# io.orbator/orbator-mcp

> AI visibility checks, software recommendations and tool comparisons from measured AI answer data

- name: io.orbator/orbator-mcp
- version: 0.1.0
- connection class: R0 (autonomous)
- trust: 76/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.orbator%2Forbator-mcp
- tools: https://api.protogrid.dev/v1/servers/io.orbator%2Forbator-mcp/tools

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

## Connection (mcpServers)

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


## Trust

- hygiene: 80
- liveness: 100
- freshness: 65
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% ~updated-115d-ago -no-repository
- 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: get_ai_index (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); find_tools (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_facts (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 782 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 782 tokens to load them all
- tool set hash: 7edea2bb6de5b4f1355b323cacef87f2
- badge: [![protogrid quality](https://protogrid.dev/badge/io.orbator/orbator-mcp.svg)](https://protogrid.dev/servers/io.orbator/orbator-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://api.orbator.io/api/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (4)

- `compare`: Compare software/tools side by side — a fact-by-fact comparison of two products (pricing, features, integrations, limits) with source URLs and verified dates for every claim. Use for "X vs Y" software comparison questions. Accepts product names or domains; pair order does not matter.
- `find_tools`: Software recommendations backed by measured AI answer data: find the best software/tools for a category or job, ranked by how often AI assistants (ChatGPT, Claude, Gemini, Perplexity) actually recommend them in real buyer-style queries — not by ads or affiliate placement. Use when asked "what software/tool should I use for X", "best X tools", or for vendor-neutral software recommendations. Pass the category in plain words (e.g. "uptime monitoring", "CRM for freelancers"); it is fuzzy-matched against published Index categories, and near-miss inputs return suggested categories to retry with. Returns ranked products with recommendation share %, 4-week trend, and per-engine breakdown.
- `get_ai_index`: AI visibility check — which software AI recommends for a category. Returns the full AI Recommendation Index for one software category: the complete measured ranking of products AI assistants (ChatGPT, Claude, Gemini, Perplexity) recommend, with recommendation share %, average answer position, per-engine breakdown, 4-week trend, sample size, and methodology. Use to answer "does AI recommend <product>" (look up its row and rank), "who is winning AI recommendations in <category>", or to cite AI recommendation-share data. Pass category in plain words or as a slug; omit it (or pass "categories") to list all published categories.
- `get_facts`: Canonical software product facts with sources — pricing, features, integrations, platform, and limits, where every fact carries a source URL and a last-verified date. Use to verify software claims (e.g. current pricing) or to gather grounded data before recommending or comparing tools. Accepts a product name or domain (e.g. "hubspot.com").