AI agents use add_bookmark to create or update resources in Pinboard MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pinboard MCP Server environment.
The tool creates new bookmark entries, which is a reversible modification of the user's data. While not destructive (can be deleted), it modifies stored state. Severity is medium rather than low because adding bookmarks at scale could clutter or pollute a user's bookmark collection if misused by an agent, but the impact is recoverable and limited to the user's own Pinboard account.
From the tool's definition Tool name 'add_bookmark' combined with server description stating 'adding...bookmarks' indicates creation of new data in the user's bookmark collection.
Documented attack patterns abuse exactly the kind of access add_bookmark gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pinboard MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_bookmark:
{
"version": "1",
"default": "deny",
"tools": {
"add_bookmark": {
"limits": [
{
"counter": "add_bookmark_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_bookmark stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
add_bookmark. It is categorised as a Write tool in the Pinboard MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pinboard MCP Server MCP server in PolicyLayer and add a rule for add_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 Pinboard MCP Server. Nothing to install.
add_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 add_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 add_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.
add_bookmark is provided by the Pinboard MCP Server MCP server (vicgarcia/pinboard-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pinboard MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Pinboard MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.