# call

Call a specific remote tool with provided parameters.

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

## Facts

- Tool: `call`
- 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: Financial (Critical risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Approval-gated

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

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

## Why call is rated Critical

This tool executes arbitrary remote tools on a server explicitly designed for financial capabilities. Since the server's primary purpose is routing financial operations (payments, trades, subscriptions, etc.), calling any remote tool could trigger financial transactions. The most severe applicable category is Financial, given the server context.

From the tool's own definition: "'Call a specific remote tool with provided parameters' on a server described as providing '10,000+ real-world financial capabilities'"

## Use case

AI agents use call to commit financial operations through Qverisai, usually the final step of a payment, billing, or trading workflow. A call moves real money.

## Recommended policy (PolicyLayer)

Verdict: **Approval-gated**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Qverisai:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "call": {
      "deny_if": [
        {
          "conditions": [],
          "on_deny": "Requires human approval."
        }
      ]
    }
  }
}
```

## Other tools on Qverisai (8)

- `execute_tool` — Execute — https://policylayer.com/tools/qverisai-qveris-agent-toolkit/execute-tool.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
- `inspect` — Read — https://policylayer.com/tools/qverisai-qveris-agent-toolkit/inspect.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