MCP endpoint (JSON-RPC 2.0)
curl --request POST \
--url https://{host}/v2/workspaces/slug:ai-collection-v3/webhooks/ai-collection/mcp \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"jsonrpc": "2.0",
"method": "tools/call"
}
'const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({jsonrpc: '2.0', method: 'tools/call'})
};
fetch('https://{host}/v2/workspaces/slug:ai-collection-v3/webhooks/ai-collection/mcp', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));import requests
url = "https://{host}/v2/workspaces/slug:ai-collection-v3/webhooks/ai-collection/mcp"
payload = {
"jsonrpc": "2.0",
"method": "tools/call"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text){
"jsonrpc": "2.0",
"id": "<string>",
"result": {},
"error": {
"code": 123,
"message": "<string>"
}
}MCP
MCP endpoint (JSON-RPC 2.0)
Model Context Protocol endpoint for AI agents and MCP clients.
Implements initialize, tools/list, and tools/call over
JSON-RPC 2.0.
Available tools: data_discover (schema + sample rows, call first),
data_create_collection, data_insert, data_query, data_get,
data_update, data_upsert, data_delete, data_count,
data_distinct, data_aggregate, suggest_schema.
Tool arguments mirror the REST payloads documented above.
A per-collection scoped endpoint is also available at
/v1/collections/{collection_id}/mcp: it binds an agent to a single
collection (no collection_id argument needed on each call).
Rate limit: 100 requests/min per user.
POST
/
ai-collection
/
mcp
MCP endpoint (JSON-RPC 2.0)
curl --request POST \
--url https://{host}/v2/workspaces/slug:ai-collection-v3/webhooks/ai-collection/mcp \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"jsonrpc": "2.0",
"method": "tools/call"
}
'const options = {
method: 'POST',
headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
body: JSON.stringify({jsonrpc: '2.0', method: 'tools/call'})
};
fetch('https://{host}/v2/workspaces/slug:ai-collection-v3/webhooks/ai-collection/mcp', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));import requests
url = "https://{host}/v2/workspaces/slug:ai-collection-v3/webhooks/ai-collection/mcp"
payload = {
"jsonrpc": "2.0",
"method": "tools/call"
}
headers = {
"Authorization": "Bearer <token>",
"Content-Type": "application/json"
}
response = requests.post(url, json=payload, headers=headers)
print(response.text){
"jsonrpc": "2.0",
"id": "<string>",
"result": {},
"error": {
"code": 123,
"message": "<string>"
}
}Authorizations
BearerAuthOrgApiKeyAuth
User session JWT. Send as Authorization: Bearer <token>.
Body
application/json
Was this page helpful?