call_upstream · Memex MCP: Risk & Policy

WHAT IT DOES

What call_upstream does on Memex

AI agents invoke call_upstream to trigger actions in Memex. 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 call_upstream needs a policy

The server description explicitly mentions 'integration with upstream MCP servers' and acts as an 'MCP gateway.' The tool name 'call_upstream' strongly implies it proxies or triggers operations on upstream MCP servers. Since upstream calls could invoke any category of tool (read, write, execute, destructive, financial), the effective category is Execute with high severity due to the unbounded blast radius.

From the tool's definition Tool name 'call_upstream' in context of an MCP gateway server that integrates with upstream MCP servers.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

call_upstream Rate-limited

call_upstream 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": {
    "call_upstream": {
      "limits": [
        {
          "counter": "call_upstream_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 Memex, so you can run agents against it safely.

FAQ

Questions about call_upstream

What does the call_upstream tool do? +

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

How do I enforce a policy on call_upstream? +

Register the Memex MCP server in PolicyLayer and add a rule for call_upstream: 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 Memex. Nothing to install.

What risk level is call_upstream? +

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

Can I rate-limit call_upstream? +

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

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

call_upstream is provided by the Memex MCP server (queflyhq/memex). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.