# Agent Jail MCP server

Agent View of the PolicyLayer registry record for Agent Jail: identity, probed posture, risk grade, and all 35 tools classified. HTML page: https://policylayer.com/tools/agent-jail-mcp

## Facts

- Server id: `idiscoord13-sketch/agent-jail-mcp`
- Homepage: https://github.com/idiscoord13-sketch/agent-jail-mcp
- Registry record: grade F, identity unverified
- Lifecycle: active
- Rate-limited: no
- Tools: 35
- Tool categories present: Destructive, Execute, Read, Write
- Tags: agent jail mcp, admin, automation
- Record last modified: 2026-08-07T15:20:08.900Z

## Tools (35)

| Tool | Category | Risk | Record |
| --- | --- | --- | --- |
| `cleanup_expired_sandboxes` | Destructive | Critical | https://policylayer.com/tools/agent-jail-mcp/cleanup-expired-sandboxes.md |
| `destroy_sandbox` | Destructive | Critical | https://policylayer.com/tools/agent-jail-mcp/destroy-sandbox.md |
| `run_in_sandbox` | Execute | High | https://policylayer.com/tools/agent-jail-mcp/run-in-sandbox.md |
| `run_query` | Execute | High | https://policylayer.com/tools/agent-jail-mcp/run-query.md |
| `schedule_task` | Execute | High | https://policylayer.com/tools/agent-jail-mcp/schedule-task.md |
| `add` | Other | Low | https://policylayer.com/tools/agent-jail-mcp/add.md |
| `async_tool` | Other | Low | https://policylayer.com/tools/agent-jail-mcp/async-tool.md |
| `custom_name` | Other | Low | https://policylayer.com/tools/agent-jail-mcp/custom-name.md |
| `greet` | Other | Low | https://policylayer.com/tools/agent-jail-mcp/greet.md |
| `log_progress` | Other | Low | https://policylayer.com/tools/agent-jail-mcp/log-progress.md |
| `multiply` | Other | Low | https://policylayer.com/tools/agent-jail-mcp/multiply.md |
| `my_task` | Other | Low | https://policylayer.com/tools/agent-jail-mcp/my-task.md |
| `my_tool` | Other | Low | https://policylayer.com/tools/agent-jail-mcp/my-tool.md |
| `tool_with_context` | Other | Low | https://policylayer.com/tools/agent-jail-mcp/tool-with-context.md |
| `check_worker_status` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/check-worker-status.md |
| `docker_health` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/docker-health.md |
| `echo_tool` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/echo-tool.md |
| `get_auth_type` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/get-auth-type.md |
| `get_client_ip` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/get-client-ip.md |
| `get_info` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/get-info.md |
| `get_my_emails` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/get-my-emails.md |
| `get_user_id` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/get-user-id.md |
| `greeting` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/greeting.md |
| `introspect` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/introspect.md |
| `list_files` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/list-files.md |
| `list_sandboxes` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/list-sandboxes.md |
| `long_running_task` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/long-running-task.md |
| `read_file` | Read | Low | https://policylayer.com/tools/agent-jail-mcp/read-file.md |
| `add_expense` | Write | Medium | https://policylayer.com/tools/agent-jail-mcp/add-expense.md |
| `create_sandbox` | Write | Medium | https://policylayer.com/tools/agent-jail-mcp/create-sandbox.md |
| `save` | Write | Medium | https://policylayer.com/tools/agent-jail-mcp/save.md |
| `save_contact` | Write | Medium | https://policylayer.com/tools/agent-jail-mcp/save-contact.md |
| `store_data` | Write | Medium | https://policylayer.com/tools/agent-jail-mcp/store-data.md |
| `store_files` | Write | Medium | https://policylayer.com/tools/agent-jail-mcp/store-files.md |
| `submit_form` | Write | Medium | https://policylayer.com/tools/agent-jail-mcp/submit-form.md |

## Tool descriptions

- `cleanup_expired_sandboxes` — Destroy expired sandboxes.
- `destroy_sandbox` — Force destroy a sandbox container.
- `run_in_sandbox` — Run a shell command inside the sandbox container. timeout=0 uses default timeout.
- `docker_health` — Check if Docker daemon is reachable.
- `echo_tool` — Echo the input text
- `get_info` — Provides a simple info.
- `list_files` — List all uploaded files with metadata.
- `list_sandboxes` — List all agent-jail sandbox containers.
- `read_file` — Read an uploaded file's contents by name.
- `create_sandbox` — Create a disposable Docker sandbox for AI agents. Returns sandbox_id.
- `store_files` — Store uploaded files. Receives file objects with name, size, type, data (base64).
- `submit_form` — Validate and process form submission.

## Related servers

- UnClick (1662 tools) — https://policylayer.com/tools/io-github-malamutemayhem-unclick-mcp-server.md
- Delx Mcp A2a (1076 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-a2a.md
- Nodebench (824 tools) — https://policylayer.com/tools/io-github-homenshum-nodebench.md
- Delx MCP Server (740 tools) — https://policylayer.com/tools/io-github-davidmosiah-delx-mcp-server.md
- Binance MCP Server (734 tools) — https://policylayer.com/tools/nirholas-binance-mcp.md
- Eda Agent (726 tools) — https://policylayer.com/tools/eda-agent.md
- GoCreative Agent API (647 tools) — https://policylayer.com/tools/io-github-colinhughes2121-gocreative-agent-api.md
- Yaver (645 tools) — https://policylayer.com/tools/io-github-kivanccakmak-yaver.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=agent-jail-mcp · API: https://policylayer.com/registry/api · Recommended policies for every tool: https://policylayer.com/policies/agent-jail-mcp