Low Risk

query_pyroscope

Unified Pyroscope query tool for fetching profiles or metrics from Pyroscope. Profile data shows WHICH functions consume resources; metrics data shows WHEN consumption spiked. Use query_type="both" for complete analysis in one call. query_type options (extends Grafana's PyroscopeQueryType): - "...

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

AI agents call query_pyroscope to retrieve information from Mcp Grafana Npx 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 query_pyroscope 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.

mcp-grafana-npx.yaml
tools:
  query_pyroscope:
    rules:
      - action: allow

See the full Mcp Grafana Npx policy for all 50 tools.

Tool Name query_pyroscope
Category Read
Risk Level Low

View all 50 tools →

Agents calling read-class tools like query_pyroscope 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 query_pyroscope tool do? +

Unified Pyroscope query tool for fetching profiles or metrics from Pyroscope. Profile data shows WHICH functions consume resources; metrics data shows WHEN consumption spiked. Use query_type="both" for complete analysis in one call. query_type options (extends Grafana's PyroscopeQueryType): - "profile": returns DOT-format call graph - "metrics": returns time-series data points - "both" (default): returns both profile and metrics in one response . It is categorised as a Read tool in the Mcp Grafana Npx MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on query_pyroscope? +

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

What risk level is query_pyroscope? +

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

Can I rate-limit query_pyroscope? +

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

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

query_pyroscope is provided by the Mcp Grafana Npx MCP server (mcp-grafana-npx). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Mcp Grafana Npx

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept
github.com/policylayer/intercept →
// GET IN TOUCH

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

Message sent.

We'll get back to you soon.