Best of mcp — January 2026

  1. 1
    Article
    Avatar of claudeClaude·11w

    Interactive tools in Claude

    Claude now supports interactive tools directly within conversations, allowing users to work with applications like Asana, Slack, Figma, and Amplitude without switching tabs. The feature is built on the Model Context Protocol (MCP), an open standard for connecting tools to AI applications. A new MCP Apps extension enables developers to build interactive UIs that work across any supporting AI product. The interactive tools are available on web and desktop for Pro, Max, Team, and Enterprise plans.

  2. 2
    Article
    Avatar of shaafShaaf·15w

    Keycloak MCP Server: Manage Identity with Natural Language

    An MCP server enables natural language management of Keycloak identity and access management through AI assistants. The open-source project supports 45+ operations including user management, realm configuration, client setup, and authentication flows. Version 0.3 introduces JWT authentication, SSE transport, Kubernetes deployment support, containerization, and production-ready features like health checks and Prometheus metrics. Developers can manage Keycloak by conversing with AI assistants instead of using the admin console or CLI commands.

  3. 3
    Video
    Avatar of johnhammondJohn Hammond·12w

    "I made an Evil MCP server" (and AI fell for it)

    A security researcher demonstrates critical vulnerabilities in the Model Context Protocol (MCP) by creating a malicious MCP server that successfully tricks AI models into leaking sensitive data and injecting security vulnerabilities into code. The demonstration shows how Gemini 3 Pro falls for prompt injection attacks through MCP tools, exfiltrating prompts, code, and secrets while actively hiding malicious code changes from users. The researcher argues MCP is fundamentally insecure because it allows arbitrary prompt injection with no reliable defense, whether running locally or remotely. Claude Opus showed better resistance by recognizing the malicious intent, but the overall MCP ecosystem remains vulnerable to data exfiltration and code execution attacks through compromised or malicious servers.

  4. 4
    Article
    Avatar of cursorCursor·14w

    Dynamic context discovery

    Cursor introduces dynamic context discovery, a pattern where AI coding agents pull relevant context on-demand rather than receiving everything upfront. This approach reduces token usage by 46.9% for MCP tools while improving response quality. Key implementations include converting long tool responses to files, using chat history during summarization, supporting Agent Skills standard, lazy-loading MCP tools, and treating terminal sessions as files. The file-based abstraction enables agents to efficiently discover and retrieve only the information they need.

See all mcp archives