set_current_project · AgentCortex MCP: Risk & Policy

WHAT IT DOES

What set_current_project does on AgentCortex MCP

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

WHY IT NEEDS A POLICY

Why set_current_project needs a policy

This tool modifies persistent application state (the current project selection) that persists across operations and influences the behavior of other tools. While not creating new data objects like create_project would, it changes the active context in a way that affects memory and task operations going forward. This is a reversible Write operation since switching to a different project can undo the effect.

From the tool's definition Tool description states it will 'Switch the active project context' and 'All memory and task operations will use this project until changed.' This modifies the state of the system by changing which project is currently active, affecting subsequent operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

set_current_project Rate-limited

set_current_project 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": {
    "set_current_project": {
      "limits": [
        {
          "counter": "set_current_project_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 AgentCortex MCP, so you can run agents against it safely.

FAQ

Questions about set_current_project

What does the set_current_project tool do? +

Switch the active project context. All memory and task operations will use this project until changed. It is categorised as a Write tool in the AgentCortex MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on set_current_project? +

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

What risk level is set_current_project? +

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

Can I rate-limit set_current_project? +

Yes. Add a rate_limit block to the set_current_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 set_current_project completely? +

Set action: deny in the PolicyLayer policy for set_current_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 set_current_project? +

set_current_project is provided by the AgentCortex MCP server (sage-hq/agentcortex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.