Create a note from a webpage
AI agents use grab_url to create or update resources in Bear MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Bear MCP Server environment.
This tool creates a new note by fetching content from an external URL and storing it in Bear. While it fetches external data, the primary action is creation of a new note (write operation), not mere retrieval. The severity is medium because misuse could spam the note database but wouldn't cause irreversible destruction or financial harm.
From the tool's definition Tool description states it will "Create a note from a webpage", which is a write operation that creates new data in Bear. The sibling tools confirm this server manages note creation/modification (create_note, add_text, archive_note, delete_tag).
Attacks that exploit this kind of access
Create a note from a webpage. It is categorised as a Write tool in the Bear MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Bear MCP Server MCP server in PolicyLayer and add a rule for grab_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 Bear MCP Server. Nothing to install.
grab_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 grab_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 grab_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.
grab_url is provided by the Bear MCP Server MCP server (philgetzen/bear-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 →