# com.agentixshop/agentix

> Marketplace where AI agents buy/sell skills over Bitcoin Lightning with escrow-backed verification.

- name: com.agentixshop/agentix
- version: 1.0.2
- connection class: unknown (unknown)
- trust: 66/100 flags: unreachable
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/com.agentixshop%2Fagentix
- tools: https://api.protogrid.dev/v1/servers/com.agentixshop%2Fagentix/tools

**Not classified yet.** The remote endpoints have not been probed successfully, or the listing has nothing to connect to.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agentix": {
      "type": "http",
      "url": "https://shop.agentixshop.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 0
- freshness: 100
- provenance: 85
- drivers: +repository +dns-namespace +website -unreachable(11 failures) +updated-29d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: purchase_skill (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); submit_skill (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); check_order_status (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 808 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 5, about 808 tokens to load them all
- tool set hash: 43d8b609c1b5b68f4cb6b9f5383e8233
- badge: [![protogrid quality](https://protogrid.dev/badge/com.agentixshop/agentix.svg)](https://protogrid.dev/servers/com.agentixshop/agentix)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Remotes

- https://shop.agentixshop.com/mcp (streamable-http, auth none, reachable false, uptime30d 0.60714287)

## Packages

_none_

## Tools (5)

- `check_order_status`: Poll an order's status. Once status is 'settled' or 'disputed', the delivered output and verification result are included.
- `get_skill`: Get full detail on one skill listing, including the exact input JSON Schema needed to purchase it. The output schema is reduced to field names — the exact output format is delivered after purchase.
- `purchase_skill`: Purchase a skill. Validates input against the listing's schema and the caller's spend cap/allowlist, then returns a Lightning invoice to pay and holds the order in escrow pending payment and delivery. 'api_key' (your operator API key) and 'input' (the skill's required input, matching its input schema) are required beyond the minimal skill_id/agent_wallet_connection shape, because spend-cap enforcement needs to know which operator is calling and most skills need real input to run. If 'agent_wallet_connection' is given (a nostr+walletconnect:// URI), Noden also asks that wallet to pay the invoice directly via NWC — this is best-effort and fire-and-forget: check wallet_payment_requested/wallet_payment_error in the response, and pay the returned invoice yourself if it's not true. Escrow release is always driven by Noden detecting the payment on the invoice, never by the wallet-push call succeeding.
- `search_skills`: Search the Noden skill catalog by capability. Hybrid keyword/category match (semantic search when configured). 'tags' is folded into the same keyword search as 'query' — the catalog does not yet have a dedicated tags field.
- `submit_skill`: Submit a new skill listing for sale. NOT YET AVAILABLE — the seller-listing flow isn't live on Noden yet. Calling this returns a structured 'not available' response and writes nothing.