Decodes JSXN notation and writes the resulting JSX/TSX or HTML to a file on disk. Creates parent directories if needed. Writes to .jsx/.tsx/.js/.ts/.html/.svg files. For .html and .svg files, decodes with HTML format (class attrs, void elements, SVG self-closing, etc.). JSXN Format Reference JSXN...
Risk signalsAccepts freeform code/query input (code) · Accepts file system path (path) · Bulk/mass operation — affects multiple targets
Part of the Jsx Notation server.
Free to start. No card required.
AI agents use write_jsxn to create or modify resources in Jsx Notation. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call write_jsxn repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Jsx Notation.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"write_jsxn": {
"limits": [
{
"counter": "write_jsxn_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Jsx Notation policy for all 4 tools.
These attack patterns abuse exactly the kind of access write_jsxn gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Decodes JSXN notation and writes the resulting JSX/TSX or HTML to a file on disk. Creates parent directories if needed. Writes to .jsx/.tsx/.js/.ts/.html/.svg files. For .html and .svg files, decodes with HTML format (class attrs, void elements, SVG self-closing, etc.). JSXN Format Reference JSXN is a compact notation for React/Next.js code that saves ~40% tokens. File-level headers - @I module: default Name, x, y → import Name, { x, y } from "module" - @I "styles.css" → import "styles.css" - @T module: Type1 → import type { Type1 } from "module" Directives - "use client" / "use server" → passed through as-is Types - Name { field: Type } → interface Name { field: Type } - Name = Type | Other → type Name = Type | Other Function blocks - export default Name(params) → function signature - @state count = 0 → const [count, setCount] = useState(0) - @ref inputRef = null → const inputRef = useRef(null) - name = useHook(args) → const name = useHook(args) - variable = expr → const variable = expr - let variable = expr → preserved as let - --- → separator; everything after is the JSX return body JSX body notation - Alias headers (optional): @C Button=B, @P onClick=k, @S items-center=ic - Elements: tag.class1.class2#id {prop:val, flag} "text" or (expr) - Implicit div: .className (div is omitted when it has selectors) - Nesting: 1-space indentation per level - Fragments: _ → <>...</> - Conditionals: ?cond > Element → {cond && (<Element />)} - Ternaries: ?cond > A | B → {cond ? (<A />) : (<B />)} - Maps: *items > Element → {items.map(item => (<Element />))} - Text nodes: "Hello" → raw text - Expressions: (expr) → {expr} - Props: {key:value} string for HTML attrs, {key:expr} expression otherwise - Boolean props: {disabled} → disabled - Spread: {...props} → {...props} - Self-closing: element with no children → <Element /> - Member expressions: Form.Input (dot after uppercase = member, not class) Example @C Modal=M, Button=B @P onClick=k, disabled=x M {isOpen:show, onClose:handleClose} .modal-body h2 (title) ?error > Alert {type:error} (error) ul.item-list *items > li.item {key:item.id, k:()=>select(item)} (item.name) B {x:!selected, k:handleSubmit} "Confirm". It is categorised as a Write tool in the Jsx Notation MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Jsx Notation MCP server in PolicyLayer and add a rule for write_jsxn: 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 Jsx Notation. Nothing to install.
write_jsxn 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 write_jsxn 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 write_jsxn. 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.
write_jsxn is provided by the Jsx Notation MCP server (jsx-notation). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Jsx Notation tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.