Update a bookmark
AI agents use update_bookmark to create or update resources in Krill To MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Krill To MCP Server environment.
The tool creates or modifies data in a reversible manner (updating bookmark metadata, collections, or notes), which is characteristic of Write operations. The blast radius is moderate — misuse could alter user's saved bookmarks and collections, but changes are reversible through further updates.
From the tool's definition Tool name is 'update_bookmark' and description states 'Update a bookmark' — this modifies existing bookmark data.
Attacks that exploit this kind of access
Update a bookmark. It is categorised as a Write tool in the Krill To MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Krill To MCP Server MCP server in PolicyLayer and add a rule for update_bookmark: 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 Krill To MCP Server. Nothing to install.
update_bookmark 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 update_bookmark 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 update_bookmark. 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.
update_bookmark is provided by the Krill To MCP Server MCP server (krillto/mcp-server). 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 →