Niches · Guardrails & safety filters
Check an agent's tool call before it runs
No company's docs show a full fit yet. The listings below do the job with a limit, or not at all.
What counts as done
The 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.
How 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
Does the job, with a limit 8
It 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.
| Listing | Why |
|---|---|
| AgentGate D 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. source |
| Cisco AI Defense Inspection API B 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. source |
| Granite Guardian B 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. source |
| Lakera Guard (Check Point AI Guardrails) B 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. source |
| LlamaFirewall D 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. source |
| NVIDIA NeMo Guardrails BB 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. source |
| OpenAI Guardrails BB 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. source |
| Prisma AIRS AI Runtime Security API C 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. source |
Couldn't check 1
The docs were closed to us, or silent. These carry no mark either way.
| Listing | Why |
|---|---|
| Guardrails AI D 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. |
Doesn't do this job 8
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| Amazon Bedrock Guardrails A 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. source |
| Azure AI Content Safety (Prompt Shields) B 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. source |
| Google Cloud Model Armor BB 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. source |
| Llama Guard 4 D Meta Platforms, Inc. | S14 Code Interpreter Abuse covers text only; there is no tool-call input or allow, deny or ask verdict. source |
| Presidio B 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. source |
| Mistral Moderation API B 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. source |
| OpenAI Moderation API BB OpenAI OpCo, LLC | Classifies text and images; no tool-call input or allow, deny or ask verdict. source |
| ShieldGemma C 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. source |
What stops agents finishing
- guardrail screens message text only, so tool-call-only turns pass unchecked
- ask verdict needs a human with no channel to reach them
Around it
Before: inference.tool-loop. After: human-in-the-loop.approve-action, code-sandboxes.run-generated-code.
Where this comes from
Weight 9 of 100 in Guardrails & 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
The same as data: /api/v1/use-cases/guardrails.gate-tool-calls.json, or the MCP tool get_use_case with id guardrails.gate-tool-calls. Other jobs in this category: /api/v1/niches?category=guardrails.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.