a2a-meta-clones

a2a-meta-clones

Deployable MCP clone services for A2A-Meta, hosting pending clones via a multiplexer for Railway deployment.

Category
Visit Server

README

a2a-meta-clones

Canonical policy (binding): This repo is orchestrated by A2A-Meta (sibling of !A2A-Meta-Repos/). See A2A-Meta/docs/repo_topology.md for the relationship, and A2A-Meta/docs/clone_repo_architecture_v0_DRAFT.md for the spec this repo implements.

A2A-Meta/docs/repo_topology.md is the canonical policy document. This README is a convenience mirror, not a second authority. If they conflict, the root side wins.

Deployable MCP clone services for A2A-Meta. Hosts 3 Railway service slots (slot-a, slot-b, slot-c) for the 5 PENDING_CLONES MCP clones catalogued in A2A-Meta/api/middleware/live_clone_catalog.py.

The catalog in A2A-Meta is the single source of truth for which clones are LIVE. This repo vendors a snapshot (via sync_catalog.py) and serves the clones via the multiplexer vendored from A2A-Meta/api/multiplexer.py.

Status (Phase A — local scaffold)

  • Phase A (local scaffold): in progress, see docs/parallel_prep_runlog.md (mirror) and A2A-Meta/docs/a2a_meta_clones_v1_implementation_plan_v0_DRAFT.md (canonical plan)
  • Phase B (GitHub + CI): not started
  • Phase C (Railway provisioning): not started
  • Phase D (deploy + promotion): not started

Local layout

a2a-meta-clones/
├── README.md                        # this file
├── LICENSE                          # MIT
├── .gitignore
├── .env.example                     # shows expected env vars
├── pyproject.toml                   # package metadata
├── Dockerfile                       # shared, used by all 3 slots
├── railway.toml                     # shared template
├── requirements.txt
├── services/
│   ├── slot-a/                      # 2 clones: agent-lens, audit-bazaar
│   ├── slot-b/                      # 2 clones: agent-fabric-oversight, agent-ledger
│   ├── slot-c/                      # 1 clone: compliance-lens (+ 2 free capacity)
│   └── shared/
│       ├── multiplexer/             # vendored from A2A-Meta/api/multiplexer.py
│       ├── catalog_client/          # HTTP client for the A2A-Meta catalog
│       └── middleware/              # shared middleware
├── clone_specs/                     # 10 files: 5 PENDING + 5 backlog
├── server_manifests/                # 10 directories
├── scripts/
│   ├── pipeline.py                  # 9 commands: init / scaffold / test / package / review / verify / promote / demote / status
│   ├── smoke_gate.py                # 8 BLOCKED checks (--dry-run safe)
│   ├── check_no_legacy_slug.py      # token-aware static check
│   ├── verify_endpoint.py           # 4-probe HTTP 200 verify
│   └── sync_catalog.py              # one-way copy of A2A-Meta catalog
├── tests/                           # 9 test files + conftest
└── docs/
    ├── README.md
    ├── env_contract.md
    ├── promotion_log.md
    └── rollback_runbook.md

Quick start (Phase A only)

# 1. Install dependencies
pip install -r requirements.txt

# 2. Run local tests
python -m pytest tests/ -v

# 3. Run the 8 smoke checks (--dry-run is safe; no network)
python scripts/smoke_gate.py --dry-run

# 4. Verify the legacy-slug static check
python scripts/check_no_legacy_slug.py

# 5. Show pipeline status
python scripts/pipeline.py status

What is NOT here

  • No git init in this folder (Phase B's responsibility)
  • No GitHub remote (Phase B)
  • No Railway services (Phase C)
  • No deploys (Phase D)
  • No promotion_request_*.json (Phase D)

This folder is a local scaffold. It will become a Git repo in Phase B.

Cross-references

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured