AI agents call read_passage to retrieve information from Mcp Score without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The verb 'read' indicates a query/retrieval operation with no capability to modify, delete, or execute arbitrary operations. No description is provided, which introduces some uncertainty, but the name itself is clear. Given the sibling tools that perform writes (add_live_chord_symbol, add_live_rehearsal_mark) and connections (connect_to_*), this tool's purpose appears to be information retrieval.
From the tool's definition Tool name 'read_passage' strongly suggests data retrieval with no side effects. Within the music notation context, this likely reads passage/section information from a score.
Documented attack patterns abuse exactly the kind of access read_passage gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Score, and nothing reaches the server without passing your rules. This is the rule we recommend for read_passage:
{
"version": "1",
"default": "deny",
"tools": {
"read_passage": {}
}
}read_passage is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
read_passage. It is categorised as a Read tool in the Mcp Score MCP Server, which means it retrieves data without modifying state.
Register the Mcp Score MCP server in PolicyLayer and add a rule for read_passage: 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 Mcp Score. Nothing to install.
read_passage 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 read_passage 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 read_passage. 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.
read_passage is provided by the Mcp Score MCP server (tskovlund/mcp-score). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Score, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
18 Mcp Score tools catalogued and risk-classified — across an index of 43,000+ MCP servers.