AgentTwin

io.github.AgentTwinPublished by GitHub account AgentTwinv0.3.27Updated Nov 7, 2026

Test AI agent workflows against service twins with injected faults. Runs locally; no source upload.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

AgentTwin provides agent instructions, skills and a read-only documentation MCP for testing AI agent workflows against synthetic service twins with injected…

What you can do
  • Search and read AgentTwin developer documentation through the public docs MCP tools
  • Prepare a real repository workflow with explicit invocation, synthetic fixtures, supported operations and correctness assertions
  • Investigate recorded failures and verify an application repair against unchanged checks
  • Replay a captured run, verify a source-only repair and record the restored baseline as a reviewed regression
  • Supply coding-agent guidance files and plugin configuration for supported clients
When to use it
Useful when you are building or debugging an AI agent or application workflow and want to test it against synthetic service state with injected failures, or when you need the AgentTwin documentation available to a coding assistant. Not a general-purpose testing or production replica service.
Requirements
Runs as a local stdio process via npx (Node.js). The documentation MCP is a public endpoint that needs no credentials. The README notes that installing the skills does not install the AgentTwin CLI, which is separate.
Before you install
Local workflow execution can access the host filesystem and network, so review code, fixtures and invocation before running. The public MCP has no customer access or execution. Static discovery is not a runnable test, and no production replica, provider parity or automatic repair is promised.

Installation

In SourceWeft

  1. Open AgentTwin in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

AgentTwin agent tools

Official public integration resources for AgentTwin agent testing. The product implementation repository is private; this repository contains only public agent instructions, skills and read-only documentation MCP configuration.

AgentTwin is Node.js workflow testing for prepared applications and AI agents. It runs those workflows against synthetic service state, injects supported failures and records operations, state changes and assertions for review. It is a developer integration testing tool, separate from unrelated research projects that use the same name.

Skills

  • agenttwin-prepare — prepare a real repository workflow with explicit invocation, synthetic fixtures, supported operations and correctness assertions.
  • agenttwin-investigate — investigate recorded failures and verify an application repair against unchanged checks.
  • agenttwin-replay — replay a captured run, verify a source-only repair against unchanged checks, and record the restored baseline as a reviewed regression.

Install with a compatible skills client:

sh
npx skills add AgentTwin/agenttwin-agent-tools

Review the skills before installing. This does not install the CLI or run application code. The AgentTwin Node CLI is separate.

The public skill detail pages are agenttwin-prepare and agenttwin-investigate and agenttwin-replay. Directory rankings and security assessments are independent.

Agent configuration

AGENTS.md gives coding agents public integration guidance. Cursor users can opt into .cursor/rules/agenttwin.mdc. The portable Agent Plugins manifest is plugin.json, with the documentation server configured in mcp.json. Use your client's supported plugin installer; client support varies.

The public MCP at https://agenttwin.si/mcp/docs supplies search_docs and read_doc. No credentials are required. It has no customer access or execution. The official MCP Registry entry links to the owned developer page and endpoint.

Maintained references

Local workflow execution can access the host filesystem and network. Review code, fixtures and invocation before running. Static discovery is not a runnable test; no production replica, provider parity or automatic repair is promised.

The canonical maintained source for these public files lives in AgentTwin's website integration bundle. MIT licensed; see LICENSE.

Source: README.md at commit 3d831d0

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.3.27LatestNov 7, 2026

Score

50% 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 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

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

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts