# Orbit

> Turn any task into the right API calls: discover, evaluate, and integrate public APIs.

- name: ai.buildwithorbit/orbit
- version: 1.0.0
- connection class: R0 (autonomous)
- trust: 80/100 flags: no-repository
- quality: 85/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.buildwithorbit%2Forbit
- tools: https://api.protogrid.dev/v1/servers/ai.buildwithorbit%2Forbit/tools

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

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "orbit": {
      "type": "http",
      "url": "https://mcp.buildwithorbit.ai/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 100
- freshness: 85
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-100% ~updated-55d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 85/100 (good)

### protocol: 100 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- pass `protocol.list_ttl`: tool list is cacheable (ttlMs 30000)

### 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: 64 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- 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 (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); integrate (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 956 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: 2, about 956 tokens to load them all
- tool set hash: c07725e9bd1d64aa555b930d906218c2
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.buildwithorbit/orbit.svg)](https://protogrid.dev/servers/ai.buildwithorbit/orbit)
- 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://mcp.buildwithorbit.ai/mcp (streamable-http, auth none, reachable true, uptime30d 1)

## Packages

_none_

## Tools (2)

- `integrate`: Get integration details for public endpoints and MCPs from `search` results. Provide a `task` describing what you want to accomplish and up to 10 `resources` — each with an `id` and `type` taken from the matching search result's `resourceType`. Returns a task brief covering authentication, base URLs, request steps, parameters, expected responses, dependencies between steps, and other important considerations.
- `search`: Find and evaluate public API endpoints and MCPs that match your query. Set `q` to a natural language query, keywords, an API name, or a question — results are matched by meaning and keyword; each result includes `id`, `resourceType` (`endpoint` or `mcp`), `name`, `description`, `method` (for an `endpoint`) or `transport` (for an `mcp`), `url`, and `evaluateGuide` — an evaluation of what the endpoint or MCP does, when to use it, and its limitations. Review `evaluateGuide` to pick the best fit, then pass each chosen result's `id` and `resourceType` (as `type`) to `integrate`. Paginate with `cursor` from `meta.nextCursor` (`limit` defaults to 10, max 25; pagination stops at 40 results total). No authentication required.

Best practices for querying:
- Use focused keyword queries that include the product or provider name along with the endpoint details, for example "PayPal create invoice".
- Alternatively, use natural language queries such as "PayPal API to create an invoice".
- Avoid jumbled queries that cram many unrelated keywords into a single query, for example "paypal invoice payment delivery payments ordering".
- Avoid OR-separated queries such as "paypal invoice OR paypal create invoice OR paypal OR invoice creation".
- If you need to explore multiple intents, try each as a separate call.