MCP for Transaction Monitoring: Real-Time Fraud Rules via AI Agents

Transaction Monitoring is a control that never sleeps. Every payment, transfer, and top-up has to be evaluated against your rules in real time, the flags have to be triaged, the genuine risks have to become cases, and some of those cases have to become a Suspicious Activity Report (SAR). It is high-volume, procedural, and evidence-driven work — the kind that an AI agent can move through quickly when it has a dependable set of tools to call. The Didit Model Context Protocol (MCP) server exposes the operational side of Transaction Monitoring — ingest, search, triage, wallet screening, and the case lifecycle — as tools an agent can invoke in plain language, from submitting a transaction to closing out a remediation loop.

This post walks the full arc: connect a client, submit transactions for real-time evaluation, triage what gets flagged, open and work cases, assemble the evidence behind a filing, and run the AWAITING_USER auto-remediation loop. Rule-bundle setup and the SAR filing itself stay in the Business Console — the agent covers everything in between.

Key takeaways

• Didit's MCP server puts Transaction Monitoring — part of its 115 tools across 11 categories — behind natural-language commands, so an agent can submit transactions, triage flags, screen wallets, and work cases in one conversation.
• Transaction Monitoring runs a real-time rule engine with 11 seeded rule bundles across fiat and crypto, at $0.02 per transaction.
• Case management and the SAR workflow are built in, so a flagged transaction can travel from alert to filed report without leaving the platform.
• The AWAITING_USER state drives an auto-remediation loop: when a transaction needs more information from the customer, the system pauses, collects it, and resumes — and an agent can orchestrate that end to end.
• Authentication is OAuth 2.1 with Proof Key for Code Exchange (PKCE) — "Log in with Didit," no Application Programming Interface (API) key for the hosted server, scoped to your console role.
• You get 500 free checks per month, sub-2-second responses, and the MCP layer itself is free — you pay $0.02 per transaction only for what you monitor.

Why Transaction Monitoring suits an agent

Monitoring work is a sequence of well-defined decisions. Did this transaction break a rule? Is the flag a real concern or expected behavior? Does it warrant a case? Does the case warrant a SAR? Each step reads structured evidence and produces a documented outcome — the shape of task an AI agent handles reliably when the underlying platform does the detection. The agent is not inventing risk logic; it is orchestrating a real-time rule engine, reading its output, and carrying each item to its correct next state, with a human approving the consequential moves.

Didit's Transaction Monitoring module provides that engine: real-time evaluation, 11 seeded rule bundles covering common fiat and crypto typologies, velocity aggregations, case management, and a SAR workflow. Over MCP, all of it becomes callable in a sentence.

Connecting your agent to the MCP server

The server lives at https://mcp.didit.me/mcp over Streamable HTTP — hosted, or self-hosted from the open-source repository under the MIT license. Authentication is OAuth 2.1 with PKCE: a "Log in with Didit" prompt on first connect, no API key to paste for the hosted endpoint, and the agent inherits your console role through the didit:management and didit:verification scopes. It can only act where your account already can.

Add it to Claude Code in one line, then verify with /mcp:

claude mcp add --transport http didit https://mcp.didit.me/mcp

Claude Desktop, Cursor, VS Code, Windsurf, and Zed connect through a short JSON config pointing at the same URL. ChatGPT Developer Mode can attach through OpenAI's beta MCP support, which is still early, so treat it as experimental. Full setup details are in the MCP overview docs.

Setting up your rules, then handing the queue to the agent

You do not start from a blank rule set. Didit ships 11 seeded rule bundles across fiat and crypto, and you install and tune them in the Business Console — choosing the bundle that matches your risk profile, adjusting velocity thresholds, narrowing jurisdiction lists, and backtesting against your history before anything runs live.

That configuration step is deliberately a human, console-side decision: a bundle that would have flagged a third of last month's legitimate volume needs tuning before it touches production, and that is a risk-appetite call, not an automation target.

Once the rules are live, everything downstream is where the agent earns its keep. Submit traffic for evaluation and read the decision back in plain language:

"Submit this transaction for monitoring and tell me the risk decision and which rule fired."

The agent calls the monitoring tools, returns the decision and the rule that produced it, and you keep working in the same conversation.

Triaging flags and opening cases

Once the bundle is live at $0.02 per transaction, flags arrive in real time. Triage is the daily grind, and it is where an agent earns its place. Ask it to summarize the queue:

"Show me today's flagged transactions grouped by rule, and tell me which look like genuine risk versus expected customer behavior."

The agent reads each flag with its context — amount, counterparty, velocity pattern, the rule that fired — and sorts them into likely-genuine and likely-benign, explaining its reasoning for the ones that matter. For the transactions that warrant a closer look, it opens cases:

"Open a case for the three structuring-pattern flags on account 4471 and attach the triggering transactions."

Case management holds the evidence, the timeline, and the analyst notes in one place, so the record of the investigation builds itself as the agent works.

From case to filed report

When a case crosses the threshold from suspicious to reportable, the SAR (Suspicious Activity Report) workflow takes over in the console. The agent's job is everything that leads up to it: it has been reading the transactions, holding the case record, and adding the evidence, so it can assemble the narrative you file from.

"Escalate the structuring case on account 4471 and summarize the pattern, the transactions involved, and the timeline."

The agent escalates the case and assembles the summary from the case record — what was observed, which transactions, over what period, why it meets the suspicious-activity bar. A human reviews and files the SAR itself in the console. The agent removes the blank-page problem and makes sure nothing in the case evidence is left out; because the summary is built from the same case the agent has been managing, it stays consistent with the underlying record rather than becoming a separate retelling.

Running the AWAITING_USER remediation loop

Not every flag is fraud — sometimes a transaction just needs more information from the customer before it can clear. That is what the AWAITING_USER state is for. When a transaction lands there, the platform pauses it, requests the missing detail from the customer, and resumes automatically once the customer responds. An agent can drive the whole loop:

"Put the pending large-transfer flag into AWAITING_USER, request source-of-funds documentation from the customer, and resume monitoring when they reply."

The transaction sits in a controlled pending state instead of being blocked outright or waved through. When the customer supplies the documentation, the flow continues; if they do not, the item stays surfaced for review. This auto-remediation loop keeps legitimate customers moving while holding genuinely unresolved transactions, and it means your agent can resolve a large slice of flags without a human touching every one.

Start free

Transaction Monitoring over MCP means an analyst describes the control — submit the transaction, triage the queue, open a case, assemble the evidence, run the remediation loop — and the agent carries each transaction to its correct next state with a human on the consequential decisions. Didit is used by 2,000+ companies, is backed by $7.5M in funding, is a Y Combinator W26 company, is profitable, and covers 220+ countries and territories. Start free: 500 checks per month at no cost, the MCP layer free, and $0.02 per transaction beyond the free tier. Read the MCP overview, browse the developer hub, or self-host the open-source server and connect your agent today.