Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

toolgate

Small web demo that takes a planned agent tool call and context and returns allow, ask_human or deny with Jev risk scores.

MCP serverprototype
View on GitHub ↗

Overview

This toolgate is a minimal demo, separate from the RiskAverseTech project of the same name. You paste a planned tool or MCP call and some context, and it returns allow, ask_human or deny along with risk scores from TypeSafe Jev.

The README is a single line plus a run command, so implementation details, thresholds and the exact questions are not documented. It is useful as a quick playground for the tool-call gating pattern rather than as a production component.

What the decision model decides

TypeQuestionAnswers
ChoiceShould this planned tool call be allowed, sent to a human, or denied?allow · ask_human · deny

How it works

  1. Paste a planned tool call and context into the app.
  2. Jev scores the call's risk.
  3. The app shows allow, ask_human or deny with the scores.

Strengths

  • Quick way to try tool-call gating with Jev.

Caveats

  • README is minimal; logic and thresholds are undocumented.
  • Demo only, not a hook or proxy.
  • Not the same project as riskaversetech/toolgate.

Getting started

npm i && npm run dev

At a glance

Type
MCP server
Status
prototype
Language
TypeScript
Runtime
Node web app
Has code
yes

Use cases and integrations

How curated lists describe it

Frequently asked questions

What does it decide?

Whether a planned agent tool call should be allowed, escalated to a human, or denied.

Is it the same as the other toolgate?

No, it is a separate, much smaller demo by a different author.

How do I run it?

npm i && npm run dev, with a TypeSafe key presumably required for Jev.

Related projects

  • jev-zig-cli

    Auditable Zig terminal agent pairing Codex for coding with Jev typed preflight and postflight checks under deterministic policy gates.

    CLIproductionZig
  • actiongate-jev

    Gateway that checks agent tool calls with policy plus Jev evidence, then binds approval to a single-use permit for that exact action.

    MCP serverbetaTypeScript
  • Agent Chaperone

    MCP proxy and hooks that screen agent tool calls before they run and their results before the agent reads them, using Jev judgments.

    MCP serverbetaTypeScript
  • agent-guardrail-jev

    Xano backend template where Jev judges each agent tool call as safe, needs review or dangerous, and uncertain calls wait for a human.

    ProjectbetaXanoScript
  • approval-judge-bridge

    OpenAI-compatible endpoint that answers an agent's command-approval call with APPROVE, DENY or ESCALATE from a Jev Choice, failing closed.

    ProxybetaPython
  • claude-jev-plugin

    Claude Code plugin adding Jev judgments to Bash, Write and Edit calls and their outputs; a semantic guardrail, not a sandbox.

    Pluginbeta