Medium Risk

save_literature_notes

save_literature_notes

How to control save_literature_notes ↓

What save_literature_notes does on Pubmed Search

AI agents use save_literature_notes to create or update resources in Pubmed Search — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pubmed Search environment.

Medium Risk

Why save_literature_notes needs a policy

This tool creates or modifies user notes tied to literature research—reversible write operations. It lacks destructive intent (notes can be edited/deleted separately) and does not execute external code or move money. The medium severity reflects that misuse could corrupt a user's research notes or create unwanted persistent records, but the impact is localized to the user's note collection.

From the tool's definition Tool name 'save_literature_notes' indicates creation or modification of note data. Description is empty, limiting direct confirmation, but the verb 'save' combined with 'notes' suggests persistent storage of user-generated content.

Documented attack patterns abuse exactly the kind of access save_literature_notes gives an agent:

How to control save_literature_notes

PolicyLayer is an MCP gateway — it sits between your AI agents and Pubmed Search, and nothing reaches the server without passing your rules. This is the rule we recommend for save_literature_notes:

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

save_literature_notes 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.

  1. Create a free account and register Pubmed Search — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about save_literature_notes

What does the save_literature_notes tool do? +

save_literature_notes. It is categorised as a Write tool in the Pubmed Search MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on save_literature_notes? +

Register the Pubmed Search MCP server in PolicyLayer and add a rule for save_literature_notes: 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 Pubmed Search. Nothing to install.

What risk level is save_literature_notes? +

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

Can I rate-limit save_literature_notes? +

Yes. Add a rate_limit block to the save_literature_notes 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 save_literature_notes completely? +

Set action: deny in the PolicyLayer policy for save_literature_notes. 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 save_literature_notes? +

save_literature_notes is provided by the Pubmed Search MCP server (u9401066/pubmed-search-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Pubmed Search tool call.

Start from Pubmed Search, 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.

63 Pubmed Search tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.