Smoke-test Bedrock embeddings (internal)

Add MCP server to your AI tool

Allow AI tools and LLMs to interact with the API documentation portal through MCP.

MCP server URL


        
          
            https://docs.usehearsay.com/mcp

Standard setup for AI tools providing an mcp.json file

{
  "integrations MCP server": {
    "url": "https://docs.usehearsay.com/mcp"
  }
}

POST /ai/admin/ping/embedding

Access token

Embeds a fixed test string through Bedrock and reports the model, latency and, in sample, the vector size and its first three values. A Bedrock failure still answers 200, with ok: false, model: unknown and the error class and message. Super admins only.

Responses

200 application/json
Hide response attributes Show response attributes object
- data object Required
  
  Hide data attributes Show data attributes object
  
  ok boolean
  
  purpose string
  
  model string
  
  unknown when the call failed
  
  latencyMs number
  
  sample string
  
  Present when ok is true.
  
  errorClass string
  
  Present when ok is false.
  
  errorMessage string
  
  Present when ok is false.
- statusCode number Required
- timestamp string(date-time) Required

POST /ai/admin/ping/embedding

curl \
 --request POST 'http://api.example.com/ai/admin/ping/embedding' \
 --header "Authorization: Bearer $ACCESS_TOKEN"

Response examples (200)

{
  "data": {
    "ok": true,
    "purpose": "admin_ping",
    "model": "string",
    "latencyMs": 412,
    "sample": "string",
    "errorClass": "string",
    "errorMessage": "string"
  },
  "statusCode": 200,
  "timestamp": "2026-01-15T10:15:00.000Z"
}