query_loki_logs
AI agents call query_loki_logs to retrieve information from Observability MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Querying logs via Loki is a retrieval operation with no side effects or ability to modify systems. While the description is empty, the tool name and server context strongly indicate this is a read-only observability function. The primary risk from misuse would be information disclosure (accessing sensitive logs), not operational damage.
From the tool's definition Tool name 'query_loki_logs' indicates querying Loki (a log aggregation system); server description emphasizes monitoring and observability functions; sibling tools are all read-only observability operations (analyze, check, collect, correlate, export,…
Attacks that exploit this kind of access
query_loki_logs. It is categorised as a Read tool in the Observability MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Observability MCP Server MCP server in PolicyLayer and add a rule for query_loki_logs: 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 Observability MCP Server. Nothing to install.
query_loki_logs 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 query_loki_logs 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 query_loki_logs. 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.
query_loki_logs is provided by the Observability MCP Server MCP server (sandraschi/observability-mcp). 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 →