Business Software for Model Context Protocol (MCP) - Page 4

Visualize your microservices end-to-end, from your CDN all the way to your databases, including external dependencies. Automatically measure baselines and get recommendations of SLIs and SLOs. Understand and measure the impact across microservices. Every change introduces a ripple through your connected system. Did a security group change affect Login API? Last9 makes it easy to locate the ‘last change’ that triggered an incident. Last9 is a modern reliability stack. It’s designed to leverage your existing observability tricks and allow you to build and enforce mental models on top of your data to help you cover infrastructure, service, and product metrics with minimal effort and distractions. With all the love and passion for reliability, we address the challenges of every layer to make running systems at scale fun and embarrassingly easy! Last9 leverages the knowledge graph to automatically generate a map view of known infrastructure and service components.

Le Chat is a conversational entry point to interact with the various models from Mistral AI. It offers a pedagogical and fun way to explore Mistral AI’s technology. Le Chat can use Mistral Large or Mistral Small under the hood, or a prototype model called Mistral Next, designed to be brief and concise. We are hard at work to make our models as useful and as little opinionated as possible, although much remain to be improved! Thanks to a tunable system-level moderation mechanism, Le Chat warns you in a non-invasive way when you’re pushing the conversation in directions where the assistant may produce sensitive or controversial content.

Claude Haiku 3 is the fastest and most affordable model in its intelligence class. With state-of-the-art vision capabilities and strong performance on industry benchmarks, Haiku is a versatile solution for a wide range of enterprise applications. The model is now available alongside Sonnet and Opus in the Claude API and on claude.ai for our Claude Pro subscribers.

Sky is an AI-powered assistant designed for macOS, offering natural computing capabilities that allow users to interact with their computers through natural language. It overlays your current activities, enabling seamless access to AI assistance across various tasks such as chatting, writing, planning, and coding. Sky understands the context of what's on your screen and can execute actions using your existing applications. Users can customize Sky with personalized prompts, scripts, shortcuts, and Model Context Protocols (MCPs), tailoring the experience to their specific workflows. This integration aims to make computing more intuitive by bridging the gap between human language and computer operations. Sky is scheduled for release in the summer of 2025, with more information available on its official website.

SchemaFlow is a powerful tool designed to enhance AI-powered development by providing real-time access to your PostgreSQL database schema through the Model Context Protocol (MCP). It allows developers to connect their databases, visualize schema structures with interactive diagrams, and export schemas in various formats such as JSON, Markdown, SQL, and Mermaid. With native MCP support via Server-Sent Events (SSE), SchemaFlow enables seamless integration with AI-Integrated Development Environments (AI-IDEs) like Cursor, Windsurf, and VS Code, ensuring that AI assistants have up-to-date schema information for accurate code generation. It offers secure token-based authentication for MCP connections, automatic schema synchronization to keep AI assistants informed of any changes, and a schema browser for easy navigation of tables and relationships.

11.ai is a voice-first AI assistant built on ElevenLabs Conversational AI that connects your voice to everyday workflows via the Model Context Protocol (MCP), enabling hands-free planning, research, project management, and team communication. By integrating out of the box with tools such as Perplexity for live web research, Linear for issue tracking, Slack for messaging, and Notion for knowledge management, and supporting custom MCP servers, 11.ai can interpret sequential voice commands, contextualize data, and take meaningful actions. It delivers real-time, low-latency interactions with multimodal support (voice and text), integrated retrieval-augmented generation, automatic language detection for seamless multilingual conversations, and enterprise-grade security (including HIPAA compliance).

The next era of financial infrastructure is here—and it’s driven by AI, not legacy code. Finpace replaces brittle, manual systems with an intelligent backend that adapts instantly. No more waiting for release cycles. No more workarounds. Institutions using Finpace can create, launch, and refine financial products in real time, without compromising compliance or control.

Claude Opus 4.1 is an incremental upgrade to Claude Opus 4 that boosts coding, agentic reasoning, and data-analysis performance without changing deployment complexity. It raises coding accuracy to 74.5 percent on SWE-bench Verified and sharpens in-depth research and detailed tracking for agentic search tasks. GitHub reports notable gains in multi-file code refactoring, while Rakuten Group highlights its precision in pinpointing exact corrections within large codebases without introducing bugs. Independent benchmarks show about a one-standard-deviation improvement on junior developer tests compared to Opus 4, mirroring major leaps seen in prior Claude releases. Opus 4.1 is available now to paid Claude users, in Claude Code, and via the Anthropic API (model ID claude-opus-4-1-20250805), as well as through Amazon Bedrock and Google Cloud Vertex AI, and integrates seamlessly into existing workflows with no additional setup beyond selecting the new model.

Rube is a universal MCP (Model Context Protocol) server that enables AI chat clients to perform real-world actions across 500+ applications, including Gmail, Slack, GitHub, Notion, and more. Once installed, users authenticate their apps just once, and then, via natural language within their AI chat, they can instruct Rube to execute tasks like sending emails, creating tasks, updating databases, or posting updates. It intelligently manages authentication, API routing, and context handling behind the scenes, allowing for seamless multi-step workflows, such as fetching data from one app and sending it to another, without manual setup. Rube supports both individual and team use: shared connections let teammates access apps through a single, unified interface, while integrations persist across different AI clients. Built on Composio’s secure infrastructure, Rube ensures encrypted OAuth flows and SOC‑2 compliant practice, all wrapped in a streamlined, chat-first automation experience.

Auggie CLI brings Augment’s intelligent coding agent directly into your terminal by leveraging its powerful context engine to analyze code, make edits, and execute tools both interactively and within automated workflows. Developers can install it via npm (requiring Node.js 22+ and a compatible shell), then launch a full-screen interactive session using auggie, complete with real-time streaming, visual progress, and conversational tooling, for debugging, feature development, PR review, or triaging alerts. For automation, Auggie offers streamlined modes ideal for CI/CD pipelines and background tasks. The CLI also supports custom slash commands for repeatable workflows, integrates with external tools and systems via native integrations and Model Context Protocol (MCP) servers, and can be scripted in pipelines or GitHub Actions for tasks like auto-generating PR descriptions.

Incredible is a no-code automation platform powered by agentic AI models designed for real work across applications, letting users create AI “coworkers” that perform complex, multi-step workflows merely by describing tasks in plain English. These AI agents integrate with hundreds of productivity tools, CRMs, ERPs, email systems, Notion, HubSpot, OneDrive, Trello, Slack, and more to perform actions like content repurposing, CRM health checks, contract reviews, and content calendar updates without writing any code. Its architecture supports parallel execution of hundreds of actions with low latency and handles large datasets efficiently, dramatically reducing token limitations and hallucinations in data-critical tasks. The latest model, Incredible Small 1.0, is available in research preview and via API as a drop-in alternative to other LLM endpoints, offering high-precision data processing, near-zero hallucination, and enterprise-scale automation.

Koi is a software supply chain security platform that helps organizations track, govern, and control installations across every endpoint. From browser extensions to IDE plug-ins, CI/CD tools, and AI models, Koi secures the blind spots where attackers often gain entry. Its Wings™ technology goes beyond surface scans by analyzing actual code for secrets, vulnerabilities, and malware while continuously updating risk scores. Koi combines marketplace scanning, publisher reputation intelligence, and dynamic code analysis to deliver real-time visibility and control. With features like automated approvals, preventive policies, and detailed risk reports, teams can block unsafe installs without slowing down adoption of safe tools. By making every install transparent and governable, Koi ensures enterprises can safely harness the full power of their software ecosystem.

Google’s Agent Payments Protocol (AP2) is an open protocol designed together with over 60 payments, fintech, and tech companies (e.g., Mastercard, PayPal, Adyen, Coinbase, Etsy) to enable secure, agent-led transactions across platforms. It builds on earlier open standards like Agent2Agent (A2A) and the Model Context Protocol (MCP) to ensure that when an AI agent initiates or completes a payment on behalf of a user, three core requirements are met: authorization (proving the user explicitly gave permission for that specific purchase), authenticity (ensuring the agent’s intended purchase matches what the user meant), and accountability (clear audit trails and responsibility in case of errors or fraud). The protocol uses mandates, which are cryptographically signed digital contracts backed by verifiable credentials.

Gentoro is a platform built to empower enterprises to adopt agentic automation by bridging AI agents with real-world systems securely and at scale. It uses the Model Context Protocol (MCP) as its foundation, allowing developers to automatically convert OpenAPI specs or backend endpoints into production-ready MCP Tools, without writing custom integration code. Gentoro takes care of runtime concerns like logging, retries, monitoring, and cost optimization, while enforcing secure access, auditability, and governance policies (e.g., OAuth support, policy enforcement) whether deployed in a private cloud or on-premises. It is model- and framework-agnostic, meaning it supports integration with various LLMs and agent architectures. Gentoro helps avoid vendor lock-in and simplifies tool orchestration in enterprise environments by managing tool generation, runtime, security, and maintenance in one stack.

8090 describes itself as a next-generation software factory platform that aims to let individuals or small teams build production-quality software without needing a full engineering team. Its offering includes modules like refinery, foundry, planner, assembler, and validator, components intended to streamline the software building lifecycle from specification to deployment. It sits in beta and is currently invite-only via a waitlist, with account, billing, and team management features rolling out gradually. Key frameworks include xRx, a multimodal conversational AI framework developed by 8090 that helps orchestrate reasoning systems across different modalities. 8090 positions itself as an incubator and platform, with the promise of delivering 80% feature-complete versions of enterprise software at dramatically reduced cost by combining AI and offshoring.

Claude Sonnet 4.5 is Anthropic’s latest frontier model, designed to excel in long-horizon coding, agentic workflows, and intensive computer use while maintaining safety and alignment. It achieves state-of-the-art performance on the SWE-bench Verified benchmark (for software engineering) and leads on OSWorld (a computer use benchmark), with the ability to sustain focus over 30 hours on complex, multi-step tasks. The model introduces improvements in tool handling, memory management, and context processing, enabling more sophisticated reasoning, better domain understanding (from finance and law to STEM), and deeper code comprehension. It supports context editing and memory tools to sustain long conversations or multi-agent tasks, and allows code execution and file creation within Claude apps. Sonnet 4.5 is deployed at AI Safety Level 3 (ASL-3), with classifiers protecting against inputs or outputs tied to risky domains, and includes mitigations against prompt injection.

Agent Builder is part of OpenAI’s tooling for constructing agentic applications, systems that use large language models to perform multi-step tasks autonomously, with governance, tool integration, memory, orchestration, and observability baked in. The platform offers a composable set of primitives—models, tools, memory/state, guardrails, and workflow orchestration- that developers assemble into agents capable of deciding when to call a tool, when to act, and when to halt and hand off control. OpenAI provides a new Responses API that combines chat capabilities with built-in tool use, along with an Agents SDK (Python, JS/TS) that abstracts the control loop, supports guardrail enforcement (validations on inputs/outputs), handoffs between agents, session management, and tracing of agent executions. Agents can be augmented with built-in tools like web search, file search, or computer use, or custom function-calling tools.

Amazon QuickSuite is a unified generative-AI and analytics workspace designed to help business users, analysts, and domain experts turn data, workflows, and internal knowledge into actionable insights and automation. The platform brings together multiple capabilities; interactive dashboards and visualizations (leveraging the existing QuickSight service), natural-language Q&A and generative BI, workflow automation, deep data discovery and research agents, and connector support for enterprise systems and SaaS tools. From a data perspective, QuickSuite enables users to connect multiple data sources, spreadsheets, cloud warehouses, third-party apps, and on-premises systems, and ask questions in plain language, build dashboards, schedule reports, or trigger automations. From a workflow perspective, it allows non-technical roles to automate routine tasks, such as report generation, alerting, or data onboarding, through agent-powered flows.

Claude Opus 4.5 is Anthropic’s newest flagship model, delivering major improvements in reasoning, coding, agentic workflows, and real-world problem solving. It outperforms previous models and leading competitors on benchmarks such as SWE-bench, multilingual coding tests, and advanced agent evaluations. Opus 4.5 also introduces stronger safety features, including significantly higher resistance to prompt injection and improved alignment across sensitive tasks. Developers gain new controls through the Claude API—like effort parameters, context compaction, and advanced tool use—allowing for more efficient, longer-running agentic workflows. Product updates across Claude, Claude Code, the Chrome extension, and Excel integrations expand how users interact with the model for software engineering, research, and everyday productivity. Overall, Claude Opus 4.5 marks a substantial step forward in capability, reliability, and usability for developers, enterprises, and end users.

Claude, developed by Anthropic, is an advanced conversational AI model that now includes a revolutionary capability called computer use. This feature allows Claude to interact with a computer in a way that mimics human behavior, such as moving a cursor, clicking buttons, and typing. The goal of computer use is to automate complex workflows and tasks that require interaction with multiple applications, such as filling out forms or conducting research. Although still in public beta, this feature marks a significant step forward in creating AI models that can function independently within computing environments, making them more versatile in business applications like software testing, automation, and task completion.

Bluebricks enables companies to create stable, governed cloud environments from reusable blueprints. No need to depend on DevOps for every request. The platform uses environment orchestration to work with existing Infrastructure as Code tools like Terraform and Helm. It adds AI capabilities to maintain consistency and eliminate configuration errors. Teams get self-service infrastructure provisioning while maintaining centralized governance and security controls across any cloud provider. The platform supports AWS, Google Cloud, Azure, Oracle, and Kubernetes environments. Organizations can transform complex deployments into standardized, reusable blueprints that work across environments. Automatic dependency tracking prevents breaking changes, while built-in RBAC and policy enforcement maintain enterprise security requirements. Bluebricks serves as the backend for internal developer portals, providing developers with infrastructure capabilities without sacrificing control.

Sita cuts AI spend by 30% and saves 25 hours per developer each month by automating search and documentation. It turns code, messages, and docs into a knowledge graph and feeds only relevant context to your coding tools, cutting input tokens by 32%. Sita also keeps your docs up to date and helps ship features 37% faster with 68% fewer bugs. We onboard you with white-glove support in one hour. Sita works with or without your current tools and can power them through MCP or our own agent.