Agentlock

io.github.Olum289Published by GitHub account Olum289v0.2.0Updated Oct 24, 2026

Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.

VerifiedStreamable HTTPWeb executableSecurity & Monitoring

Overview

AI-generated overview

AgentLock is a remote security gateway that lets an AI assistant run actions under policies, approvals, and audited execution without sharing secrets.

What you can do
AgentLock acts as a security gateway for AI agents, combining policy enforcement, approval steps, and audited execution. The registry description says secrets are not shared with the agent. No individual tools are listed in the manifest, so the specific operations available are not documented here.
When to use it
Consider it when an assistant needs to perform actions that should be governed by policy and human or system approval, and when you want an audit trail of what was executed. It is less relevant for assistants that only read public information.
Requirements
A remote MCP endpoint at app.agentlock.net over streamable HTTP. Authentication is required: a bearer credential sent in the Authorization header, in the form of an AgentLock API token created in the dashboard. No environment variables or local packages are declared.
Before you install
The server requires an AgentLock API token in the Authorization header; treat it as a secret and keep it out of logs and shared configuration. Because the service is described as executing actions under approval and audit, review which actions are permitted and who approves them before connecting an assistant.

Installation

In SourceWeft

  1. Open Agentlock in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.Olum289%2Fagentlock/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "agentlock": {
      "type": "http",
      "url": "https://app.agentlock.net/api/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

This repository has no README.

Tools

0
SourceWeft has not read this server's tools yet.

Version history

1
  1. v0.2.0LatestSep 16, 2026

Score

60% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.