# introspect

A read tool on the Sap Btp Destination MCP server.

Agent View of the PolicyLayer registry record for `introspect`. HTML page: https://policylayer.com/tools/facusada-mcp-btp/introspect

## Facts

- Tool: `introspect`
- Server: Sap Btp Destination (`facusada/mcp-btp`) — https://policylayer.com/tools/facusada-mcp-btp.md
- Homepage: https://github.com/facusada/mcp-btp
- Risk category: Read (Low risk)
- Registry record: grade D, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "introspect",
    "arguments": {}
  }
}
```

## Why introspect is rated Low

Introspection typically retrieves metadata or configuration details (Read category). However, without explicit description, there is some uncertainty. The 'medium' severity reflects that introspecting SAP BTP destination configurations could expose sensitive endpoint URLs, authentication types, or credentials if not properly restricted—moderate blast radius if an agent queries and exfiltrates this metadata.

From the tool's own definition: "Tool name 'introspect' combined with server purpose (reads Destination Service configurations and exposes endpoints/tools). The empty description is uninformative, lowering confidence slightly."

## Use case

AI agents call introspect to retrieve information from Sap Btp Destination without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Sap Btp Destination:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "introspect": {}
  }
}
```

## Other tools on Sap Btp Destination (35)

- `call_destination` — Execute — https://policylayer.com/tools/facusada-mcp-btp/call-destination.md
- `run_query` — Execute — https://policylayer.com/tools/facusada-mcp-btp/run-query.md
- `admin_tool` — Other — https://policylayer.com/tools/facusada-mcp-btp/admin-tool.md
- `async_tool` — Other — https://policylayer.com/tools/facusada-mcp-btp/async-tool.md
- `custom_name` — Other — https://policylayer.com/tools/facusada-mcp-btp/custom-name.md
- `flexible_task` — Other — https://policylayer.com/tools/facusada-mcp-btp/flexible-task.md
- `greet` — Other — https://policylayer.com/tools/facusada-mcp-btp/greet.md
- `greeting` — Other — https://policylayer.com/tools/facusada-mcp-btp/greeting.md
- `multiply` — Other — https://policylayer.com/tools/facusada-mcp-btp/multiply.md
- `my_task` — Other — https://policylayer.com/tools/facusada-mcp-btp/my-task.md
- `my_tool` — Other — https://policylayer.com/tools/facusada-mcp-btp/my-tool.md
- `protected_tool` — Other — https://policylayer.com/tools/facusada-mcp-btp/protected-tool.md
- `check_worker_status` — Read — https://policylayer.com/tools/facusada-mcp-btp/check-worker-status.md
- `echo_tool` — Read — https://policylayer.com/tools/facusada-mcp-btp/echo-tool.md
- `get_auth_type` — Read — https://policylayer.com/tools/facusada-mcp-btp/get-auth-type.md
- `get_client_ip` — Read — https://policylayer.com/tools/facusada-mcp-btp/get-client-ip.md
- `get_destination` — Read — https://policylayer.com/tools/facusada-mcp-btp/get-destination.md
- `get_info` — Read — https://policylayer.com/tools/facusada-mcp-btp/get-info.md
- `get_my_emails` — Read — https://policylayer.com/tools/facusada-mcp-btp/get-my-emails.md
- `get_user_id` — Read — https://policylayer.com/tools/facusada-mcp-btp/get-user-id.md
- `healthcheck` — Read — https://policylayer.com/tools/facusada-mcp-btp/healthcheck.md
- `list_files` — Read — https://policylayer.com/tools/facusada-mcp-btp/list-files.md
- `log_progress` — Read — https://policylayer.com/tools/facusada-mcp-btp/log-progress.md
- `long_running_task` — Read — https://policylayer.com/tools/facusada-mcp-btp/long-running-task.md
- `read_file` — Read — https://policylayer.com/tools/facusada-mcp-btp/read-file.md
- `read_write_tool` — Read — https://policylayer.com/tools/facusada-mcp-btp/read-write-tool.md
- `tool_with_context` — Read — https://policylayer.com/tools/facusada-mcp-btp/tool-with-context.md
- `add` — Write — https://policylayer.com/tools/facusada-mcp-btp/add.md
- `add_expense` — Write — https://policylayer.com/tools/facusada-mcp-btp/add-expense.md
- `save` — Write — https://policylayer.com/tools/facusada-mcp-btp/save.md
- …and 5 more: https://policylayer.com/tools/facusada-mcp-btp.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=facusada-mcp-btp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/facusada-mcp-btp