Enterprise DNAEnterprise DNA
MMCP ServersDeveloperlow

emektor/toolwrit

by Various

A written authority for AI agents. Allowlist the tools, cap the budget, prove what happened.

Visit siteSubmit your build →

MCP

emektor/toolwrit

Added 18 Oct 2026

#agent-security#ai-agents#audit-log#guardrails#llm#mcp#policy-engine#python
Catalogue record, not a reviewed recommendation. This record can include automatically collected descriptions and setup details. Confirm important claims with the original source. Explore source-reviewed tools.

Overview

A written authority for AI agents that lets you allowlist tools, cap budgets, and prove what happened. It provides a declarative way to define agent permissions and spending limits. Written in TypeScript.

Best for

Best for
Developers building AI agents that need strict tool permissions and audit trails

Use cases

  • Restricting an AI agent to a specific set of tools
  • Setting and enforcing budget caps for agent actions
  • Auditing agent activity with verifiable records

Notes

0 stars on GitHub. Last updated 2026-10-13. Licensed Apache-2.0.

Pros

  • Declarative allowlist for agent tools
  • Built-in budget capping
  • Provides proof of agent actions

Cons

  • Zero stars, so no community validation
  • Vendor listed as Various, so long-term maintenance is unclear
  • Requires agents to follow its written authority model
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to MCP ServersSubmit your own entry →