approve_all

THE RISK

High Risk

Why approve_all needs a policy

This tool triggers automated job application submissions across multiple external platforms (Lever, Ashby, etc.) for ALL pending items in the queue at once. It initiates external operations with real-world consequences (submitting job applications on behalf of the user) that are difficult or impossible to reverse once submitted. The bulk nature ('all pending jobs') amplifies the blast radius significantly if misused.

From the tool's definition Approve all pending jobs in the queue for application submission

Risk signalsBulk/mass operation — affects multiple targets

Documented attack patterns abuse exactly the kind of access approve_all gives an agent:

POLICY

How to control approve_all

PolicyLayer is an MCP gateway — it sits between your AI agents and Shortlist MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for approve_all:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "approve_all": {
      "limits": [
        {
          "counter": "approve_all_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

approve_all 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.

Create a free account and register Shortlist MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Shortlist MCP Server tools

Destructive clear_queue Clear all jobs from your application queue. Destructive delete_education Delete an education entry by ID. Get the ID from get_profile. Destructive delete_resume Delete a resume by ID. Get the ID from list_resumes. Destructive delete_work_experience Delete a work experience or project by ID. Get the ID from get_profile. Destructive remove_from_queue Remove a specific job from your application queue by its ID. Destructive remove_languages Remove one or more languages from your profile by name. Destructive remove_skills Remove one or more skills from your profile by name. Execute start_applying Start the bot to submit all approved job applications. The bot fills out forms and submits

All 32 Shortlist MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Shortlist MCP Server → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about approve_all

What does the approve_all tool do? +

Approve all pending jobs in the queue for application submission. It is categorised as a Execute tool in the Shortlist MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on approve_all? +

Register the Shortlist MCP Server MCP server in PolicyLayer and add a rule for approve_all: 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 Shortlist MCP Server. Nothing to install.

What risk level is approve_all? +

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

Can I rate-limit approve_all? +

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

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

approve_all is provided by the Shortlist MCP Server MCP server (mls-tech-inc/shortlistjobs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Shortlist MCP Server tool call.

Start from Shortlist MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →