create_context · SelfHub MCP Server MCP: Risk & Policy

WHAT IT DOES

What create_context does on SelfHub MCP Server

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

WHY IT NEEDS A POLICY

Why create_context needs a policy

This tool creates new data structures (contexts) within a personal memory hub. It is reversible (contexts can be deleted as evidenced by the sibling 'delete_memory' tool), so it falls under Write rather than Destructive. The severity is medium because misuse could lead to creation of unwanted memory contexts, but the impact is limited to data organization rather than deletion or external system effects.

From the tool's definition Tool description states 'Create a new context for organizing memories' - the word 'Create' indicates data creation. Combined with the server's purpose of storing personal data, this tool creates new organizational structures in the personal memory system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_context Rate-limited

create_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": {
    "create_context": {
      "limits": [
        {
          "counter": "create_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 SelfHub MCP Server, so you can run agents against it safely.

FAQ

Questions about create_context

What does the create_context tool do? +

Create a new context for organizing memories. It is categorised as a Write tool in the SelfHub MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_context? +

Register the SelfHub MCP Server MCP server in PolicyLayer and add a rule for create_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 SelfHub MCP Server. Nothing to install.

What risk level is create_context? +

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

Can I rate-limit create_context? +

Yes. Add a rate_limit block to the create_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 create_context completely? +

Set action: deny in the PolicyLayer policy for create_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 create_context? +

create_context is provided by the SelfHub MCP Server MCP server (sagargupta16/selfhub). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.