English Français العربية

Agentalog — Agent Auto Log

Official registry AI and agents

Agent Auto Log: MCP servers, skills and plugins, with an automatic log of every change.

Source code Website Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code 
claude mcp add --transport http agentalog-agent-auto-log 'https://agentalog.com/mcp'
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "agentalog-agent-auto-log": {
            "type": "http",
            "url": "https://agentalog.com/mcp"
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. Agent Auto Log MCP server
  2. Configure
  3. Use
  4. Access and cost
  5. Documentation and support

Agent Auto Log MCP server

Agent Auto Log (Agentalog) helps an assistant find MCP servers, agent skills and plugins. Each listing provides its source and available repository information. The service also provides tool lists, change history and review signals. This repository contains the connection settings and a user skill. The hosted service runs at agentalog.com.

Configure

The server uses Streamable HTTP. No local program is required. Add this to .vscode/mcp.json for GitHub Copilot in VS Code:

{
  "servers": {
    "agentalog": {
      "type": "http",
      "url": "https://agentalog.com/mcp?checkout=site"
    }
  }
}

For Cursor, use the same entry under mcpServers in .cursor/mcp.json. For other clients, select an HTTP server and enter the URL above. The official registry entry is com.agentalog/meta-agent-tools.

Use

Ask: "Find MCP servers for PostgreSQL and show their source repositories."

  • list_listings searches MCP servers, skills and plugins.
  • get_listing reads one result by its ID.
  • get_listing_readme reads the available documentation.
  • listing_security reads available review signals and their limits.
  • listing_history reads recorded changes.

Use IDs returned by search. Cite the source of each recommendation. Review signals are observations with limits, not a guarantee that a tool is safe. Agentalog is independent of the Official MCP Registry and links to its sources.

Access and cost

Server discovery requires no account. Some searches, reviews and monitoring operations use paid access. If a tool requires payment, complete the purchase on the website. The connection above disables payment transactions through the assistant. Read the current conditions when opening the paid feature.

Documentation and support

Send support requests to contato@agentalog.com or open an issue here. The files in this repository use the MIT-0 license. The hosted service has separate terms. Its source code is not included.

Frequently asked questions

What is Agentalog — Agent Auto Log?

Agent Auto Log: MCP servers, skills and plugins, with an automatic log of every change.

How do I install Agentalog — Agent Auto Log?

It runs as a remote server. In Claude Code: claude mcp add --transport http agentalog-agent-auto-log 'https://agentalog.com/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does Agentalog — Agent Auto Log need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is Agentalog — Agent Auto Log open source?

Yes. Its code is on GitHub under the MIT-0 license.

Who maintains Agentalog — Agent Auto Log?

It is published by wrpbr. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.