This record as markdown: /tools/3akhp-prts-mcp/find-speakers-in.md
What find_speakers_in does on Prts
AI agents call find_speakers_in to retrieve information from Prts without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why find_speakers_in is rated Low
This tool queries and retrieves dialogue information from the PRTS Wiki/game data without modifying, executing code, deleting, or involving financial transactions. It is a straightforward read operation that returns aggregated data about speakers and dialogue counts for lore/fan-creation purposes. No side effects or state changes occur.
From the tool's definition Tool name 'find_speakers_in' and description '列出某活动中的所有发言角色及其台词数' (list all speaking characters and their line counts in an activity) indicate retrieval of character dialogue metadata from game archives.
Attacks that exploit this kind of access
The rule that runs find_speakers_in safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Prts, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For find_speakers_in, this is the rule to start with:
find_speakers_in 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 Prts, apply this rule, and every find_speakers_in call is checked against it from then on.
Questions about find_speakers_in
列出某活动中的所有发言角色及其台词数。. It is categorised as a Read tool in the Prts MCP Server, which means it retrieves data without modifying state.
Register the Prts MCP server in PolicyLayer and add a rule for find_speakers_in: 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 Prts. Nothing to install.
find_speakers_in 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 find_speakers_in 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 find_speakers_in. 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.
find_speakers_in is provided by the Prts MCP server (3akhp/prts-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Prts, and thousands of servers like it.
This server
Across the catalogue