Medium Risk

bookmark_asset

Save a conduitAI catalog asset (MCP server, agent, skill, prompt, plugin, MCP client) to your bookmarks for later. Idempotent: bookmarking an already-bookmarked asset is a no-op. Capacity is capped at 1000 per user.

Part of the Conduitai App server.

bookmark_asset can modify Conduitai App data, with no limits today. PolicyLayer puts allow, deny, and rate-limit rules on every call. Live in minutes.

SECURE CONDUITAI APP →

Free to start. No card required.

AI agents use bookmark_asset to create or modify resources in Conduitai App. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call bookmark_asset repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Conduitai App.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "bookmark_asset": {
      "limits": [
        {
          "counter": "bookmark_asset_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

See the full Conduitai App policy for all 14 tools.

Get this rule live on your own Conduitai App server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY CONDUITAI APP →

View all 14 tools →

These attack patterns abuse exactly the kind of access bookmark_asset gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so bookmark_asset only ever does what you allow.

SECURE CONDUITAI APP →

Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.

What does the bookmark_asset tool do? +

Save a conduitAI catalog asset (MCP server, agent, skill, prompt, plugin, MCP client) to your bookmarks for later. Idempotent: bookmarking an already-bookmarked asset is a no-op. Capacity is capped at 1000 per user.. It is categorised as a Write tool in the Conduitai App MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on bookmark_asset? +

Register the Conduitai App MCP server in PolicyLayer and add a rule for bookmark_asset: 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 Conduitai App. Nothing to install.

What risk level is bookmark_asset? +

bookmark_asset is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit bookmark_asset? +

Yes. Add a rate_limit block to the bookmark_asset 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.

How do I block bookmark_asset completely? +

Set action: deny in the PolicyLayer policy for bookmark_asset. 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.

What MCP server provides bookmark_asset? +

bookmark_asset is provided by the Conduitai App MCP server (@conduitai-app/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Conduitai App tool call.

Deterministic rules across all 14 Conduitai App tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.