Low Risk

sdk_logs_list

List raw incoming SDK request/response log entries for an app via /o?method=logs. Used for debugging SDK payloads (device_id, timestamp, payload). Requires the logger plugin. For server-side errors use server_logs_files_list.

Part of the Countly MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

AI agents call sdk_logs_list to retrieve information from Countly without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though sdk_logs_list only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

countly.yaml
tools:
  sdk_logs_list:
    rules:
      - action: allow

See the full Countly policy for all 127 tools.

Tool Name sdk_logs_list
Category Read
MCP Server Countly MCP Server
Risk Level Low

View all 127 tools →

Agents calling read-class tools like sdk_logs_list have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.

What does the sdk_logs_list tool do? +

List raw incoming SDK request/response log entries for an app via /o?method=logs. Used for debugging SDK payloads (device_id, timestamp, payload). Requires the logger plugin. For server-side errors use server_logs_files_list.. It is categorised as a Read tool in the Countly MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on sdk_logs_list? +

Add a rule in your Intercept YAML policy under the tools section for sdk_logs_list. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Countly MCP server.

What risk level is sdk_logs_list? +

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

Can I rate-limit sdk_logs_list? +

Yes. Add a rate_limit block to the sdk_logs_list rule in your Intercept 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 sdk_logs_list completely? +

Set action: deny in the Intercept policy for sdk_logs_list. 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 sdk_logs_list? +

sdk_logs_list is provided by the Countly MCP server (countly-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.