Skip to main content
The Orthogonal MCP server provides four tools that AI assistants can use to discover and call APIs. Find APIs by describing what you need in natural language. Parameters:
NameTypeRequiredDescription
promptstringYesWhat you’re looking for (e.g., “enrich lead”, “web scraping”, “AI search”)
limitnumberNoMax results (default: 10, max: 50)
Example prompt: “Find APIs to enrich leads and get contact info” Response: 
{
  "success": true,
  "results": [
    {
      "id": "api-uuid",
      "name": "Apollo.io",
      "slug": "apollo",
      "baseUrl": "https://api.apollo.io",
      "endpoints": [
        {
          "id": "endpoint-uuid",
          "path": "/v1/people/match",
          "method": "POST",
          "description": "Enrich a person by email, name, or LinkedIn URL",
          "price": "0.03",
          "isPayable": true,
          "score": 0.95
        },
        {
          "path": "/v1/organizations/enrich",
          "description": "Enrich a company by domain",
          "price": "0.03"
        }
      ]
    }
  ],
  "count": 2,
  "apisCount": 1
}

​
get_details

Get full parameter information for a specific endpoint. Parameters:
NameTypeRequiredDescription
apistringYesAPI slug from search results (e.g., “apollo”, “linkup”, “olostep”)
pathstringYesEndpoint path (e.g., “/v1/people/match”)
Example prompt: “Show me the parameters for Apollo person enrichment” Response: 
{
  "success": true,
  "api": {
    "name": "Apollo.io",
    "slug": "apollo",
    "description": "B2B lead enrichment and contact database"
  },
  "endpoint": {
    "path": "/v1/people/match",
    "method": "POST",
    "description": "Enrich a person by email, name, or LinkedIn URL",
    "price": "$0.03",
    "isPayable": true,
    "bodyParams": [
      {
        "name": "email",
        "type": "string",
        "required": false,
        "description": "Email address to enrich"
      }
    ]
  }
}

​
integrate

Get ready-to-use code snippets for calling an endpoint. Parameters:
NameTypeRequiredDescription
apistringYesAPI slug
pathstringYesEndpoint path
formatstringNoCode format: orth-sdk, run-api, curl, x402-fetch, x402-python, all
Example prompt: “Give me curl code to scrape a webpage with Olostep” Response: 
{
  "success": true,
  "api": {
    "name": "Olostep",
    "slug": "olostep"
  },
  "endpoint": {
    "path": "/v1/scrapes",
    "method": "POST",
    "price": "$0.005"
  },
  "format": "curl",
  "snippets": {
    "curl": "curl -X POST 'https://api.orth.sh/v1/run' \\\n  -H 'Authorization: Bearer $ORTHOGONAL_API_KEY' \\\n  -H 'Content-Type: application/json' \\\n  -d '{\"api\": \"olostep\", \"path\": \"/v1/scrapes\", \"body\": {\"url_to_scrape\": \"https://example.com\"}}'"
  }
}

​
use

Execute an API call and return the results. Parameters:
NameTypeRequiredDescription
apistringYesAPI slug
pathstringYesEndpoint path
bodyobjectNoRequest body parameters
queryobjectNoQuery string parameters
Example prompt: “Use LinkUp to search for recent fintech funding news” Response: 
{
  "success": true,
  "price": "0.004",
  "priceCents": 400,
  "data": {
    "results": [
      {
        "title": "Stripe raises $6.5B at $50B valuation",
        "url": "https://...",
        "content": "..."
      }
    ]
  },
  "requestId": "run_1234567890_abc123",
  "paymentMethod": "credits"
}

​
Multi-API Workflow

AI agents can chain multiple APIs for complete workflows: 
User: Research Stripe and find contact info for their leadership team

Agent:
1. *search* "AI web search company research" → finds LinkUp
2. *use* linkup /v1/search → gets company info and news
3. *search* "lead enrichment email" → finds Apollo, Hunter
4. *use* apollo /v1/people/match → enriches CEO by email
5. *use* hunter /domain-search → finds more contacts at stripe.com

Result: Complete company research + contacts
The AI handles this flow automatically based on your request.