Skip to main content
Glama
aimarket-mcp-packager

aimarket-mcp-packager

AIMarket Hub Plugins

๐Ÿ”„ Synced from the AI-Factory monorepo (append-only history). Pull requests are welcome โ€” merged PRs are imported back and re-synced here. Issues ยท Pull requests

Ecosystem: AICOM overview & live demos ยท Community: Discord ยท Pollux ยท Telegram ยท 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, โ€ฆ) โ€” 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: docs/install.md. All 15 protocol plugins are published; the Hub's plugins extra installs the five core plugins.

Package

PyPI status

aimarket-hub

Published; Python 3.11+

aimarket-tee, aimarket-channels, aimarket-reputation, aimarket-safety, aimarket-mcp-packager

Published; included in pip install "aimarket-hub[plugins]"

aimarket-zk and the remaining protocol plugins

Published; install individually โ€” see the install guide

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

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

Related MCP server: my-mcp-server2

TEE Escrow

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

What

aimarket-tee + provenance + safety โ†’ hold โ†’ invoke โ†’ release/refund

Why

Micropay scale with both-side protection โ€” no human escrow desk

Deep dive

docs/killer-feature-tee-escrow.md ยท Ecosystem capabilities

MCP server โ€” aimarket-mcp-packager

One of the 15 plugins is a full Model Context Protocol server โ€” 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.

Run

python plugins/aimarket-mcp-packager/mcp_stdio_server.py (stdio) ยท docker build from repo root

Tools

package_capability ยท generate_dockerfile ยท generate_claude_desktop_config

Registry

Listed on Glama (score badge above) โ€” see aimarket-mcp-packager/ for the server, glama.json, and Dockerfile

MCP server โ€” 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 โ€” pay-per-call over AIMarket, every result independently verifiable.

Run

pip install aimarket-oracle-gateway, then aimarket-oracle-gateway; configure AIMARKET_HUB_URL and the selected result's AIMARKET_SOURCE_HUB for federated oracles โ€” see its README

Tools

get_random ยท compute_vdf ยท get_reputation_scores ยท list_oracle_capabilities ยท โ€ฆ

Registry

aimarket-oracle-gateway MCP server โ€” glama.json + Dockerfile

Plugin index

Plugin

Role

aimarket-safety

Pre-invoke policy, signed reject

aimarket-tee

TEE attestation, escrow hooks

aimarket-provenance

W3C VC invoke receipts

aimarket-reputation

Scores + stake bonds

aimarket-channels

USDT channel lifecycle

aimarket-auction

Price discovery

aimarket-orchestrator

Multi-capability plans

aimarket-data-cap

Data-capability packaging

aimarket-dataset

Dataset listings

aimarket-mcp-packager

MCP server (stdio) โ€” package capabilities as Docker + MCP manifest + Claude Desktop config

aimarket-nft

Capability NFTs

aimarket-personas

Seller personas

aimarket-promo

Promotions

aimarket-streaming

Streaming invoke

aimarket-zk

ZK 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

Repo

Role

aimarket-hub

Loads plugins at invoke time

oracles

Verifiable math capabilities (separate repo)

aicom

AI-Factory monorepo

dioscuri

Twin community agents โ€” MNEMOSYNE Q&A

Community

The DIOSCURI twins answer questions from synced GitHub docs.

Channel

Twin

Best for

Discord

Pollux

Help, ideas, show-and-tell

Telegram

Castor

Releases, digests, quick news

Ecosystem map: Alien Monitor ยท AICOM

Available Tools

3 tools
generate_claude_desktop_configA

Generate a claude_desktop_config.json snippet for the packaged MCP server.

Takes the same capability inputs as package_capability and returns the mcpServers entry that registers the docker-run MCP server with Claude Desktop (or any MCP host that reads this config format).

Returns: A JSON object (string) containing an mcpServers block โ€” merge it into the user's existing claude_desktop_config.json and restart the host.

Example: generate_claude_desktop_config( capability_id="translate.multi@v2", product_id="prod-translate", name="Lyra Translator", )

Inputs: name (required), product_id (required), capability_id (required), registry, +2 more. Returns: result

generate_dockerfileA

Generate a ready-to-build Dockerfile for the packaged MCP server.

Takes the same capability inputs as package_capability and returns the Dockerfile text that builds the self-hosted MCP server image for it.

Returns: The Dockerfile contents as plain text โ€” write it to Dockerfile and run docker build to produce the image named in package_capability's docker_image field.

Example: generate_dockerfile( capability_id="translate.multi@v2", product_id="prod-translate", name="Lyra Translator", )

Inputs: name (required), product_id (required), capability_id (required), registry, +2 more. Returns: result

package_capabilityA

Build a complete self-hosted MCP server package for an AIMarket capability.

Use this first. It assembles everything needed to ship the capability as a standalone MCP server: the Docker image name, the MCP manifest (server + tool definition), subscription/pricing tiers, and a connection string.

Returns: A JSON object (string) with keys: - docker_image: the image name to build/run. - mcp_manifest: the full MCP manifest (server metadata + tools). - subscription_tiers: pricing tiers derived for the capability. - connection_string: how a client connects to the running server.

Example: package_capability( capability_id="translate.multi@v2", product_id="prod-translate", name="Lyra Translator", description="Translate text into multiple languages.", input_schema={"type": "object", "properties": {"text": {"type": "string"}}, "required": ["text"]}, )

Inputs: name (required), product_id (required), capability_id (required), registry, +2 more. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelogโ€ฆ

    TDQS

    A4.2/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: package_capability builds the package, generate_dockerfile produces the Dockerfile, and generate_claude_desktop_config outputs the config snippet. There is no overlap in functionality.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern (package_capability, generate_dockerfile, generate_claude_desktop_config), making them predictable and easy to understand.

    Tool Count4/5

    With 3 tools, the server is slightly small but well-scoped for its packaging purpose. Each tool serves a necessary step, and adding more would risk bloat.

    Completeness4/5

    The tool set covers the core packaging workflow: build the package, generate Dockerfile, and generate config. Minor gaps exist, such as lacking a validation or listing tool, but the main path is complete.

    Maintenance

    ActivityActive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol server built with FastMCP that features dynamic tool loading and modular management via a dedicated tool directory. It supports both stdio and HTTP transport modes, enabling efficient development and deployment of custom MCP tools.
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol (MCP) server built with the mcp-framework for developing and managing custom tools. It provides a structured foundation for building and integrating modular components like data processors and API clients into Claude Desktop.
      -
    • A
      license
      A
      quality
      B
      maintenance
      Local MCP server that wraps the headless Claude Code CLI as MCP tools, providing stateless access to Claude's coding capabilities through prompt-based interactions. It enables users to execute Claude Code commands with various prompt formats and structured outputs directly from MCP clients.
      3
      MIT