{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/guardrails.gate-tool-calls/",
    "json": "https://www.anchorterminal.com/niches/guardrails.gate-tool-calls/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/guardrails.gate-tool-calls/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/guardrails.gate-tool-calls/index.min.md"
  },
  "markdown": "No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 0 | 8 | 20 | 9 | 5 |\n\n## What counts as done\n\nThe tool name and arguments are screened before execution, the verdict is allow, deny or ask a person with a reason, secrets and personal data in arguments are caught, and a turn that holds only tool calls is not skipped.\n\nHow agents ask for it: stop the agent running dangerous shell commands; check this tool call before executing it; block tool calls that leak secrets or customer data\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **AgentGate (Mohit Singh (individual))**: POST /v1/assess scores tool name and arguments before execution and returns allow, deny or ask with reason_codes, and on_model_error defaults to ask; but secret or PII detection in arguments is not a head, and the classifier has no published accuracy.\n- **Cisco AI Defense Inspection API (Cisco Systems, Inc.)**: MCP inspection covers call_tool and list_tools messages before they run and returns is_safe with the triggered rules, but there is no ask-a-person verdict.\n- **Granite Guardian (International Business Machines Corporation)**: available_tools and the function calling hallucination criterion check a call against the declared tools, and custom criteria can state a rule, but the verdict is yes or no with no ask outcome and secrets are not a pre-baked target.\n- **Lakera Guard (Check Point AI Guardrails) (Check Point Software Technologies Ltd.)**: tool_calls are screened as the agent's actions with a Tool Allow/Deny List and a beta Dangerous Deviation detector, but the verdict is flagged or not, with no ask-a-person outcome.\n- **LlamaFirewall (Meta Platforms, Inc.)**: AlignmentCheck audits the trace and assistant tool_calls against the user's goal, and ScanDecision has allow, block and human_in_the_loop_required; but it calls Together AI by default and nothing targets secrets in arguments.\n- **NVIDIA NeMo Guardrails (NVIDIA Corporation)**: Tool call validation blocks undeclared tools and schema-violating arguments, fails closed and names the reason, but it is structural only: no secret or PII screening of arguments and no ask-a-person verdict.\n- **OpenAI Guardrails (OpenAI (as named in the LICENSE copyright line and the PyPI author field))**: Before tool calls run, the check tests whether the requested function fits the user's goal and trips a block, but there is no ask-a-person verdict and secrets in arguments are not named as a target.\n- **Prisma AIRS AI Runtime Security API (Palo Alto Networks, Inc.)**: tool_event takes the raw JSON input of an MCP or function call and tool_detected reports findings with an allow or block action, but there is no ask-a-person verdict.\n\n## Couldn't check\n\nThe docs were closed to us, or silent. These carry no mark either way.\n\n- **Guardrails AI (Guardrails AI, Inc.)**: Issue 1601 on validating tool calls with on=\"tools:...\" is closed, but no shipped docs or release note confirming it were read.\n\n- not this job: Amazon Bedrock Guardrails (Amazon Web Services, Inc.): The docs state that in tool-use workloads tool-call arguments, tool results and tool definitions are not evaluated, and acc-18 saw tool-call-only turns never sent; there is no allow, deny or ask verdict on an action.\n- not this job: Azure AI Content Safety (Prompt Shields) (Microsoft Corporation): Prompt Shields scan user input and, in preview for agents, tool responses; nothing read screens tool-call names and arguments or returns an allow, deny or ask verdict.\n- not this job: Google Cloud Model Armor (Google LLC): The sanitize calls take a user prompt or a model response; the overview names no tool-call field, tool definition screening or allow, deny or ask verdict.\n- not this job: Llama Guard 4 (Meta Platforms, Inc.): S14 Code Interpreter Abuse covers text only; there is no tool-call input or allow, deny or ask verdict.\n- not this job: Presidio (Data Privacy Stack (community organisation, no legal entity stated)): It can find PII in argument text a caller passes, but returns entities, not an allow, deny or ask verdict on a tool call.\n- not this job: Mistral Moderation API (Mistral AI (RCS Paris 952 418 325)): Moderation classifies text or the last conversation turn; no tool-call argument screening or allow, deny or ask verdict is documented.\n- not this job: OpenAI Moderation API (OpenAI OpCo, LLC): Classifies text and images; no tool-call input or allow, deny or ask verdict.\n- not this job: ShieldGemma (Google LLC (RDAP registrant of gemma.ai; the Gemma Terms of Use are Google's and the cards name Google as author)): Takes a prompt or a prompt and response; no tool-call input or verdict.\n\n## What stops agents finishing\n\n- guardrail screens message text only, so tool-call-only turns pass unchecked\n- ask verdict needs a human with no channel to reach them\n\n## Around it\n\nBefore: inference.tool-loop. After: human-in-the-loop.approve-action, code-sandboxes.run-generated-code.\n\n## Where this comes from\n\nWeight 9 of 100 in Guardrails \u0026 safety filters: 5 of 50 accounts, two of them from builders of competing tools (acc-41, acc-42) and one a vendor-run benchmark; the job is named often but few users report doing it with a listed tool\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/guardrails.gate-tool-calls.json, or the MCP tool get_use_case with id guardrails.gate-tool-calls. Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Check an agent's tool call before it runs",
        "url": ""
      }
    ],
    "description": "Check an agent's tool call before it runs: 0 companies fully do it, 8 with a limit, 20 carry the tag. Every listing in Guardrails \u0026 safety filters with the reason and a source.",
    "facts": null,
    "h1": "Check an agent's tool call before it runs",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/guardrails.gate-tool-calls/",
    "published": "",
    "section": "agents",
    "title": "Check an agent's tool call before it runs | Anchor Terminal",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/guardrails.gate-tool-calls/"
  },
  "tokens": {
    "markdown": 1600,
    "slim": 380
  },
  "version": 1
}
