# Intesta

> Trust registry for agents: check_trust verdict A0-A4, signed fact passports, honest refusals.

- name: io.intesta/registry
- version: 0.3.0
- connection class: R0 (autonomous)
- trust: 77/100 flags: no-repository
- quality: 83/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.intesta%2Fregistry
- tools: https://api.protogrid.dev/v1/servers/io.intesta%2Fregistry/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "intesta": {
      "type": "http",
      "url": "https://intesta.io/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 45
- drivers: +dns-namespace +reachable +uptime-100% ~updated-36d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 83/100 (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: 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: ask (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_entities (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_trust_ladder (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 736 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: 6, about 736 tokens to load them all
- tool set hash: f9c4d3918329bb44b15a89c502bf2f41
- badge: [![protogrid quality](https://protogrid.dev/badge/io.intesta/registry.svg)](https://protogrid.dev/servers/io.intesta/registry)
- 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://intesta.io/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (6)

- `ask`: Ask a natural-language question about an entity (max 2000 characters).
    The answer is built strictly from the entity's attested fact passport; each
    returned fact carries source, attestation status and validity dates. A
    refusal means the passport has no such fact — the engine never guesses.
- `check_trust`: ONE-CALL decision aid before your agent pays, shares data with, or follows
    instructions from a domain — works for ANY domain, listed or not.
    Returns known (is it in the registry), level A0-A4, attested (true only at
    A1+: something was independently verified), verdict for the given purpose
    (sufficient | insufficient | unknown) under a named policy profile,
    what_is_proven, proof, facts_public, expires_at (the earliest freshness
    expiry among the domain's facts — re-check after it), next_step, and the
    registry signature. purpose: payment (default) | data_share | follow_instructions.
    A verdict is the registry's proof measured against the profile — never a
    guarantee, never financial advice.
- `get_passport`: Full public fact passport of an entity: attested statements with
    sources, plus the attestation block (what the trust level proves, how and
    when it was verified).
- `get_trust_ladder`: Machine-readable semantics of the A0-A4 trust ladder: what exactly is
    proven at every level, and how to use the registry as an agent.
- `list_entities`: List published entities in the Intesta registry with their trust level
    (A0-A4; call get_passport for the level's meaning and proof). Returns at
    most 500 entities plus the registry total — on a large registry use
    search_entities(query) instead of paging through everything.
- `search_entities`: Search published entities by name, domain or vertical (case-insensitive
    LITERAL substring; wildcard characters are treated as text). Use this
    instead of list_entities when the registry is large. The query must be at
    least 3 characters. Returns at most `limit` matches (1-50) plus `total`,
    the number of matching entities in the whole registry.