Orbit

Official2 tools

by buildwithorbit

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

MCP Server: ai.buildwithorbit/orbit

The Model Context Protocol (MCP) server ai.buildwithorbit/orbit provides a way to “turn any task into the right API calls” by supporting discovery, evaluation, and integration of public APIs. It is represented with 2 tools available in the server.

🛠️ Key Features

Converts tasks into appropriate API call workflows
Discovers public APIs
Evaluates APIs before integration
Integrates selected public APIs
Tool availability: 2

🚀 Use Cases

Finding relevant public APIs for a given task
Comparing candidate APIs and selecting a suitable option
Integrating a chosen public API into an end-to-end workflow

⚡ Developer Benefits

Structured flow aligned to discovery → evaluation → integration
Small tool set (2 tools) for implementing API-call orchestration

⚠️ Limitations

Only described as handling public APIs; scope beyond public APIs is not specified

Captured live from the server via tools/list.

search

Find and evaluate public API endpoints 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`, `name`, `description`, `method`, `url`, and `evaluateGuide` — an evaluation of what the endpoint 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.

Parameters3

cursor	string	optional	Pagination cursor from a prior response's `meta.nextCursor`. Omit for the first page.
limit	integer	optional	Results per page (default 10, max 25).
q	string	required	Free-text search: a natural language query, keywords, an API name, or a question (e.g. "weather forecast", "twilio", "Add tracking details for an existing paypal order"). Matched by meaning and keyword.

Raw schema

{
  "type": "object",
  "properties": {
    "cursor": {
      "description": "Pagination cursor from a prior response's `meta.nextCursor`. Omit for the first page.",
      "type": "string"
    },
    "limit": {
      "default": 10,
      "description": "Results per page (default 10, max 25).",
      "maximum": 25,
      "minimum": 1,
      "type": "integer"
    },
    "q": {
      "description": "Free-text search: a natural language query, keywords, an API name, or a question (e.g. \"weather forecast\", \"twilio\", \"Add tracking details for an existing paypal order\"). Matched by meaning and keyword.",
      "maxLength": 512,
      "minLength": 1,
      "type": "string"
    }
  },
  "required": [
    "q"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}

integrate

Get integration details for public endpoints 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.

Parameters2

resources	array	required	Up to 10 endpoints to integrate. Each entry needs an `id` and `type` from a search result (`type` is the result's `resourceType`).
task	string	required	What you want to accomplish with the selected endpoints (max 512 characters).

Raw schema

{
  "type": "object",
  "properties": {
    "resources": {
      "description": "Up to 10 endpoints to integrate. Each entry needs an `id` and `type` from a search result (`type` is the result's `resourceType`).",
      "items": {
        "additionalProperties": false,
        "properties": {
          "id": {
            "description": "Endpoint id from a search result's `id` field.",
            "maxLength": 256,
            "minLength": 1,
            "type": "string"
          },
          "type": {
            "description": "Resource type from a search result's `resourceType` field.",
            "maxLength": 64,
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "id",
          "type"
        ],
        "type": "object"
      },
      "maxItems": 10,
      "minItems": 1,
      "type": "array"
    },
    "task": {
      "description": "What you want to accomplish with the selected endpoints (max 512 characters).",
      "maxLength": 512,
      "minLength": 1,
      "type": "string"
    }
  },
  "required": [
    "task",
    "resources"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}

Install

Tools (2)

searchintegrate

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://mcp.buildwithorbit.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "orbit": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.buildwithorbit.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.