project_set_context · XL MCP: Risk & Policy

WHAT IT DOES

What project_set_context does on XLMCP

AI agents use project_set_context to create or update resources in XLMCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your XLMCP environment.

WHY IT NEEDS A POLICY

Why project_set_context needs a policy

An AI agent can call project_set_context faster than any human can review — one bad instruction and it creates or modifies resources in XLMCP by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

project_set_context Rate-limited

project_set_context stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "project_set_context": {
      "limits": [
        {
          "counter": "project_set_context_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about project_set_context

What does the project_set_context tool do? +

project_set_context. It is categorised as a Write tool in the XLMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on project_set_context? +

Register the XL MCP server in PolicyLayer and add a rule for project_set_context: 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 XLMCP. Nothing to install.

What risk level is project_set_context? +

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

Can I rate-limit project_set_context? +

Yes. Add a rate_limit block to the project_set_context 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_set_context completely? +

Set action: deny in the PolicyLayer policy for project_set_context. 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_set_context? +

project_set_context is provided by the XL MCP server (xlydiansoftware/aix). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.