M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
A

AIWG

Community
Not a standard server
A multi-agent framework for multi-platform AI-assisted software development

This is not a typical connect-and-use MCP server; read the source repository before using it.

How to install ↓ Compare GitHub source repository ↗
Category
Dev Tools #394 of 438
Stars
★ 224 Very popular
Runtime
Node.js 20+
Credentials
No credential needed
License
MIT
Last commit
34FMRS · D

The supplied material identifies AIWG as an MIT-licensed, multi-platform AI development workflow and deployment tool that includes MCP integration. However, no server manifest is available, so its specific tools, transport, installation configuration, authentication, and client support cannot be confirmed.

Strongest · Maintenance 11/20 Weakest · Reliability 3/20

Reliability
3/20
Security and permissions
8/20
Maintenance
11/20
Documentation
8/20
Setup experience
4/20
Why each score
Reliability 3/20
The static material provides no cached server manifest, transport details, tool list, parameter schemas, initialization-handshake evidence, tests, or CI coverage. The README merely claims MCP integration, so startup success and consistency between declared and actual tools cannot be verified; substantial points are deducted, and static calibration prevents a score above 12.
Security and permissions 8/20
The README mentions token-security rules, scoped deployment, optional native features, signed releases, and supply-chain verification, but these are unverified documentation claims. There is no evidence for an MCP-specific permission model, authentication, data flows, network scope, confirmation of dangerous actions, or isolation boundaries, so least privilege and controllable side effects are unproven. No explicit fact establishes a security red line.
Maintenance 11/20
The repository is not archived and has an MIT license, 168 stars, and 1 open issue; the README also describes versioned releases and signing. These provide only basic maintenance signals. There is no evidence of commit cadence, actual release history, dependency updates, a vulnerability-response channel, or MCP-specific ownership, so significant points are deducted.
Documentation 8/20
The README is extensive for the overall framework, installation, platform deployment, troubleshooting, and feature inventory, but its MCP coverage is only high-level. It lacks reviewable server-manifest details, tool parameters, connection configuration, authentication, limits, error behavior, cost information, and MCP troubleshooting. Conflicting counts and platform claims in the README also reduce confidence, so a high score is not justified.
Setup experience 4/20
The README gives Node.js and CLI installation steps and mentions MCP as an integration surface, but it provides no server-specific launch command, transport configuration, mainstream MCP-client example, authentication procedure, or tool-verification workflow. Because the MCP setup path is not reproducible from the supplied material, the score is low.

Static review · not runListed 2026-07-30

Read the FMRS scoring method →

Fit and risk

What it can accessReads local filesWrites / deletes local files

Best for

  • Teams that need to reuse agents, skills, commands, and rules across multiple AI coding platforms
  • Complex projects lasting weeks or months that require project memory, quality gates, and auditability
  • Developers who want to deploy plain-text AI artifacts through a CLI

Not for

  • Simple scripts, typo fixes, or code explanations that fit in a single conversation
  • Users who require a confirmed MCP tool list, transport protocol, or client compatibility guarantee
  • Users seeking an LLM runtime or a framework imported directly into an application

Required permissions

  • Write agents, skills, rules, and context files to project- or user-level directories according to the selected platform and scope
  • Project deployments may create or update .aiwg/ and platform-specific directories
  • Optional native features may build dependencies such as node-pty or hnswlib-node

Risks and side effects

  • Global user-scope deployment may cause context or agent sets to bleed across projects
  • The README's quantitative claims, research findings, and performance statements are not independently verified by the supplied material
  • Because the server manifest is unavailable, the MCP endpoint, tool permissions, authentication, and data-access scope cannot be confirmed

Setup

Before you start

Runtime：Node.js 20+

The server manifest is not cached, so the MCP server's exact installation or launch procedure cannot be confirmed. The README gives general AIWG installation instructions: install Node.js 20 or later, run npm install -g aiwg, then run aiwg use <framework> or aiwg use all from a project root. These steps are not a verified MCP server configuration.

Check that it works

Run `aiwg status --probe --` (or `aiwg doctor`) to confirm deployment is engaged, or ask your AI assistant for project status and confirm it reads .aiwg/ artifacts.

Troubleshooting

  1. Confirm that Node.js 20 or later is installed
  2. For npm EACCES errors, check a user-owned npm prefix and avoid using sudo npm install -g aiwg as the default fix
  3. If the aiwg command is missing, check whether npm's global bin directory is on PATH
  4. Run aiwg doctor to inspect installation and optional native-feature health
  5. MCP connection troubleshooting cannot be verified because the README provides no server transport or launch configuration

Things to try

Once connected, you can ask your AI assistant things like:

  • Deploy the AIWG SDLC framework to this project and explain the plan first
  • Run a security review and summarize the review panel's feedback
  • Check which AIWG artifacts are deployed in this workspace and their health
  • Help me transition from the inception phase to elaboration

Use cases

Deploying AI artifacts across Claude Code, Codex, Copilot, Cursor, Warp, Factory, OpenCode, and Windsurf
Supporting software development lifecycle work with multi-agent workflows
Maintaining cross-session project memory and traceable artifacts through .aiwg/
Running structured security, testing, architecture, research, forensics, and operations workflows

Overview

AIWG is a cognitive architecture and deployment tool for AI-augmented software development. It provides specialized agents, structured SDLC workflows, plain-text agent artifacts, project memory, quality gates, and deployment across multiple AI platforms. The README explicitly lists MCP integration, but no cached server manifest, tool definitions, transport details, or client compatibility information is provided.

Similar servers

Context7 80 · B

Upstash's official server providing up-to-date third-party library docs for AI coding assistants

★ 63.3k · Tools 2 Compare with this →
Compare with other MCP servers

Source revision f0b81eab9d9f Data synced 2026-10-19 Read the FMRS scoring method