# AgentPort Discovery

> Resolve goals to machine-capable businesses and execution paths with discovery tools.

- name: io.github.maxioos/agentport-discovery
- version: 0.10.0
- connection class: R0 (autonomous)
- trust: 73/100 flags: no-repository
- quality: 96/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.maxioos%2Fagentport-discovery
- tools: https://api.protogrid.dev/v1/servers/io.github.maxioos%2Fagentport-discovery/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agentport-discovery": {
      "type": "http",
      "url": "https://discover.agentport.maxioos.com/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 98
- freshness: 85
- provenance: 35
- drivers: +reachable +uptime-96% ~updated-52d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 96/100 (good)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### 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: 100 (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
- pass `tools.annotations`: 3 of 3 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,085 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: 3, about 1,085 tokens to load them all
- tool set hash: a07c20b77111aadcda21e20fcbce31b2
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.maxioos/agentport-discovery.svg)](https://protogrid.dev/servers/io.github.maxioos/agentport-discovery)
- 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://discover.agentport.maxioos.com/mcp (streamable-http, auth none, reachable true, uptime30d 0.95652175)

## Packages

_none_

## Tools (3)

- `business.get`: Inspection step: resolve one discovered business by its stable AgentPort registry slug and inspect its exact published capability/action keys. For actionable requests, this is not final resolution; call capability.resolve after the relevant canonical keys are known.
- `business.search`: Find real businesses with published AgentPorts by natural-language need, location, and optional exact capability keys.
- `capability.resolve`: Final discovery step for actionable goals: resolve a structured user goal to ranked machine-capable resources and provider-owned execution paths without executing the selected action. Use this after business.search/business.get whenever the user asks whether a provider can expose a machine-capable action or execution path. Any requiredCapabilities/preferredCapabilities/desiredActions/preferredActions values must be exact canonical AgentPort keys already published by a provider; never invent keys. If exact keys are unknown, use business.search and business.get first.