About a-team Marketing Services
The knowledge platform for the financial technology industry
The knowledge platform for the financial technology industry

A-Team Insight Briefs

Comply Sets Out MCP Layer for Agentic Compliance Workflows

Subscribe to our newsletter

Comply has announced general availability in May 2026 for its  ComplyAI MCP Server, an enterprise-grade Model Context Protocol server designed to connect the firm’s compliance intelligence with major AI platforms used by financial services teams. The server is intended to let authorised compliance, advisor and operations users build custom AI agents in tools such as Claude, Microsoft Copilot and ChatGPT without developer support or separate IT projects.

Initial use cases include trade pre-clearance, policy guidance, morning compliance briefings, certification and onboarding workflows, annual review preparation, and natural-language reporting. So, a compliance officer could ask an AI tool to surface open certifications, open pre-clearance requests, certification gaps, and regulatory alerts, or support a pre-clearance request while maintaining the relevant compliance record.

The first enabled use case will be trade pre-clearance, where a fund manager or other financial services user can instruct an AI orchestrator to submit a request and receive an approval or denial, with audit logs retained in the Comply platform. Policy guidance through ComplyAI Policy Guide is available for testing and is expected to be available through the MCP Server in mid-2026.

Comply is framing the infrastructure layer as central to the reliability of agentic compliance. The company says its data foundation maintains regulatory content, firm-specific policies, supervisory procedures and employee compliance data for environments including the SEC, FINRA and FCA. Client data is stored, processed and audited within the Comply platform and is not shared with other firms.

Michael Stanton, CEO of Comply, linked the launch to the sequencing of data infrastructure and AI access: “We built the compliance data infrastructure before we built the AI.” David Bliss, Chief Product Officer, added: “You cannot get there by starting with AI. You have to earn it.”

Subscribe to our newsletter

Related content

WEBINAR

Recorded Webinar: GenAI and LLM case studies for Surveillance, Screening and Scanning

As Generative AI (GenAI) and Large Language Models (LLMs) move from pilot to production, compliance, surveillance, and screening functions are seeing tangible results – and new risks. From trade surveillance to adverse media screening to policy and regulatory scanning, GenAI and LLMs promise to tackle complexity and volume at a scale never seen before. But...

BLOG

SEC’s 2026 Examination Priorities – 10 Notable Changes

The U.S. Securities and Exchange Commission (SEC) has released its Examination Priorities for 2026, and while many supervisory themes continue from 2025, the tone and structure of the new document reflect a decisive pivot. After years of rapid organisational expansion and broadening remit, the Division of Examinations is now emphasising consistency, prioritisation and the effective...

EVENT

Buy AND Build: The Future of Capital Markets Technology

Buy AND Build: The Future of Capital Markets Technology London examines the latest changes and innovations in trading technology and explores how technology is being deployed to create an edge in sell side and buy side capital markets financial institutions.

GUIDE

Preparing For Primetime – How to Benefit from the Global LEI

They say time flies when you’re enjoying yourself, and so it seems the industry have been having a blast with its preparations for the introduction of the global legal entity identifier (LEI) next month. But now it’s time to get serious. To date, much of the industry debate has centred on the identifier itself: its...