# Chiwawa — AI Agent Registry

> Search and discover AI agents across A2A and MCP protocols. 2,000+ agents with health tracking.

- name: io.github.manuelrmz123/chiwawa
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 91/100
- quality: 70/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.manuelrmz123%2Fchiwawa
- tools: https://api.protogrid.dev/v1/servers/io.github.manuelrmz123%2Fchiwawa/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "chiwawa": {
      "type": "sse",
      "url": "https://chiwawa.vercel.app/mcp/sse"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 100
- freshness: 85
- provenance: 80
- drivers: +repository +namespace-matches-repo +reachable +uptime-100% ~updated-71d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 70/100 (needs work)

### protocol: 50 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-03-26; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- warn `protocol.transport`: only the legacy HTTP+SSE transport, deprecated until 2027-07-28
- 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: search_agents (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_stats (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); submit_domain (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 335 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: 4, about 335 tokens to load them all
- tool set hash: e187973296eec2fddea72120fefa6353
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.manuelrmz123/chiwawa.svg)](https://protogrid.dev/servers/io.github.manuelrmz123/chiwawa)
- 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://chiwawa.vercel.app/mcp/sse (sse, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (4)

- `get_agent`: Get full details for a specific agent by UUID: provider, version, skills, auth schemes, and last 5 crawl results.
- `get_stats`: Returns aggregate statistics for the Chiwawa AI agent registry: total agents indexed, breakdown by type (A2A, MCP Live, MCP Package), and breakdown by health status (active, degraded, unresponsive, etc.).
- `search_agents`: Search for AI agents in the Chiwawa registry. Supports full-text search, type filter, and status filter.
- `submit_domain`: Submit a domain to the Chiwawa crawler queue. The crawler will look for an A2A agent card at /.well-known/agent.json.