mcpField
A
AIMarket MCP Packager

AIMarket MCP Packager

Local
github.com/alexar76Developer Tools3Updated 1d ago

About AIMarket MCP Packager

AIMarket MCP Packager is a stdio MCP server in the AIMarket plugin collection, for developers turning AIMarket capabilities into standalone products. It generates a Docker image, MCP manifest, and Claude Desktop configuration.

Key features

  1. 01Package capabilities as MCP products
  2. 02Generate Dockerfiles
  3. 03Create MCP manifests
  4. 04Generate Claude Desktop configs

Use cases

  1. 01Turn an AIMarket capability into a self-hosted service
  2. 02Prepare Docker deployment files for a capability
  3. 03Configure Claude Desktop connections
  4. 04Package products for stdio MCP clients

MCP support

It is a stdio MCP server built with the official MCP Python SDK. Its tools—`package_capability`, `generate_dockerfile`, and `generate_claude_desktop_config`—package AIMarket capabilities as MCP products.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"alexar76-aimarket-plugins": {
"command": "uvx",
"args": [
"aimarket-mcp-packager"
],
"env": {
"AIMARKET_HUB_URL": "<AIMARKET_HUB_URL>"
}
}
}
}
Run commanduvx aimarket-mcp-packager
Environment variables to set
AIMARKET_HUB_URLAIMarket Hub base URL

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiaimarket-mcp-packager2.1.2

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

🔄 Synced from a monorepo — but with a live history. aimarket-plugins mirrors the canonical AI-Factory monorepo. History here is append-only (no force-push). Pull requests are welcome — merged PRs are imported back into the monorepo and re-synced here, so your contribution becomes canonical. 💬 Issues · Pull requests both welcome.

AIMarket Hub Plugins

CI aimarket-plugins MCP server Test coverage License: MIT AND Apache-2.0

Ecosystem: AICOM overview & live demos · Community: Discord · Pollux · Telegram · Castor

15 protocol plugins extend hub invoke, settlement, compliance, and data planes without forking core.

Verifiable math lives in the separate oracles monorepo (Platon, Chronos, Murmuration, Lumen, …) — listed on the hub like any capability. aimarket-reputation scores sellers; Lumen oracle supplies PageRank/EigenTrust-style trust artifacts agents can invoke and audit.

Install

PyPI (top-5): docs/install.md

PackagePyPI status
aimarket-hub✅ 3.0.0
aimarket-tee, aimarket-channels, aimarket-reputation✅ 2.0.0
aimarket-safety, aimarket-mcp-packager⏳ pending (PyPI new-project rate limit — install from source until published)
aimarket-zk⏳ monorepo only — pip install -e plugins/aimarket-zk until PyPI publish

Docker: all 15 plugins ship in the production hub image — ./scripts/deploy_hub.sh from the factory monorepo.

Source: pip install -e plugins/aimarket-tee after cloning this repo.

TEE Escrow

Smart-contract escrow in a Trusted Execution Environment — buyer funds stay held until attested invoke succeeds; seller is paid only on proof; failures refund on-channel.

Whataimarket-tee + provenance + safety → hold → invoke → release/refund
WhyMicropay scale with both-side protection — no human escrow desk
Deep divedocs/killer-feature-tee-escrow.md · Ecosystem capabilities

MCP server — aimarket-mcp-packager

One of the 15 plugins is a full Model Context Protocol server — stdio transport, built on the official MCP Python SDK. aimarket-mcp-packager turns any AIMarket capability into a self-hosted MCP product (Docker image, MCP manifest, and a ready claude_desktop_config.json) that runs in Claude Desktop, Cursor, Glama, or any stdio MCP client.

Runpython plugins/aimarket-mcp-packager/mcp_stdio_server.py (stdio) · docker build from repo root
Toolspackage_capability · generate_dockerfile · generate_claude_desktop_config
RegistryListed on Glama (score badge above) — see aimarket-mcp-packager/ for the server, glama.json, and Dockerfile

MCP server — aimarket-oracle-gateway (standalone repo)

A second MCP server ships as its own satellite repo alexar76/aimarket-oracle-gateway for Glama indexing. aimarket-oracle-gateway exposes Platon randomness, Chronos VDF, and LUMEN reputation as agent-callable tools — pay-per-call over AIMarket, every result independently verifiable.

RunAIMARKET_HUB_URL=https://modelmarket.dev python mcp_stdio_server.py
Toolsget_random · compute_vdf · get_reputation_scores · list_oracle_capabilities · …
Registryaimarket-oracle-gateway MCP server — glama.json + Dockerfile

Plugin index

PluginRole
aimarket-safetyPre-invoke policy, signed reject
aimarket-teeTEE attestation, escrow hooks
aimarket-provenanceW3C VC invoke receipts
aimarket-reputationScores + stake bonds
aimarket-channelsUSDT channel lifecycle
aimarket-auctionPrice discovery
aimarket-orchestratorMulti-capability plans
aimarket-data-capData-capability packaging
aimarket-datasetDataset listings
aimarket-mcp-packagerMCP server (stdio) — package capabilities as Docker + MCP manifest + Claude Desktop config
aimarket-nftCapability NFTs
aimarket-personasSeller personas
aimarket-promoPromotions
aimarket-streamingStreaming invoke
aimarket-zkZK cohort proofs

Hub loads plugins from aimarket-hub/plugins/ at runtime. Monorepo copies under plugins/ are the source-of-truth for docs and tests.

Demo

Related repos

RepoRole
aimarket-hubLoads plugins at invoke time
oraclesVerifiable math capabilities (separate repo)
aicomAI-Factory monorepo
dioscuriTwin community agents — MNEMOSYNE Q&A

Community

The DIOSCURI twins answer questions from synced GitHub docs.

ChannelTwinBest for
DiscordPolluxHelp, ideas, show-and-tell
TelegramCastorReleases, digests, quick news

Ecosystem map: Alien Monitor · AICOM

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.