send_logs_to_loki · Observability MCP Server MCP

WHAT IT DOES

What send_logs_to_loki does on Observability MCP Server

AI agents use send_logs_to_loki to create or update resources in Observability MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Observability MCP Server environment.

WHY IT NEEDS A POLICY

Why send_logs_to_loki needs a policy

This tool sends log data to an external logging system (Loki), which constitutes data creation/modification in a remote store. While no side effects occur on the MCP server itself, logs are irreversibly written to persistent storage. This is Write rather than Read (retrieves data) or Destructive (the logs themselves aren't deleted).

From the tool's definition Tool name 'send_logs_to_loki' indicates transmission/persistence of log data to Loki (a log aggregation system). The verb 'send_to' combined with a backend service name suggests write/push operations that create or modify centralized log storage.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

send_logs_to_loki Rate-limited

send_logs_to_loki stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "send_logs_to_loki": {
      "limits": [
        {
          "counter": "send_logs_to_loki_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Observability MCP Server, so you can run agents against it safely.

FAQ

Questions about send_logs_to_loki

What does the send_logs_to_loki tool do? +

send_logs_to_loki. It is categorised as a Write tool in the Observability MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on send_logs_to_loki? +

Register the Observability MCP Server MCP server in PolicyLayer and add a rule for send_logs_to_loki: 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.

What risk level is send_logs_to_loki? +

send_logs_to_loki is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit send_logs_to_loki? +

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

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

send_logs_to_loki 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.