SIDE-EFFECTFUL — fetches an EXTERNAL URL and writes a NEW KB file. Downloads the page, extracts the main article via Readability, converts to markdown, and saves it as a new clipping. NOT idempotent / no de-dup — re-clipping the same URL creates a second file. AUTH: anonymous by default; pass
AI agents use clip_url to create or update resources in Kontexta — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kontexta environment.
The tool performs two actions: reading an external URL and writing a new file to the knowledge base. Since Write > Read in severity, and the primary side effect is creating a new persistent file (not destructive, not financial, not executing arbitrary code), Write is the correct category.
From the tool's definition fetches an EXTERNAL URL and writes a NEW KB file ... saves it as a new clipping ... re-clipping the same URL creates a second file
Attacks that exploit this kind of access
SIDE-EFFECTFUL — fetches an EXTERNAL URL and writes a NEW KB file. Downloads the page, extracts the main article via Readability, converts to markdown, and saves it as a new clipping. NOT idempotent / no de-dup — re-clipping the same URL creates a second file. AUTH: anonymous by default; pass. It is categorised as a Write tool in the Kontexta MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kontexta MCP server in PolicyLayer and add a rule for clip_url: 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 Kontexta. Nothing to install.
clip_url 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 clip_url 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 clip_url. 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.
clip_url is provided by the Kontexta MCP server (safiyu/kontexta). 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 →