AI agents call list_annotations to retrieve information from Peptoma without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves peer-review annotation data for display purposes. There are no modifications, deletions, code execution, or financial operations involved. The blast radius of misuse is minimal—an agent could only over-query the endpoint or retrieve data it shouldn't access, but cannot alter state or cause irreversible harm through this tool alone.
From the tool's definition Tool description states it 'List all peer-review annotations' and 'Returns' metadata about annotations. The verb 'list' and the read-only nature of returning existing annotation data indicate pure data retrieval with no side effects.
Attacks that exploit this kind of access
List all peer-review annotations for a specific PEPTOMA sequence analysis. Returns the annotation type, content, author, vote score, and tokens earned for each annotation. It is categorised as a Read tool in the Peptoma MCP Server, which means it retrieves data without modifying state.
Register the Peptoma MCP server in PolicyLayer and add a rule for list_annotations: 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 Peptoma. Nothing to install.
list_annotations is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_annotations 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 list_annotations. 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.
list_annotations is provided by the Peptoma MCP server (peptoma/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 →