All news with #mcp tag

🧰 The new Java SDK for the Model Context Protocol (MCP) Toolbox for Databases delivers type-safe, production-grade agent orchestration for Java and Spring Boot environments. It integrates with 42+ data sources, including AlloyDB, Cloud SQL, and Cloud Spanner, and simplifies secure, parameterized mappings from natural language intents to database operations. The SDK is designed for stateful, high-concurrency transactional agents and leverages Application Default Credentials for zero-config security.

🧭 This practical guide from GoogleWalks developers through how to move AI agents from prototype to production, highlighting architecture, operational patterns, and safety considerations. It explains an agent as an LLM-driven autonomous system surrounded by an orchestration layer that manages session state, long-term memory, retrieval (RAG), tool use, and security. The post emphasizes emerging interoperability standards such as MCP and A2A, and underscores the importance of context engineering, trajectory-based testing, and staged rollouts. Authors provide targeted guides and code samples to help teams adopt these practices and validate agents before broad deployment.

🧰 Cloudflare introduces a new MCP server that uses Code Mode to expose the entire Cloudflare API through just two tools, search() and execute(). By letting agents write compact JavaScript against a typed OpenAPI spec and executing it inside a sandboxed Dynamic Worker, the server dramatically reduces model context token use. The footprint remains fixed regardless of API size, enabling progressive discovery, OAuth 2.1 downscoping, and safe execution for agents.

🔗 Gemini CLI's Neo4j extension connects graph databases to Gemini's reasoning via the Model Context Protocol (MCP). The extension bundles four MCP servers to manage Neo4j Aura, translate natural language into Cypher, support interactive data modeling and visualization, and use Neo4j as long-term memory for agentic flows. Developers can provision databases, run Cypher queries, and persist knowledge from the terminal to accelerate GraphRAG workflows.

🔒 Kiro is now available in AWS GovCloud (US-East) and AWS GovCloud (US-West), enabling agentic AI development for compliance-sensitive workloads. The platform combines an integrated development environment (IDE) and a command-line interface (CLI) to support spec-driven workflows that turn prompts into specs, working code, documentation, and tests. Native Model Context Protocol (MCP) support lets Kiro connect to documentation, databases, APIs, and other enterprise resources while integrating with AWS IAM Identity Center for enterprise authentication.

🧬 AWS HealthOmics now integrates a Kiro Power and a Kiro IDE extension to accelerate bioinformatics workflow development with AI agent-assisted creation, debugging, and optimization. The IDE extension supports domain-specific languages such as Nextflow and WDL directly in the Kiro interface, offering syntax highlighting, code completion, and troubleshooting guidance. The Kiro Power packages the HealthOmics MCP server alongside steering files and agent hooks to provide domain expertise, automated run analysis, and failure diagnostics for faster, more reliable workflow iteration.

🚨 Cybersecurity researchers have identified three prompt-injection vulnerabilities in Anthropic's reference Git server implementation, mcp-server-git, affecting default installations and all releases before 8 December 2025. The flaws let attackers manipulate what an AI assistant reads—such as a README, issue text or a webpage—to cause unintended actions without credentials or system access. Exploits can enable code execution when combined with a filesystem MCP server, delete arbitrary files, or load sensitive files into a model's context. Anthropic accepted the reports in September and issued patches in December 2025; affected users are urged to update immediately.

⚠️ A trio of vulnerabilities in mcp-server-git, the official MCP Git server maintained by Anthropic, can be chained to read or delete arbitrary files and, in certain scenarios, achieve remote code execution. Cyata researcher Yarden Porat showed these issues are exploitable via prompt injection when an AI assistant ingests attacker-controlled content such as a malicious README or poisoned issue text. Fixes were released in 2025.9.25 and 2025.12.18; users should update the Python package promptly to mitigate risk.

🔍 OpenAI is internally testing a web update for ChatGPT that it plans to roll out gradually in the coming weeks. Leaked references highlight a new task-oriented feature codenamed Salute, an "is model preferred" flag intended to improve local business and map results, and a secure tunnel option for MCP servers. The company is also trialing inline editable code and math blocks to expand the existing formatting block functionality. Collectively, these changes aim to streamline file-based workflows, enhance location-specific answers, and simplify secure enterprise connectivity.

🤖 Amazon Quick now supports invoking third‑party AI agents from Box, Canva, and PagerDuty, enabling chat and automation tasks—such as querying documents, generating presentations, and extracting incident insights—directly within the Quick workspace. Quick has also expanded its built‑in actions to include integrations with GitHub, Notion, Linear, Hugging Face, Monday.com, HubSpot, Intercom, and more, allowing users to create issues, summarize notes, and manage CRM workflows without switching apps. Customers can further connect thousands of additional applications using Model Context Protocol (MCP) and OpenAPI connectors. These features are available in all AWS Regions where Quick is offered.

🤖 Amazon Quick now supports invoking specialized third-party agents (Box, Canva, PagerDuty) and expands its built-in actions library with integrations for GitHub, Notion, Canva, Box, Linear, Hugging Face, Monday.com, HubSpot, and Intercom. Users can run agentic tasks—pull incident insights, generate presentations, or query documents—directly from a single workspace. Quick also continues to support custom MCP and OpenAPI connectors for broader application connectivity. These features are available in all regions where Amazon Quick is offered.

🚀 The preview release of a fully managed, remote MCP server for BigQuery (Jan 2026) lets developers connect LLM-powered agents directly to analytics data via a standard HTTP endpoint without managing infrastructure. The blog demonstrates step‑by‑step integration with the Agent Development Kit (ADK) and the Gemini CLI, including OAuth client creation and Gemini API key setup, and loading a sample cymbal_pets dataset. It highlights compatibility with popular frameworks (ADK, LangGraph, Claude code, Cursor IDE) and reminds readers to follow AI security and production best practices.

📢Google Cloud’s Data Cloud updates through mid‑2025 introduce new self‑service Looker features, expanded Model Context Protocol (MCP) support, and tighter AI-to-data integrations. Highlights include AlloyDB AI time‑series forecasting via AI.FORECAST, GA of Conversational Analytics powered by Gemini, and the MCP Toolbox and ADK to securely connect agents to BigQuery, Spanner, Cloud SQL, and Looker. Dataplex Universal Catalog now previews curated data products for governed, deployable datasets and AI use.

🔗 To build production-ready agentic systems, Google Cloud offers hands-on labs that demonstrate how Agent Development Kit (ADK), the Model Context Protocol (MCP), and the Agent-to-Agent Protocol (A2A) work together. The labs begin with a foundational "Hello World" agent and progress to connecting agents to knowledge sources via MCP, with concrete examples for exposing BigQuery and CloudSQL. By adopting these standards instead of bespoke integrations, teams can scale and maintain multi-agent systems more reliably.

🔗 This post explains how to expose Looker’s semantic layer to Gemini Enterprise quickly by using the MCP Toolbox for Databases and the Agent Development Kit (ADK). It outlines three concise steps: deploy the MCP Toolbox (recommended to Cloud Run), build and deploy an ADK agent to Vertex AI Agent Engine, and register that agent with Gemini Enterprise. The result: trusted Looker models available inside Gemini for natural‑language business queries.

🚀 Amazon Aurora DSQL now provisions clusters in seconds, cutting setup time from minutes to near-instant. Developers can immediately use the integrated query editor in the AWS Console to prototype or build without configuring external clients or connecting through the Aurora DSQL Model Context Protocol (MCP) server. The change supports both prototyping and production workloads while preserving Aurora DSQL’s scalability, active-active high availability, zero infrastructure management, and pay-for-what-you-use pricing. The enhancement is available in all Regions where Aurora DSQL is offered and is accessible via the AWS Free Tier.

🚀 AWS announces integration of Amazon Aurora PostgreSQL-Compatible Edition with Kiro powers, enabling agent-assisted database development using prepackaged MCP servers, steering files, and hooks. The Aurora PostgreSQL power bundles data plane (queries, schema) and control plane (cluster creation) capabilities with targeted best-practice guidance. Available via Kiro IDE and the Kiro powers catalog for one-click installation across AWS Regions.

🔒 Google’s Apigee now supports MCP with fully managed, remote servers, enabling organizations to expose existing APIs as agent tools without code changes or running MCP infrastructure. By creating an MCP proxy with your OpenAPI spec and a /mcp basepath, Apigee handles transcoding, protocol handling, and automatic registration in API hub. You can apply Apigee’s built-in security, identity, quota, and analytics controls to govern and monitor agent interactions. The capability is currently available in preview for a limited set of customers.

🔌 Google announced fully-managed, remote support for Anthropic's Model Context Protocol (MCP), enabling agents and standard MCP clients to access a unified, enterprise-ready endpoint for Google and Google Cloud services. The managed MCP servers integrate with services like Google Maps, BigQuery, GCE, and GKE to let agents perform geospatial queries, in-place analytics, and infrastructure operations. Built-in discovery, governance, IAM controls, audit logging, and Google Cloud Model Armor provide security and observability. Developers can expose and govern APIs via Apigee and the Cloud API Registry to create discoverable tools for agentic workflows.

🤖 Amazon Connect now supports the Model Context Protocol (MCP), enabling AI-driven customer self-service and employee assistance agents to invoke standardized tools to fetch information and perform actions during interactions. Amazon Connect offers out-of-the-box MCP tools for tasks like updating contact attributes and retrieving case information, and allows flow modules to be exposed as MCP tools so business logic is reusable across deterministic and generative workflows. Organizations can also integrate custom or third-party tools via flow modules or the Amazon Bedrock AgentCore Gateway to automate actions such as order lookups, refunds, and customer-record updates without human intervention.