This record as markdown: /tools/io-github-dreamrec-livepilot/corpus-research-targets.md
What corpus_research_targets does on Livepilot
AI agents call corpus_research_targets to retrieve information from Livepilot without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why corpus_research_targets is rated Low
Without a description, classification confidence is reduced. However, the name pattern 'corpus_research_targets' most naturally maps to retrieving or querying target research items from a knowledge base, which is a Read operation. No evidence of write, destructive, or financial impact. The context of a music production copilot makes data retrieval plausible.
From the tool's definition Tool name 'corpus_research_targets' suggests querying or retrieving research data/targets from a corpus. The empty description limits certainty, but the naming convention aligns with Read operations (retrieving or querying data).
Attacks that exploit this kind of access
The rule that runs corpus_research_targets safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Livepilot, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For corpus_research_targets, this is the rule to start with:
corpus_research_targets is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Livepilot, apply this rule, and every corpus_research_targets call is checked against it from then on.
Questions about corpus_research_targets
corpus_research_targets is a read tool on the Livepilot MCP server. It is categorised as a Read tool in the Livepilot MCP Server, which means it retrieves data without modifying state.
Register the Livepilot MCP server in PolicyLayer and add a rule for corpus_research_targets: 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 Livepilot. Nothing to install.
corpus_research_targets 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 corpus_research_targets 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 corpus_research_targets. 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.
corpus_research_targets is provided by the Livepilot MCP server (livepilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Livepilot, and thousands of servers like it.
This server
Across the catalogue