💰 FUNDING NEWS: Hushh.ai Secures $5 Million Strategic Investment from hushhTech.com's Evergreen Renaissance AI Fund
💰 FUNDING NEWS: Hushh.ai Secures $5 Million Strategic Investment from hushhTech.com's Evergreen Renaissance AI Fund
💰 FUNDING NEWS: Hushh.ai Secures $5 Million Strategic Investment from hushhTech.com's Evergreen Renaissance AI Fund
Hushh Plaid Financial Profile Update Agent
Update Plaid-linked financial profiles in Supabase with natural language.
This page operationalizes the update agent flow: capture a user instruction, extract fields to change, and call MCP to persist updates across Supabase and downstream CRM, analytics, and personalization systems.
Use case
Corrections + field-level updates
Transport
JSON-RPC 2.0 via MuleSoft
Data store
Supabase via MCP update_user
Overview
An AI-powered automation layer that corrects or updates Plaid-sourced financial data in Supabase using natural language. It keeps CRM, analytics, and personalization modules aligned with the latest user state.
Account + contact fixes
Balances, investments, liabilities
Timestamped confirmations
Integration Flow
1) MuleSoft crafts JSON-RPC from user/back-end instruction.
2) Agent parses fields to change and targets.
3) MCP update_user applies changes in Supabase.
4) Structured confirmation returns to Hushh UI.
Functional Workflow
Step 1
User input
Natural language asks for a correction or data change (balances, names, investments, etc).
Step 2
Agent invocation
MuleSoft sends JSON-RPC 2.0 POST to the Plaid Update Agent endpoint.
Step 3
Intent extraction
LLM identifies user/account IDs, fields to update, and target values.
Step 4
MCP + Supabase
MCP executes update_user to apply changes in Supabase.
Step 5
Confirmation
Agent returns a structured success payload with timestamps.
Quick testing presets
Load doc-based samples to instantly test the update flow.
Update Request Builder
Mirror the MuleSoft JSON-RPC call to the agent. Combine a natural language instruction with structured fields so the agent can route precise updates through MCP.
Session ID
Task ID
User prompt
Update payload (optional JSON context)
Request preview
Add or load an update payload to preview the request.Direct MCP call (update_user)
Validate how MCP ingests structured update arguments when bypassing the agent layer. Use the same request object your MuleSoft flow would POST.
tools/call payload
Response console
Responses from the Update Agent and MCP are captured here for quick debugging and demo purposes.
No calls yet. Trigger a request to see responses.
Error handling
400
Invalid JSON-RPC format
Ensure request structure matches schema.
401
Unauthorized
Validate MuleSoft or API credentials.
404
User not found
Confirm user_id and account_id exist in Supabase.
500
Internal Agent Error
Retry or contact support.
TIMEOUT
MCP server delay
Increase timeout or retry the request.
Sundhar Pichai use case
Example update: "Please update Sundhar Pichai’s bank balance to 12000 USD having their UserId xxxx and account id xxxxx."
{
"jsonrpc": "2.0",
"id": "task200",
"method": "tasks/send",
"params": {
"sessionId": "sessionSP001",
"message": {
"role": "user",
"parts": [
{
"type": "text",
"text": "Please update Sundhar Pichai’s bank balance to 12000 USD having their UserId xxxx and account id xxxxx."
}
]
}
}
}Security & privacy
• HTTPS enforced for agent and MCP endpoints.
• Only authorized MuleSoft flows can trigger updates.
• Supabase credentials stay inside the MCP environment.
• No sensitive data exposed beyond intended updates.
Versioning
v1.0.0 — Initial Hushh Plaid Financial Profile Update Agent release.