Medium Risk

discovery_estimate

Estimate cost, time, and credit requirements before running an analysis. Returns credit cost, estimated duration in seconds, whether you have sufficient credits, and whether a free public alternative exists. Always call this before discovery_analyze for private runs. Args: ...

Handles credentials or secrets (api_key)

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

AI agents use discovery_estimate to create or modify resources in Discovery Engine. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

Without a policy, an AI agent could call discovery_estimate repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Discovery Engine.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

leap-laboratories-discovery-engine.yaml
tools:
  discovery_estimate:
    rules:
      - action: allow
        rate_limit:
          max: 30
          window: 60

See the full Discovery Engine policy for all 12 tools.

Tool Name discovery_estimate
Category Write
Risk Level Medium

View all 12 tools →

Agents calling write-class tools like discovery_estimate 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 Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.

What does the discovery_estimate tool do? +

Estimate cost, time, and credit requirements before running an analysis. Returns credit cost, estimated duration in seconds, whether you have sufficient credits, and whether a free public alternative exists. Always call this before discovery_analyze for private runs. Args: file_size_mb: Size of the dataset in megabytes. num_columns: Number of columns in the dataset. num_rows: Number of rows (optional, improves time estimate). analysis_depth: Search depth (1=fast, higher=deeper). Default 1. visibility: "public" (free, results published) or "private" (costs credits). api_key: Disco API key (disco_...). Optional if DISCOVERY_API_KEY env var is set. . It is categorised as a Write tool in the Discovery Engine MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on discovery_estimate? +

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

What risk level is discovery_estimate? +

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

Can I rate-limit discovery_estimate? +

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

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

discovery_estimate is provided by the Discovery Engine MCP server (leap-laboratories/discovery-engine). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policies on Discovery Engine

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.