AI agents call peaka_get_query to retrieve information from Peaka without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and returns metadata about a query (displayName, inputQuery, queryType, auto-refresh schedule) without modifying, deleting, or executing anything. It is a straightforward read operation with minimal blast radius if misused by an AI agent.
From the tool's definition Tool description explicitly states 'Read a single saved query by its ID' and 'Returns the full query object' — this is a retrieval operation with no side effects.
Attacks that exploit this kind of access
Read a single saved query by its ID. Returns the full query object including displayName, inputQuery (SQL), queryType, and the auto-refresh schedule for materialized queries. ${PROJECT_ID_HINT}. It is categorised as a Read tool in the Peaka MCP Server, which means it retrieves data without modifying state.
Register the Peaka MCP server in PolicyLayer and add a rule for peaka_get_query: 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 Peaka. Nothing to install.
peaka_get_query 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 peaka_get_query 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 peaka_get_query. 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.
peaka_get_query is provided by the Peaka MCP server (@peaka/mcp-server-peaka). 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 →