agt_policy_check_text

THE RISK

High Risk

Why agt_policy_check_text needs a policy

The tool actively runs security analysis checks (poisoning detection, prompt-defense) against arbitrary text input. This constitutes execution of analysis/scanning operations rather than passive data retrieval. While it doesn't modify data, it triggers external processing pipelines. Misuse could involve feeding adversarial text to probe or bypass security checks, making severity medium.

From the tool's definition 'Run AGT poisoning, MCP, and prompt-defense checks against arbitrary text'

Documented attack patterns abuse exactly the kind of access agt_policy_check_text gives an agent:

POLICY

How to control agt_policy_check_text

PolicyLayer is an MCP gateway — it sits between your AI agents and Agentos, and nothing reaches the server without passing your rules. This is the rule we recommend for agt_policy_check_text:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "agt_policy_check_text": {
      "limits": [
        {
          "counter": "agt_policy_check_text_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

agt_policy_check_text stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

Create a free account and register Agentos — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Agentos tools

Execute deploy_agent Deploy an agent to start execution. Deployment environments: - local: Runs on your machin Execute establish_handshake Initiate a trust handshake with a peer agent. Creates a cryptographic challenge, reco Write attach_policy Attach safety policies to an agent. Policies enforce rules and constraints on agent behavi Write create_agent Create a new AI agent from a natural language description. The agent will be configured wi Write create_policy Create a custom policy from a natural language description. Policies define rules that ag Write record_interaction Record an interaction outcome to update trust scores. Valid outcomes: success, failur Write request_approval Request human approval for a sensitive agent action. Use this when: - Policy requires hum Read agt_policy_status Return the active AGT Antigravity policy runtime status and summary.

All 18 Agentos tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

Govern code and CI agents → Branch allowlists, approval on merges, and rate caps on the build and pipeline tools agents trigger.
High-risk tools in Agentos → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →
PolicyLayer vs alternatives → How deterministic, per-call MCP policy compares with gateways, identity layers, and authorisation platforms.

FAQ

Questions about agt_policy_check_text

What does the agt_policy_check_text tool do? +

Run AGT poisoning, MCP, and prompt-defense checks against arbitrary text. It is categorised as a Execute tool in the Agentos MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on agt_policy_check_text? +

Register the Agentos MCP server in PolicyLayer and add a rule for agt_policy_check_text: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Agentos. Nothing to install.

What risk level is agt_policy_check_text? +

agt_policy_check_text is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit agt_policy_check_text? +

Yes. Add a rate_limit block to the agt_policy_check_text rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block agt_policy_check_text completely? +

Set action: deny in the PolicyLayer policy for agt_policy_check_text. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides agt_policy_check_text? +

agt_policy_check_text is provided by the Agentos MCP server (@microsoft/agentos-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Agentos tool call.

Start from Agentos, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →