Skip to main content
Glama

https://github.com/user-attachments/assets/ed36654a-29c4-46ee-b331-5b9afde2b932

waymark

Human oversight as a property of the system, not a property of the agent.

Waymark is MCP middleware that sits between an AI agent and the filesystem. Every write_file and bash call is evaluated against your policy before it touches anything โ€” blocked, held for approval, or logged and allowed. Nothing the agent does is permanent until you say so.

npm downloads npm downloads npm version docs

npm download chart

๐Ÿ“– Full documentation โ†’ โ€” installation, CLI and API reference, policy engine, approvals, rollback, agent monitor, and philosophy.


Three pillars

Control โ€” policy lives in waymark.config.json, not in a system prompt. An agent cannot forget a rule, be jailbroken past it, or accumulate enough context to override it. Every tool call is evaluated in Node.js process space before the filesystem is touched.

blockedPaths    โ†’ BLOCK    (hard deny โ€” secrets, system files)
requireApproval โ†’ PENDING  (human must approve before execution)
allowedPaths    โ†’ ALLOW    (execute immediately, log it)
(default)       โ†’ BLOCK    (unknown paths are rejected)

Observe โ€” the action ledger records every tool call to SQLite with decision, reason, output and timestamps. A dashboard runs at localhost:47000, waymark watch gives a terminal view, and the Agent Monitor shows every AI session on the machine as a live table.

Recover โ€” before-snapshots are captured at write time. A single action can be rolled back, or an entire session undone atomically in reverse order. Approving a write knowing you can undo it is categorically different from approving without a net.


Related MCP server: safe-code-mcp

Quickstart

Zero install:

cd your-project
npx @way_marks/cli init --yes   # config + CLAUDE.md, register MCP
npx @way_marks/cli start        # start server, open the dashboard

Global install with daemon:

npm install -g @way_marks/cli
waymark global-setup            # register the MCP entry once, across all hosts
cd your-project
waymark init                    # project init (idempotent)
waymark daemon start            # one daemon at localhost:47000 for all projects

Restart Claude Desktop, or reload your Claude Code session, to pick up the MCP server.

Installation guide โ†’ ยท Quickstart โ†’ ยท Configuration โ†’


Platform support

Platform

Status

Setup

Claude Desktop

โœ… Recommended

waymark init

Claude Code

โœ… Recommended

waymark init

GitHub Copilot CLI

โœ… Supported

waymark init

GitHub Copilot Chat

โณ Future

Waiting on GitHub MCP

CodeWhisperer, Codeium, others

โณ Future

Waiting on MCP adoption

Runs on Windows, macOS and Linux. Platform guide โ†’


Part of a suite

Tool

Role

What it does

devloop

Build

Multi-agent dev pipeline โ€” architect โ†’ worker โ†’ reviewer

waymark

Run

Policy enforcement and observability for AI agents

teststop

Break

Adversarial scenario testing โ€” acts as a real, impatient user

docuflow

Document

Decision-context wiki for AI agents


Releases

Every release is published on the releases page with its notes and links to the npm packages for that version. The changelog on the documentation site carries the same history in one page.

Installing @way_marks/cli always gives you the current release.


About this repository

This repository is the public home of waymark: usage documentation, release notes and issues. It does not contain the source code โ€” waymark is a commercial product and the implementation is developed privately.

Waymark is free to use, with no warranty and at your own risk. Redistribution, resale, modification and rights in the source code are not granted. Versions published before 2026-08-27 remain under the MIT Licence. See LICENSE.

ยฉ Shaiful Shabuj. All rights reserved.

Maintenance

ActivityMaintained
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    C
    maintenance
    An MCP server that enforces runtime governance on AI agent actions โ€” file access, command execution, delegation chains, and permission escalation.
    MIT
  • F
    license
    Not graded
    quality
    C
    maintenance
    A local MCP server that provides controlled repository access with policy-based file filtering, secret redaction, and audit logging for AI coding agents.
  • A
    license
    Not graded
    quality
    B
    maintenance
    A self-hosted MCP server that enables AI coding agents to read, edit, search, and run code in local projects with human review loops and policy controls.
    MIT
  • A
    license
    Not graded
    quality
    A
    maintenance
    An MCP server that enforces repository governance rules for AI coding agents, providing tools to validate plans, diffs, and scan for architectural and safety violations.
    1
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/waymarks/waymark'

If you have feedback or need assistance with the MCP directory API, please join our Discord server