htmltoclaude v0.1: convert a source (URL OR inline HTML OR local file/zip) to a compact YAML DSL (cbm/htmltoclaude/v0) Claude-consumable representation. Hoists colors+fonts to tokens, captures box/role/style per node, walks shadowRoot, captures CSS pseudo-elements (::before/::after), preserves SV...
AI agents call to_claude to retrieve information from Custom Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and analyzes web content to produce a structured representation. It retrieves data from URLs or processes provided HTML/files but does not create side effects, execute code, delete data, or modify the source. The output is a converted format (YAML DSL) for consumption by Claude, which is a read-like transformation.
From the tool's definition Tool converts a source (URL, inline HTML, or local file) to a YAML DSL representation. The description emphasizes extraction and transformation of existing data: 'extract', 'convert', 'hoists', 'captures', 'preserves', 'walks'.
Attacks that exploit this kind of access
htmltoclaude v0.1: convert a source (URL OR inline HTML OR local file/zip) to a compact YAML DSL (cbm/htmltoclaude/v0) Claude-consumable representation. Hoists colors+fonts to tokens, captures box/role/style per node, walks shadowRoot, captures CSS pseudo-elements (::before/::after), preserves SVG outerHTML, captures raw gradient strings. v0.7.0 adds paste-HTML inputs (. It is categorised as a Read tool in the Custom Browser MCP Server, which means it retrieves data without modifying state.
Register the Custom Browser MCP server in PolicyLayer and add a rule for to_claude: 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 Custom Browser. Nothing to install.
to_claude is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the to_claude 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 to_claude. 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.
to_claude is provided by the Custom Browser MCP server (theriz78/eclectique-browser-mcp). 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 →