It is not merely reading data, nor does it permanently delete data (the run record remains), but it does trigger an irreversible state change on a live execution. This fits Execute as the closest category.
From the tool's definition 'Cancel a workflow run' — terminates an in-progress CI/CD execution, an external operational action whose effects depend on the targeted run
Attacks that exploit this kind of access
Cancel a workflow run. It is categorised as a Execute tool in the GitHub Actions MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the GitHub Actions MCP Server MCP server in PolicyLayer and add a rule for cancel_workflow_run: 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 Actions MCP Server. Nothing to install.
cancel_workflow_run 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 cancel_workflow_run 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 cancel_workflow_run. 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.
cancel_workflow_run is provided by the GitHub Actions MCP Server MCP server (onemarc/github-actions-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the 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 →