aimarket-mcp
<!-- aicom-mirror-notice -->
> **🔄 Synced from a monorepo — but with a live history.** `aimarket-mcp` 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](https://github.com/alexar76/aimarket-mcp/issues)** · **[Pull requests](https://github.com/alexar76/aimarket-mcp/pulls)** both welcome.
# aimarket-mcp — ecosystem MCP gateway
<!-- mcp-name: io.github.alexar76/aimarket-mcp -->
<!-- aicom-readme-badges -->
<p align="center">
<a href="https://github.com/alexar76/aimarket-mcp/actions/workflows/ci.yml"><img src="https://raw.githubusercontent.com/alexar76/aimarket-mcp/refs/heads/main/docs/badges/ci.svg" alt="CI" /></a>
<a href="https://glama.ai/mcp/servers/alexar76/aimarket-mcp"><img src="https://glama.ai/mcp/servers/alexar76/aimarket-mcp/badges/score.svg" alt="aimarket-mcp MCP server" /></a>
<img src="https://raw.githubusercontent.com/alexar76/aimarket-mcp/refs/heads/main/docs/badges/mcp.svg" alt="MCP gateway" />
<img src="https://raw.githubusercontent.com/alexar76/aimarket-mcp/refs/heads/main/docs/badges/transport.svg" alt="stdio + HTTP" />
<img src="https://raw.githubusercontent.com/alexar76/aimarket-mcp/refs/heads/main/docs/badges/tests.svg" alt="14 tests passing" />
<a href="https://raw.githubusercontent.com/alexar76/aimarket-mcp/refs/heads/main/docs/badges/coverage.svg"><img src="https://raw.githubusercontent.com/alexar76/aimarket-mcp/refs/heads/main/docs/badges/coverage.svg" alt="Test coverage" /></a>
<a href="https://github.com/alexar76/aimarket-mcp/blob/main/LICENSE"><img src="https://raw.githubusercontent.com/alexar76/aimarket-mcp/refs/heads/main/docs/badges/license.svg" alt="License: MIT" /></a>
</p>
<!-- /aicom-readme-badges -->
> 🌐 **English** · [Русский](docs/README.ru.md) · [Español](docs/README.es.md) · [Français](docs/README.fr.md) · [中文](docs/README.zh.md) · [Glossary](https://github.com/alexar76/aicom/blob/main/docs/localization-glossary.md)
> ### 🟢 Just want to try the marketplace? Install nothing.
> Paste **`https://modelmarket.dev/mcp`** into your MCP client and you have `market_search`
> and `market_invoke` against the live hub, with a few free trial invokes per caller and a
> signed receipt for each — no wallet, no key, no install.
> → [`docs/hosted-mcp-endpoint.md`](https://github.com/alexar76/aicom/blob/main/docs/hosted-mcp-endpoint.md)
>
> Install **this** package when you want the other three tools (`web_fetch`, `web_search`,
> `metis_verify`), or want to point the market tools at a hub of your own.
**One MCP gateway. Five hardened tools. Shared by Metis, ARGUS, and the ecosystem.**
Transport: **stdio** (`aimarket_mcp/stdio_server.py`) for Glama / Claude Desktop / Cursor, built with the
official **Model Context Protocol** Python SDK ([`mcp`](https://github.com/modelcontextprotocol/python-sdk), `FastMCP`).
Also ships **Streamable-HTTP** on `:9090` for self-hosted deployments (`aimarket-mcp-http`, Docker Compose).
| Item | Location |
|------|----------|
| MCP entrypoint (stdio) | `aimarket_mcp/stdio_server.py` |
| MCP gateway (HTTP) | [`aimarket_mcp/server.py`](aimarket_mcp/server.py) |
| Tool handlers + security | [`aimarket_mcp/tools.py`](aimarket_mcp/tools.py), [`aimarket_mcp/security.py`](aimarket_mcp/security.py) |
| Glama / Docker (stdio) | [`Dockerfile`](Dockerfile), [`glama.json`](glama.json) |
| Self-host HTTP | [`Dockerfile.http`](Dockerfile.http), [`docker-compose.yml`](docker-compose.yml) |
Compatible hosts: Claude Desktop, Cursor, Glama, and any MCP client that supports stdio or Streamable-HTTP.
## Tools
| Tool | What it does | Hardening |
|------|--------------|-----------|
| `web_fetch` | Fetch a URL, return main text (readability-lite) | SSRF-guarded; output sanitized + `<untrusted>`-wrapped |
| `web_search` | Live DuckDuckGo search → top snippets | output sanitized + `<untrusted>` |
| `metis_verify` | Metis cognition + verification envelope | returns answer + `verify_score` / `verified` gate |
| `market_search` | Discover priced capabilities on an AIMarket hub | free; no wallet, key or channel; the hub lists only what it can execute |
| `market_invoke` | Run one on the hub's free trial tier | returns the signed receipt nonce; reports the hub's 402 verbatim when the allowance is spent |
### Example — buy a GAIA Open-Meteo reading
```text
market_search_tool(intent="gaia weather open-meteo")
market_invoke_tool(
capability_id="gaia.weather.read@v1",
product_id="gaia.gateway",
source_hub="https://iot.modelmarket.dev",
# input JSON with device_id om-wx-01 — see tool schema / hub docs
)
```
Or the same HTTP the tool wraps:
```bash
curl -s -X POST "${AIMARKET_HUB_URL:-https://modelmarket.dev}/ai-market/v2/invoke" \
-H 'Content-Type: application/json' \
-H 'X-AIMarket-Sandbox-Visitor: vis_mcp_om_wx' \
-d '{"capability_id":"gaia.weather.read@v1","product_id":"gaia.gateway",
"source_hub":"https://iot.modelmarket.dev","input":{"device_id":"om-wx-01"}}'
```
That is the **easy** path (trial/sandbox). Proving an **external wallet** paid on-chain
is a separate escrow flow (`openChannel` → DebitAuthorization → hub debit/settle) —
see [`docs/onchain-journal.md`](https://github.com/alexar76/aicom/blob/main/docs/onchain-journal.md) §3l–§3m and
[`gaia/docs/LIVE-RELAYS.md`](https://github.com/alexar76/gaia/blob/main/docs/LIVE-RELAYS.md).
Why a gateway (not per-agent tools): generic capabilities are written **once**; the security core lives in one audited place. Ecosystem-specific capabilities live in their own MCP servers (`aimarket-oracle-gateway`, `aimarket-plugins`).
## Configure (env)
| var | meaning |
|-----|---------|
| `AIMARKET_METIS_URL` | Metis verify API base (default `https://metis.modelmarket.dev`) |
| `AIMARKET_METIS_KEY` | optional bearer for Metis verify |
| `AIMARKET_SEARCH_URL` | DuckDuckGo HTML endpoint override |
| `AIMARKET_HUB_URL` | AIMarket hub for `market_search` / `market_invoke` (default `https://modelmarket.dev`) |
| `AIMARKET_API_KEY` | Credit-account key from the hub's `/start` page (`https://modelmarket.dev/start`): priced `market_invoke` calls are paid from its prepaid balance; while it is short the free trial still applies. In HTTP mode it pays for every caller of that server |
| `AIMARKET_SANDBOX_VISITOR` | Trial identity for `market_invoke`; random per install, set it to keep an allowance across reinstalls |
| `AIMARKET_MCP_KEY` | HTTP only — bearer auth key |
| `AIMARKET_MCP_PRODUCTION` | HTTP only — `1` requires `AIMARKET_MCP_KEY` (fail-closed) |
| `AIMARKET_MCP_RATE` | HTTP only — requests/min per key/IP (default 120) |
| `AIMARKET_MCP_PORT` | HTTP only — listen port (default 9090) |
## Run (stdio — Glama / Claude Desktop)
Claude Desktop (`mcpServers` entry) — no clone, no working directory to get wrong:
```json
{
"mcpServers": {
"aimarket-mcp": {
"command": "uvx",
"args": ["aimarket-mcp"]
}
}
}
```
`uvx` fetches the published package and runs its `aimarket-mcp` console script, which is
the stdio server. With the package already installed, `"command": "aimarket-mcp"` and no
args does the same thing.
From a checkout, for development:
```bash
pip install -e .
python -m aimarket_mcp.stdio_server
```
## Run (HTTP — self-host)
```bash
pip install -e .
AIMARKET_MCP_KEY=sk-... AIMARKET_MCP_PRODUCTION=1 aimarket-mcp-http # :9090
# or: docker compose up -d (uses Dockerfile.http)
```
### Cursor / Claude (Streamable HTTP)
```json
{
"mcpServers": {
"aimarket-web": {
"type": "streamable-http",
"url": "http://127.0.0.1:9090/mcp",
"headers": {
"Authorization": "Bearer YOUR_AIMARKET_MCP_KEY"
}
}
}
}
```
## Publish on Glama
Listing: [aimarket-mcp](https://glama.ai/mcp/servers/alexar76/aimarket-mcp).
Glama generates a container from the build settings in its admin panel:
| Field | Value |
|-------|-------|
| Build steps | `["bash scripts/glama_install.sh"]` |
| CMD arguments | `["mcp-proxy", "--", ".venv/bin/python", "-m", "aimarket_mcp.stdio_server"]` |
| Placeholder parameters | `{}` |
| Pinned commit SHA | empty (latest synced commit) |
Build, inspect, and publish a release after syncing source changes. A repository
sync alone does not refresh the deployed tool catalog or its quality evaluation.
The catalog should contain all five tools listed above.
See [Glama build and release instructions](docs/GLAMA.md).
## Consumers
- Connected successfully? Share your host, configuration, and one working tool using
the [Show and tell template](docs/show-and-tell-template.md).
- **Metis** — enable the preset:
```yaml
enable_mcp_tools: true
mcp_ecosystem_presets: [aimarket-web]
```
- **ARGUS** — add the server to `argus.config.json` `mcpServers` (see that repo).
## Test
```bash
pip install -e '.[dev]' && pytest -q
```
## Registries
See the [directory submission checklist and current status](docs/REGISTRIES.md)
before submitting or refreshing a listing.
| Registry | Listing |
|----------|---------|
| **Glama** | [glama.ai/mcp/servers/alexar76/aimarket-mcp](https://glama.ai/mcp/servers/alexar76/aimarket-mcp) |
| **Official MCP Registry** | `io.github.alexar76/aimarket-mcp` — `server.json` + GitHub Actions |
| **PyPI** | `pip install aimarket-mcp` |
| **GitHub Releases** | [github.com/alexar76/aimarket-mcp/releases](https://github.com/alexar76/aimarket-mcp/releases) |
TDQS
Scored across 5 tools
Each tool has a fairly distinct purpose: web_search vs web_fetch (find vs retrieve), market_search vs market_invoke (discover vs execute), and metis_verify is a standalone verification endpoint. The only slight overlap is that market_invoke can run arbitrary hub capabilities while metis_verify runs a specific one, which could raise 'which do I call?' questions, but the descriptions clarify the difference.
All five tools follow the same {domain}_{verb}_tool snake_case convention (web_search_tool, market_invoke_tool, market_search_tool, metis_verify_tool, web_fetch_tool). The redundant '_tool' suffix is unnecessary but applied uniformly, so it remains fully predictable.
Five tools is a lean but reasonable set covering search, fetch, market discovery, invocation, and verification. It is on the thin side for a market/hub server since no tool exposes trial quota, hub config, or errors-as-state beyond what invoke returns, but nothing feels padded.
The core loop is covered: discover capabilities (market_search), run one (market_invoke), verify output (metis_verify), plus web search/fetch for grounding. Minor gaps exist (no tool to inspect remaining trial invokes or hub status), and paid escrow is intentionally excluded, but agents can work around these.