AI agents use html_encode 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.
HTML encoding transforms data reversibly without destructive side effects or external operations. It modifies content in-place and can be reversed via html_decode. No code execution, deletion, financial impact, or irreversible changes occur. This is a data transformation utility, categorized as Write (creates/modifies data reversibly).
From the tool's definition Tool name 'html_encode' and description 'Encode special characters in a string to HTML entities' — this converts input strings by replacing special characters with HTML entity equivalents.
Attacks that exploit this kind of access
Encode special characters in a string to HTML entities. 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 html_encode: 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.
html_encode 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 html_encode 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 html_encode. 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.
html_encode 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 →