AI agents call run-view to retrieve information from Python without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only retrieves and returns information about a workflow run. No side effects, modifications, or executions are implied — it is a read/query operation.
From the tool's definition 'Views a workflow run by ID. Returns structured data with status, conclusion, jobs (with steps), and workflow details.'
Attacks that exploit this kind of access
Views a workflow run by ID. Returns structured data with status, conclusion, jobs (with steps), and workflow details. It is categorised as a Read tool in the Python MCP Server, which means it retrieves data without modifying state.
Register the Python MCP server in PolicyLayer and add a rule for run-view: 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 Python. Nothing to install.
run-view is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the run-view 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-view. 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-view is provided by the Python MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
run-view is one line of Python's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →