execute_claude · MCP Claude Context Continuity MCP

WHAT IT DOES

What execute_claude does on MCP Claude Context Continuity

AI agents invoke execute_claude to trigger actions in MCP Claude Context Continuity. 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 execute_claude needs a policy

This tool runs the Claude CLI, which can trigger external operations and computational processes whose effects depend on the arguments passed. While not destructive by itself, CLI execution is inherently an Execute category risk due to the potential for the AI to invoke arbitrary Claude operations with side effects. The high severity reflects the broad scope of actions possible through CLI invocation.

From the tool's definition Tool name is 'execute_claude' and description states 'Claude CLIを実行して結果を返す' (Execute the Claude CLI and return results). The verb 'execute' directly indicates code/command execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_claude Rate-limited

execute_claude 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": {
    "execute_claude": {
      "limits": [
        {
          "counter": "execute_claude_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 MCP Claude Context Continuity, so you can run agents against it safely.

FAQ

Questions about execute_claude

What does the execute_claude tool do? +

Claude CLIを実行して結果を返す. It is categorised as a Execute tool in the MCP Claude Context Continuity MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_claude? +

Register the MCP Claude Context Continuity MCP server in PolicyLayer and add a rule for execute_claude: 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 MCP Claude Context Continuity. Nothing to install.

What risk level is execute_claude? +

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

Can I rate-limit execute_claude? +

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

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

execute_claude is provided by the MCP Claude Context Continuity MCP server (tethiro/mcp-claude-context-continuity). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.