verify · Claude Session Continuity MCP: Risk & Policy

WHAT IT DOES

What verify does on Claude Session Continuity

AI agents invoke verify to trigger actions in Claude Session 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 verify needs a policy

This tool executes build, test, and lint processes against a project. Running builds and tests constitutes executing code and external operations. While framed as verification, it actively runs scripts and commands whose effects depend on the project's code and configuration, placing it firmly in the Execute category.

From the tool's definition 프로젝트 검증 (빌드/테스트/린트) — gates include 'build: 빌드 검증', 'test: 테스트 실행', 'lint: 린트 검사'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

verify Rate-limited

verify 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": {
    "verify": {
      "limits": [
        {
          "counter": "verify_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 Claude Session Continuity, so you can run agents against it safely.

FAQ

Questions about verify

What does the verify tool do? +

프로젝트 검증 (빌드/테스트/린트). - gates: 실행할 게이트 배열 (기본: 전체) - build: 빌드 검증 - test: 테스트 실행 - lint: 린트 검사 각 게이트 결과와 전체 성공 여부 반환. 실패 시 에러 메시지 포함. It is categorised as a Execute tool in the Claude Session 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 verify? +

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

What risk level is verify? +

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

Can I rate-limit verify? +

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

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

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