read_scores

读打分快照历史。

SERVERA2p2a SOURCEtendQQ/a2p2a

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/a2p2a/read-scores.md

WHAT IT DOES

What read_scores does on A2p2a

AI agents call read_scores to retrieve information from A2p2a without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why read_scores is rated Low

Retrieves historical scoring data without modifying records or triggering actions.

From the tool's definition reads scoring snapshot history; no modification or side effects

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs read_scores safely

PolicyLayer is an MCP gateway: it sits between your AI agents and A2p2a, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For read_scores, this is the rule to start with:

read_scores Allowed

read_scores is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "read_scores": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect A2p2a, apply this rule, and every read_scores call is checked against it from then on.

FAQ

Questions about read_scores

What does the read_scores tool do? +

读打分快照历史。. It is categorised as a Read tool in the A2p2a MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on read_scores? +

Register the A2p2a MCP server in PolicyLayer and add a rule for read_scores: 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 A2p2a. Nothing to install.

What risk level is read_scores? +

read_scores is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit read_scores? +

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

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

read_scores is provided by the A2p2a MCP server (tendQQ/a2p2a). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on A2p2a, and thousands of servers like it.

This server

All 15 A2p2a tools →

Across the catalogue

binary_read on 010 Editor → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →