AI agents invoke yq to trigger actions in Python. 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.
The tool executes arbitrary yq expressions against files or inline strings. yq expressions can perform complex transformations including writes back to files. Since it runs arbitrary expressions against potentially any file on the filesystem, the blast radius is high — a misused expression could read, modify, or overwrite configuration files.
From the tool's definition Processes and transforms YAML, JSON, XML, TOML, and properties files using yq expressions
Attacks that exploit this kind of access
Processes and transforms YAML, JSON, XML, TOML, and properties files using yq expressions. Accepts input from a file path or inline string. Returns the transformed result. It is categorised as a Execute tool in the Python MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Python MCP server in PolicyLayer and add a rule for yq: 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.
yq 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 yq 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 yq. 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.
yq 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.
yq 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 →