Low Risk

project

Project ops: list/get/metadata/flow/map. map returns normalized connectivity in structuredContent.map; includeRaw adds original graph payload.

Part of the Dataiku MCP server.

project is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE DATAIKU MCP →

Free to start. No card required.

AI agents call project to retrieve information from Dataiku MCP 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 project 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.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "project": {}
  }
}

See the full Dataiku MCP policy for all 9 tools.

Get this rule live on your own Dataiku MCP server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY DATAIKU MCP →

View all 9 tools →

These attack patterns abuse exactly the kind of access project gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so project only ever does what you allow.

SECURE DATAIKU MCP →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the project tool do? +

Project ops: list/get/metadata/flow/map. map returns normalized connectivity in structuredContent.map; includeRaw adds original graph payload.. It is categorised as a Read tool in the Dataiku MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on project? +

Register the Dataiku MCP server in PolicyLayer and add a rule for 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 Dataiku MCP. Nothing to install.

What risk level is project? +

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

Can I rate-limit project? +

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

Set action: deny in the PolicyLayer policy for 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 project? +

project is provided by the Dataiku MCP server (clssck/Dataiku_MCP). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Dataiku MCP tool call.

Deterministic rules across all 9 Dataiku MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.