# inspect

Inspect tools by their IDs to get detailed information.

Agent View of the PolicyLayer registry record for `inspect`. HTML page: https://policylayer.com/tools/qverisai-qveris-agent-toolkit/inspect

## Facts

- Tool: `inspect`
- Server: Qverisai (`qverisai/qveris-agent-toolkit`) — https://policylayer.com/tools/qverisai-qveris-agent-toolkit.md
- Homepage: https://github.com/QVerisAI/qveris-agent-toolkit
- Risk category: Read (Low risk)
- Registry record: grade C, 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": "inspect",
    "arguments": {}
  }
}
```

## Why inspect is rated Low

The inspect tool queries and returns information about other tools available in the network. This is a non-destructive read operation with no side effects—it merely retrieves and displays tool metadata. The blast radius is minimal since inspection cannot modify, execute, or delete anything.

From the tool's own definition: "Tool name 'inspect' and description 'Inspect tools by their IDs to get detailed information' indicate a read-only operation that retrieves metadata about tools without modification or execution."

## Use case

AI agents call inspect to retrieve information from Qverisai 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 Qverisai:

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

## Other tools on Qverisai (8)

- `execute_tool` — Execute — https://policylayer.com/tools/qverisai-qveris-agent-toolkit/execute-tool.md
- `call` — Financial — https://policylayer.com/tools/qverisai-qveris-agent-toolkit/call.md
- `credits_ledger` — Read — https://policylayer.com/tools/qverisai-qveris-agent-toolkit/credits-ledger.md
- `discover` — Read — https://policylayer.com/tools/qverisai-qveris-agent-toolkit/discover.md
- `get_tools_by_ids` — Read — https://policylayer.com/tools/qverisai-qveris-agent-toolkit/get-tools-by-ids.md
- `probe` — Read — https://policylayer.com/tools/qverisai-qveris-agent-toolkit/probe.md
- `search_tools` — Read — https://policylayer.com/tools/qverisai-qveris-agent-toolkit/search-tools.md
- `usage_history` — Read — https://policylayer.com/tools/qverisai-qveris-agent-toolkit/usage-history.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=qverisai-qveris-agent-toolkit · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/qverisai-qveris-agent-toolkit