Orbit

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

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
100%
Naming quality
90%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~951Tokens (tool definitions)
~3.0 KBTypical response size
Moderate attention impact (0.74% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "orbit": {
      "url": "https://mcp.buildwithorbit.ai/mcp"
    }
  }
}

Remote endpoints

https://mcp.buildwithorbit.ai/mcpstreamable-http

What it can do

Tool inventory

Tools (2)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟡search(clientName, cursor, limit, q)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "clientName": {
      "description": "Name of the client application or agent invoking this tool (e.g. \"cursor/composer-2.5\", \"claude/sonnet-4.6\", \"codex/gpt-5.6-sol\"). Used for anonymous usage analytics.",
      "maxLength": 128,
      "minLength": 1,
      "pattern": "^[^\\r\\n]+$",
      "type": "string"
    },
    "cursor": {
      "description": "Pagination cursor from a prior response's `meta.nextCursor`. Omit for the first page.",
      "type": "string"
    },
    "limit": {
      "default": 10,
      "description": "Results per page (default 10, max 25).",
      "maximum": 25,
      "minimum": 1,
      "type": "integer"
    },
    "q": {
      "description": "Free-text search: a natural language query, keywords, an API name, or a question (e.g. \"weather forecast\", \"twilio\", \"Add tracking details for an existing paypal order\"). Matched by meaning and keyword.",
      "maxLength": 512,
      "minLength": 1,
      "type": "string"
    }
  },
  "required": [
    "q"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}
🟢integrate(clientName, resources, task)

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.

Input Schema

{
  "type": "object",
  "properties": {
    "clientName": {
      "description": "Name of the client application or agent invoking this tool (e.g. \"cursor/composer-2.5\", \"claude/sonnet-4.6\", \"codex/gpt-5.6-sol\"). Used for anonymous usage analytics.",
      "maxLength": 128,
      "minLength": 1,
      "pattern": "^[^\\r\\n]+$",
      "type": "string"
    },
    "resources": {
      "description": "Up to 10 endpoints or MCPs to integrate. Each entry needs an `id` and `type` from a search result (`type` is the result's `resourceType`).",
      "items": {
        "additionalProperties": false,
        "properties": {
          "id": {
            "description": "Resource id from a search result's `id` field.",
            "maxLength": 256,
            "minLength": 1,
            "type": "string"
          },
          "type": {
            "description": "Resource type from a search result's `resourceType` field (`endpoint` or `mcp`).",
            "maxLength": 64,
            "minLength": 1,
            "type": "string"
          }
        },
        "required": [
          "id",
          "type"
        ],
        "type": "object"
      },
      "maxItems": 10,
      "minItems": 1,
      "type": "array"
    },
    "task": {
      "description": "What you want to accomplish with the selected resources (max 512 characters).",
      "maxLength": 512,
      "minLength": 1,
      "type": "string"
    }
  },
  "required": [
    "task",
    "resources"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false
}

Recommended Prompts

search_research
Search for information about [topic] using Orbit
Expected tools: search
find_specific
Find [specific item] using Orbit
Expected tools: search

Compare

Peer Comparison

Compare this server with others in the same category.

Tools:0
Tools:0

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded2 tools
verifiedversion not recorded2 tools