Getting Started
Quickstart
Make your first API call in under a minute
Quickstart
1. Find a restaurant
curl -X POST https://api.seemor.ai/api/mcp \
-H "Authorization: Bearer sk_seemor_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "find_restaurant",
"arguments": {
"name": "Barrafina",
"city": "London"
}
}
}'The response body contains a result object. The tool output is in result.content[0].text as a JSON string:
{
"status": "ok",
"results": [
{
"seemor_id": "a1b2c3d4-...",
"name": "Barrafina Dean Street",
"address": "26-27 Dean St, London W1D 3LL",
"coordinates": { "lat": 51.5138, "lng": -0.1318 },
"city": "London",
"neighborhood": "Soho",
"cuisine_tags": ["spanish", "tapas"],
"grade": "A",
"coverage_level": "full"
}
],
"total_matches": 3
}2. Look up full details
Use the seemor_id from the previous response:
curl -X POST https://api.seemor.ai/api/mcp \
-H "Authorization: Bearer sk_seemor_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "lookup_restaurant",
"arguments": {
"restaurant_id": "a1b2c3d4-..."
}
}
}'This returns basic fields (grade, TL;DR, cuisine, price level). For richer data, set "fields": "standard" or "fields": "premium" (requires a paid key).
Understanding the response envelope
Every MCP response follows this structure:
{
"jsonrpc": "2.0",
"id": 1,
"result": {
"content": [
{
"type": "text",
"text": "{ ... JSON string with tool output ... }"
}
]
}
}Parse result.content[0].text as JSON to get the tool's response object.
Next steps
- Browse the Tool Reference for complete parameter and response documentation
- Set up MCP integration with Claude Desktop or other clients