Model Context Protocol

4 use cases using this technology

4published use cases

2industries

2countries on record

Agentic AI

top AI capability

Evidence mix: High 4 · Medium 0 · Low 0 — bands are computed from each record's evidence signals.

Industry

Country

4 use cases

Financial ServicesAgentic AILarge Language Models

Qonto builds Claude-powered agents that run payroll 5x faster and cut invoice creation time 3x

Qonto, a European business banking platform serving over 600,000 businesses across eight markets, built AI agents on Claude Opus 4.5/Sonnet/Haiku via Amazon Bedrock that prepare bulk payroll transfers, draft client invoices from a CSV, and answer cash-flow questions, with the customer always giving final approval before money moves. Since launching six weeks after the November 2025 project start, the agents send bank transfers 2x faster, cut invoice creation time 3x, run payroll 5x quicker, and have processed customer-approved transfers as large as €100,000.

QontoClaude Opus 4.5 · Claude Sonnet · Claude Haiku +2

Financial ServicesAgentic AICode Generation

Satispay's engineers generate 75% of committed code with Claude Code, cutting a Java upgrade from 4 weeks to 4 days

Satispay, Italy's leading independent payment network with 6 million consumers, rolled out Claude Code to its engineering organization after a structured 30-day evaluation, deploying it fleet-wide within 30 days. Engineers now generate over 75% of monthly committed code with Claude, achieved 10x faster modernization of the core transaction service (a Java 8-to-21 and Spring upgrade done in under four days versus a four-week estimate), cut data-transformation Lambda development from three days to under an hour, and completed an 18-month code update roadmap in 7 months.

Satispay· ItalyClaude Code · Claude Enterprise · Claude Cowork +1

Financial ServicesAgentic AICode Generation

Pictet rolls out Claude Code to 700 staff, cutting a two-week compliance gap analysis to hours

Swiss private bank Pictet, which manages around CHF 800 billion, rolled out Claude Code and Claude Cowork to about 700 people across its technology, product and business teams, training over 500 staff through 25 workshops with partner Artefact, with business data processing kept in the EU and Switzerland behind a purpose-built API gateway. A compliance gap analysis comparing over 50 internal directives against current regulations, originally sized at two weeks for a three-person team, was completed in hours, and product managers now generate working prototypes in two hours instead of two weeks.

PictetClaude Code · Claude Cowork · Model Context Protocol

LegalAgentic AIDocument Intelligence

Delivering agentic AI to law firms globally using AWS with stp.one

stp.one, a Karlsruhe, Germany-based legal tech provider founded in 1993, built Legal Twin, an AI-driven platform integrated with its document management system STP Documents, using Amazon Bedrock (including Anthropic's Claude and the Titan embedding model) and Amazon Aurora PostgreSQL. Legal Twin offers six AI-powered capabilities including intelligent contract risk analysis and automated receivables processing, with responses grounded in case documents and court decisions and citations shown so lawyers can verify sources. It supports Model Context Protocol integration and lets clients with data sovereignty requirements store and process data locally, connecting on-premises storage with cloud-based processing. Certain claims that traditionally took 6-10 minutes to file can now be processed in under 30 seconds using Legal Twin, and productivity gains for users reach up to 3x at the upper end. The platform must comply with GDPR and Germany's federal code for lawyers.

stp.one· GermanyAmazon Bedrock · Anthropic Claude · Amazon Titan embedding model +2