query_project · Watson Discovery MCP Server MCP

WHAT IT DOES

What query_project does on Watson Discovery MCP Server

AI agents invoke query_project to trigger actions in Watson Discovery MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why query_project needs a policy

The server description explicitly mentions 'executing natural language queries', and sibling tools suggest this tool runs queries against Watson Discovery projects. Queries can trigger backend processing and retrieve data, placing this in Execute. However, the empty description lowers confidence — it could be a pure Read operation.

From the tool's definition Tool name 'query_project' on a server described as 'executing natural language queries' against Watson Discovery.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

query_project Rate-limited

query_project stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "query_project": {
      "limits": [
        {
          "counter": "query_project_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about query_project

What does the query_project tool do? +

query_project. It is categorised as a Execute tool in the Watson Discovery MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on query_project? +

Register the Watson Discovery MCP Server MCP server in PolicyLayer and add a rule for query_project: 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 Watson Discovery MCP Server. Nothing to install.

What risk level is query_project? +

query_project is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit query_project? +

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

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

query_project is provided by the Watson Discovery MCP Server MCP server (matlock08/watson_discovery_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// THE FULL RECORD

query_project is one line of Watson Discovery MCP Server's registry record.

The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →