# AILegal — verified legal provisions for agents

> Legal answers from official sources; refuses when no norm is verified.

- name: io.github.mrpkk/ailegal-mcp
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 96/100
- quality: 79/100 (new)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.mrpkk%2Failegal-mcp
- tools: https://api.protogrid.dev/v1/servers/io.github.mrpkk%2Failegal-mcp/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "ailegal-mcp": {
      "type": "http",
      "url": "https://ailegal.legal/api/mcp/"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 95
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-88% +updated-2d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (new)

### 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: 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: oracle_lookup (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); verify_citation (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); legal_breakdown (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 318 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

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

- n/a `stability.changes`, `stability.rug_pull`: tool history recorded for 1 of the 7 days needed

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

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

- tools: 3, about 318 tokens to load them all
- tool set hash: c3899743a337b4de4b792645654d35e6
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.mrpkk/ailegal-mcp.svg)](https://protogrid.dev/servers/io.github.mrpkk/ailegal-mcp)
- 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://ailegal.legal/api/mcp/ (streamable-http, auth none, reachable true, uptime30d 0.875)

## Packages

_none_

## Tools (3)

- `legal_breakdown`: Describe a legal situation; get the verified provisions that apply with official-source links. jurisdiction: ru|in|us|uk|ca|hk. Returns a refusal when the corpus has no norm.
- `oracle_lookup`: Legal Oracle: which verified provisions relate to a query. Optional jurisdiction filter. An empty list means the corpus has no norm for this query.
- `verify_citation`: Legal Oracle: does this citation exist in the verified corpus? Use before relying on any code/article pair. found=false means do not rely on it.