Payment Reconciliation & Matching

Payment Reconciliation & Matching

Match receipts, bank lines and GST 2B rows to open invoices and the ledger. Proposes one-to-many and many-to-one matches with confidence and reasons, flags deductions (TDS, bank charges, part payments), and returns an exceptions queue plus updated matching rules. Low-confidence matches always go to a person; nothing is auto-posted. We never connect to banks or the GST portal.

Registry name	ai.saifs/payment-reconciliation
Endpoint	https://payment-reconciliation-mcp-microsoft.saifs.ai/mcp
Transport	Streamable HTTP (remote, nothing to install)
Auth	OAuth 2.1 — PKCE (S256) and dynamic client registration; your client opens a sign-in page on first use
Publisher	SAIFS AI

Install

VS Code / GitHub Copilot

Add to .vscode/mcp.json (workspace) or your user mcp.json:

{
  "servers": {
    "saifs-payment-reconciliation": {
      "type": "http",
      "url": "https://payment-reconciliation-mcp-microsoft.saifs.ai/mcp"
    }
  }
}

Then start the server from the MCP view and sign in when prompted.

Claude (claude.ai, Desktop)

Settings → Connectors → Add custom connector, and paste:

https://payment-reconciliation-mcp-microsoft.saifs.ai/mcp

Claude Code

claude mcp add --transport http saifs-payment-reconciliation https://payment-reconciliation-mcp-microsoft.saifs.ai/mcp

Any other MCP client

Point it at https://payment-reconciliation-mcp-microsoft.saifs.ai/mcp using the Streamable HTTP transport. The server returns 401 with a WWW-Authenticate: Bearer … resource_metadata=… challenge, so OAuth-aware clients sign in automatically.

Tools

Tool	What it does
explain_match	Why these items match — amount combination, name score, date gap and reference.
gst_2b_match	India GSTR-2B vs purchase register: matched, mismatched, missing, and ITC at risk.
match_bank_to_ledger	Bank reconciliation with one-to-many and many-to-one matches.
match_receipts	Cash application including combinations, part payments and deductions.
reconciliation_report	Matched %, unmatched value, ageing of exceptions and ITC at risk.
suggest_rules	New matching rules learned from confirmed matches, returned in rules_snapshot.

Example prompts

• “Match today’s receipts to open invoices”
• “Reconcile the bank statement”
• “Run GSTR-2B vs purchase register”

Support

• Website: https://saifs.ai
• Issues: https://github.com/Saify-Technologies/saifs-ai-mcps-docs/issues
• Privacy: https://saifs.ai/privacy_policy