List all available research topics (vector databases).
AI agents call list_research_topics to retrieve information from Pocket Assistant MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves metadata about existing research topics without creating, modifying, or deleting any data. It is a read-only operation with minimal blast radius if misused by an AI agent—at worst, it exposes the names of available research topics, which is informational only.
From the tool's definition Tool name 'list_research_topics' and description 'List all available research topics' indicate a query/retrieval operation with no modification or deletion of data.
Attacks that exploit this kind of access
List all available research topics (vector databases). It is categorised as a Read tool in the Pocket Assistant MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Pocket Assistant MCP Server MCP server in PolicyLayer and add a rule for list_research_topics: 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 Pocket Assistant MCP Server. Nothing to install.
list_research_topics 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_research_topics 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_research_topics. 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_research_topics is provided by the Pocket Assistant MCP Server MCP server (vikashs/pocket_agent_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 →