html_entities
Escape the five special HTML characters (optionally all non-ASCII) or decode named and numeric HTML entities back to text. Runs on smart-tools.xyz.
This record as markdown: /tools/io-github-9thshini-smart-tools/html-entities.md
What html_entities does on SmartTools
AI agents invoke html_entities to trigger actions in SmartTools. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | Text to encode, or HTML with entities to decode |
locale | string | — | Language for the source_url link (default en) |
direction | string | — | encode (default) or decode |
encode_all | boolean | — | When encoding, also convert every non-ASCII character to a numeric entity. Default false |
Parameters from the server's own tool schema.
Why html_entities is rated High
html_entities triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Attacks that exploit this kind of access
The rule that runs html_entities safely
PolicyLayer is an MCP gateway: it sits between your AI agents and SmartTools, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For html_entities, this is the rule to start with:
html_entities stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect SmartTools, apply this rule, and every html_entities call is checked against it from then on.
Questions about html_entities
Escape the five special HTML characters (optionally all non-ASCII) or decode named and numeric HTML entities back to text. Runs on smart-tools.xyz. It is categorised as a Execute tool in the SmartTools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
html_entities accepts 4 parameters: text, locale, direction, encode_all. Required: text. The full parameter table on this page comes from the server's own tool schema.
Register the SmartTools MCP server in PolicyLayer and add a rule for html_entities: 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 SmartTools. Nothing to install.
html_entities 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 html_entities 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_entities. 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_entities is provided by the SmartTools MCP server (https://smart-tools.xyz/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on SmartTools, and thousands of servers like it.
Across the catalogue