MCP

Rocket Close collaborated with AWS to create Supercharger, an agentic AI solution using Strands Agents, Amazon Bedrock, and MCP tools to streamline title operations. By centralizing knowledge and automating research-heavy tasks, the solution reduced contact center calls and emails by 30%, improved title exam accuracy, and enhanced client satisfaction. This post details the technical architecture, business impact, and lessons learned.

PULSE8.ai Cortex is an agent-native knowledge OS built on Markdown, providing a shared vault for AI agents and humans with a typed knowledge graph, full-text search, and a MarkItDown-powered compiler, all accessible via a unified MCP interface. Inspired by Andrej Karpathy's LLM Wiki pattern, it requires no database.

Nenya is a lightweight, zero-dependency AI API gateway written in Go. It sits between AI coding clients and upstream LLM providers, adding secret redaction, context management, agent routing, and MCP tool integration with transparent SSE streaming. Security-hardened features include non-root execution, mlock for secrets, seccomp, and no-new-privileges.

This post shows how to build a custom meeting prep and follow-up assistant using Amazon Quick and Cisco Webex MCP servers. From a single prompt, the agent finds an upcoming Webex meeting, reviews prior meeting summaries and transcripts, and pulls related Vidcast highlights and transcript context. It then searches Webex message threads for unresolved follow-ups and creates a concise prep brief. After the meeting, the same assistant can summarize the discussion and identify action items. It can also find related Vidcast updates and draft a follow-up message for the right Webex space.

Compact language models face challenges beyond isolated function calling when using tools. Evoflux uses evolutionary search at inference time to repair executable tool workflows, raising execution feasibility from 3% to 17-24% on MCP-Bench tasks, outperforming SFT and DPO baselines.

xAI today released the Grok Build Plugin Marketplace, a built-in catalog of plugins for its terminal coding agent. Plugins bundle skills, commands, agents, hooks, MCP servers, and LSPs into one package, installable without leaving the terminal. Six plugins launch with partners including MongoDB, Vercel, Sentry, Chrome DevTools, Cloudflare, and Superpowers, with commit-SHA pinning for security.

The next wave of enterprise AI focuses on software and data infrastructure needed to make models useful in real businesses. Snowflake is positioning itself as a connector between proprietary data and AI models. Key insights include strong data foundations, security and governance frameworks, and the importance of trusted, governed intelligence for production AI.

Databricks Marketplace now offers pre-built MCP servers from partners including Climb, Atropos Health, Kythera Labs, and Redox, covering biomedical, clinical evidence, medical semantics, and interoperability. These servers are centrally governed in the MCP Catalog with Unity AI Gateway, enabling rapid development of secure healthcare AI agents via low-code or custom coding.

Nous Research has released a Profile Builder for Hermes Agent within its local web dashboard, replacing the multi-step CLI setup with a single guided flow. Users can define identity, select model/provider, toggle built-in skills, install skills from the hub, and attach MCP servers, all producing isolated profile directories for running multiple agents without state collision.

CrustRecruiter is a set of MCP-based skills for Claude that combines Claude's reasoning with Crustdata's live database of 800M+ candidate profiles to automate recruiting tasks such as sourcing, market mapping, email verification, preference memory, and outreach/ATS sync, enabling personalized recruiting at scale.

CLI Market is a new platform providing verified retail pricing data for AI agents and commercial teams in Latin America, covering 51,000+ prices from 68 retailers across 8 countries, with normalized prices by kg/L, updated every 4 hours, and offering 22 MCP tools and an API.

CalmSEO is an MCP server that exposes Google Search Console data, live SERPs, keyword volumes, and on-page audits to AI agents like Claude, ChatGPT, Cursor, and Codex. It offers a free tier and paid plans with credit-based usage.

HeadlessTracker is an MCP server for portfolio tracking across crypto exchanges, on-chain wallets, and prediction markets. It supports connectors for Bybit, Binance, MetaMask, Solana, and Polymarket, offering 15 MCP tools, an interactive dashboard, and CLI queries. Users can query their portfolio via AI hosts like Claude Desktop using natural language, without building a UI.

AI agents should be first-class software users with their own identity, credentials, and permissions, rather than borrowing human sessions or acting as faceless service accounts. This article explores the agent-first authentication and authorization model, analyzes the problems with borrowed identity, discusses converging industry trends (e.g., MCP, GitHub Apps, Microsoft Entra), and outlines concrete authentication and authorization requirements, along with a GitHub-compatible implementation called agent-git-service.

Deep Memory is an open-source library that provides AI agents with structured, persistent memory using vocabulary-driven knowledge graphs. It solves the cold-start problem by predefining entity types, relationships, and property constraints, enabling agents to create and traverse entities efficiently. Supports multiple storage backends, MCP server integration, and domain starter kits.

Superhighway is a web-search API designed for AI agents: no signup, no API key, and agents pay per call (0.001 USDC each) via the x402 protocol on Base. The API returns clean JSON results, and the entire payment flow is automated, requiring zero human involvement.

This article updates the 2024 AI agents stack diagram, introducing a six-layer architecture for 2026: Models & Inference, Protocols & Tools, Memory & Knowledge, Frameworks & SDKs, Eval & Observability, and more. Key changes include MCP standardization, reasoning models, and memory as a first-class primitive. It offers honest takes and guidance on evaluating each layer.

CogCore is a lightweight TypeScript runtime library that helps developers build AI agents around their application APIs. It offers model role separation, tool calling, worker agents, sandboxed execution, skill learning, and more, allowing apps to integrate AI capabilities securely while retaining their own UI, data, permissions, and release workflow.

Salesforce and SAP adopted opposite strategies for enterprise AI using the same MCP protocol: Salesforce exposes its platform as a substrate for any agent to call directly, while SAP forces external agents to go through its first-party agent Joule. This divergence has profound implications for security, liability, pricing, and the entire enterprise software ecosystem.

AI Boost is an MCP server that lets developers capture, index, and automatically inject their coding patterns and conventions into future LLM agent sessions. It emphasizes privacy and community sharing.

Web Speed parses HTML pages into sitemaps for AI agents, making them faster and cheaper by avoiding full HTML analysis. It is MCP-native and features a global sitemap cache for faster agent performance.

Context Mode Insight is an observability platform for enterprise AI engineering, built on an open-source plugin trusted by 250K+ developers. It supports 14 AI assistants, analyzes 222 patterns, and provides role-aware insights via a privacy-first design. The paid tier ($20/seat/month) offers org-level dashboards, REST API, and remote MCP for agents, addressing needs of CTOs, EMs, CISOs, and more.

Moonshot AI has launched Kimi Code CLI, an open-source terminal AI coding agent built with TypeScript. It features subagents for parallel tasks, MCP configuration, video input, and lifecycle hooks. The tool is MIT-licensed and supports Kimi models or other providers.

A personal project called tinderbox allows users to export Claude.ai conversations, index them locally, and search them from any Claude session via an MCP server. Supports hybrid retrieval, Supabase storage, and Ollama embeddings.

A new local-first MCP server enables AI agents to safely search, edit, and maintain Apple Contacts on macOS using AppleScript automation, with dry-run writes and privacy-first design.

Michael Bolin, OpenAI Codex Tech Lead, shares his simple and straightforward AI-assisted engineering workflow: write spec, simple prompt, review code. He uses Notion docs for requirements, leverages Codex's Notion connector to auto-read context, breaks work into right-sized PRs, and lets Codex handle merge conflicts and CI babysitting. The approach emphasizes code review quality and fast iteration.

agentgateway, a unified open source gateway for AI and agent workloads, has joined the Agentic AI Foundation (AAIF) under the Linux Foundation as its fourth hosted project. It manages MCP, A2A, LLM inference, HTTP, and gRPC traffic through a single plane, providing security, observability, routing, and governance.

Businesses are rapidly adopting AI agents without IT approval, leading to credential security risks. Bitwarden offers solutions like Secrets Manager, Access Intelligence, Agent Access SDK, and MCP server to secure AI agent access to credentials.

Nexus is a local-first open-source tool that lets AI agents (like Claude Code) query and manipulate local spreadsheets (CSV, XLSX, SQLite, Google Sheets) without uploading data to the cloud. It exposes data via MCP protocol, supports non-destructive derivations (views, branches, snapshots), and includes an optional semantic reading layer called Iris.

A new open-source MCP server enables AI assistants like Claude and Codex to read OpenAI Ads data through natural language queries. The read-only tool supports 11 API endpoints for campaigns, ad groups, ads, and insights. Works with Claude Desktop, Cursor, VS Code, and other MCP clients. Requires Node.js 20+ and an OpenAI Ads API key.

Gate is a deterministic PII redaction tool written in Rust for AI agents. It uses regex, column heuristics, and Luhn checks instead of LLMs. It intercepts Bash commands and MCP tool calls via hooks, supports multiple harnesses, and provides scanning, real-time redaction, and aggregated reporting while keeping data local.

Lookspan is a local-first observability dashboard for AI agents, supporting MCP, LangGraph, CrewAI, and OpenTelemetry. All data stays in local SQLite, no cloud required. Features include real-time tracing, cost tracking, alerts, replay evaluation, and dataset experiments. Launch with one command.

DNS-AID leverages existing DNS infrastructure for AI agent discovery, publishing, and verification without new overlay networks, using DNSSEC for trust. It supports MCP, A2A, and HTTPS, and integrates into existing DNS zones.

This article outlines two methods to connect Kiro IDE to Databricks: a quick setup using four managed MCP servers, or a one-click install via the Databricks AI Dev Kit Power. Both approaches leverage Unity Catalog metadata to ground AI assistants, ensuring they only access authorized data and reducing hallucinations. The article also highlights Databricks' advantages for AI-assisted development, including unified governance, a single data copy, and an integrated AI stack.

A practical framework for moving from simple SaaS to an AI-native platform, outlining five levels of AI integration: from MCP server and personal access tokens to embedded chat, conversation history, custom UI generation, and finally an agentic harness with planning and scheduling. The author shares insights from building multiple internal agents and retrofitting AI into existing flows.

Colour Memory API provides deterministic colour matching, search, and brand audit tools based on historical archives, with REST and MCP interfaces, no LLM required for core functions.

Composer is a real-time multiplayer markdown editor that enables people and AI agents to work side-by-side on documents, with features like real-time editing, comments, suggestions, and agent collaboration via MCP.

BridgeToAgent launches an MCP connector enabling AI assistants to check a store's AI-readiness and simulate agent shopping.

Reachy Mini can now use remote tools hosted in Hugging Face Spaces via MCP, allowing it to check weather or search the web with a single command. The article covers built-in tools, profile-based control, tool installation, naming conventions, and current limitations.

Scholar Sidekick is a free tool that generates formatted citations from DOIs, PubMed IDs, arXiv IDs, and more. It also verifies citations, checks open access, and retraction status. It offers a REST API and MCP server for developers and AI agents.

This post demonstrates how to implement Open Authorization (OAuth) Code flow as an inbound authorization mechanism for MCP servers hosted on Amazon Bedrock AgentCore Gateway. By the end of this guide, you will have a production-ready setup where each AI assistant request is authenticated with a valid user identity token issued from your organization’s identity provider.

Databricks introduces new personalization features for Genie Code, including custom instructions, skills, and MCP servers, enabling the AI coding assistant to better align with team coding standards, internal workflows, and external tools. Instructions set global preferences, skills capture repeatable workflows, and MCP servers connect to systems like Jira, GitHub, and Google Drive.

Equibles is an open-source, self-hosted mini Bloomberg Terminal designed for AI agents. It scrapes, stores, and serves SEC filings, institutional holdings, insider trading, congressional trades, short data, economic indicators, and daily stock prices, and exposes them via MCP for direct AI assistant queries.

Amazon Bedrock AgentCore Gateway has been extended with new capabilities to support enterprise deployments of Model Context Protocol (MCP) servers, including enhanced tool schema support, dynamic listing, streaming, session management, and OAuth 2.0 delegated authentication, providing centralized governance, security, and observability.

An infinite clipboard tool for Claude, Codex, and other AI assistants.

This post walks through a practical implementation using KDB-X MCP server integration with Amazon Quick, demonstrating how traders and analysts can ask questions using conversational language and receive actionable insights from datasets. The integration pattern applies to various domains, from financial market analysis to IoT sensor monitoring to DevOps performance dashboards.

Uselink is a newly launched tool that converts any HTML or Markdown into a link you control. Paste a document, get a URL under your handle, decide who can read and who can comment. Readers can reply in threads without an account, which Google Docs and Notion can't do. Interactive HTML actually runs. It supports password, expiry, view limits, and versioning. New features include a visual editor and an MCP server for AI tools to publish automatically.

MAVEN (Modular Agentic Verification and Execution Network) is a lightweight symbolic reasoning scaffold designed to enhance generalization in tool-calling environments through structured decomposition, adaptive tool orchestration, and intermediate verification. On the MAVEN-Bench stress test, MAVEN improves the GPT-OSS-120b base model from 48% to 71% accuracy without additional training, using an open-weight backbone at roughly 1/10 the cost of proprietary baselines.

Moxie Docs creates living documentation for GitHub repos, provides MCP context for AI agents, a searchable workspace, and PR checks to keep docs honest.

Botcircuits is an open-source AI agent that combines LLM step reasoning with a deterministic state machine, enabling token-efficient and predictable multi-step automation. It features a CLI, workflow system with natural language authoring, skills, and MCP support.