Agentregistry MCP Server

That's the whole setup. The hook mints an identity for your agent (no account, no API key to manage), wires itself into Claude Code's tool hooks, and

Local serverstdioPython

What is the Agentregistry MCP server?

Most developer tooling work still happens through a UI a human drives. Agentregistry MCP server moves it into the conversation instead. That's the whole setup. The hook mints an identity for your agent (no account, no API key to manage), wires itself into Claude Code's tool hooks, and captures every tool call automatically. When your next session ends, a card prints in.

Getting it running

Installation goes through your MCP client rather than a global install: point it at @tethral/acr-mcp on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

The tools it exposes

The server publishes 6 tools. What each one is for:

  • orient_me — Where am I, what should I do next — state-aware routing
  • log_interaction — Log an interaction with rich fields (retry_count, chain_id, tokens_used…)
  • get_friction_report — The friction lens: where time and tokens go
  • summarize_my_agent — End-of-session summary
  • get_notifications — Unread anomaly-signal notifications for your composition
  • get_my_agent — Identity, dashboard link, registration state

What it needs from you

Configuration is passed through the environment: ACR_ADVANCED. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Agentregistry's toolset — orient_me, log_interaction, get_friction_report and 3 more — is a fair guide to whether it matches your workflow. It is maintained by tethral-inc; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Agentregistry's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
orient_meWhere am I, what should I do next — state-aware routing
log_interactionLog an interaction with rich fields (retry_count, chain_id, tokens_used…)
get_friction_reportThe friction lens: where time and tokens go
summarize_my_agentEnd-of-session summary
get_notificationsUnread anomaly-signal notifications for your composition
get_my_agentIdentity, dashboard link, registration state

How to install the Agentregistry MCP server

{
  "mcpServers": {
    "agentregistry": {
      "command": "npx",
      "args": ["-y", "@tethral/acr-mcp"],
      "env": {
        "ACR_ADVANCED": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
ACR_ADVANCEDConfiguration value read at startup.Optional

Example prompts to try

  • Use Agentregistry to orient me.
  • Use Agentregistry to log interaction.
  • Use Agentregistry to get friction report.

Frequently asked questions

It connects Agentregistry to MCP-compatible AI assistants such as Claude and Cursor, exposing 6 tools (orient_me, log_interaction, get_friction_report, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Agentregistry directly.