AI agents use json_format to create or update resources in Devutils — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Devutils environment.
The tool creates or modifies data (JSON formatting/minification) in a reversible manner. It does not delete data (ruling out Destructive), execute arbitrary operations (ruling out Execute), access external systems (ruling out Financial), or have significant side effects. The severity is low because formatting changes are easily reversible and have minimal blast radius if misused by an agent.
From the tool's definition Tool description states it can 'Format (pretty-print) a JSON string' and 'minify JSON', which are reversible transformations that modify the structure of JSON data without deleting or executing code.
Attacks that exploit this kind of access
Format (pretty-print) a JSON string with configurable indentation. Can also minify JSON. It is categorised as a Write tool in the Devutils MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Devutils MCP server in PolicyLayer and add a rule for json_format: 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 Devutils. Nothing to install.
json_format is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the json_format 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 json_format. 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.
json_format is provided by the Devutils MCP server (paladini/devutils-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 →