MCP Servers

OpenClaw v2026.7.1-beta.6 introduces major UI/UX improvements with a redesigned Control UI featuring session-primary navigation and native macOS chat, adds support for new AI models (GPT-5.6, Claude Sonnet 5, Meta Muse Spark 1.1) and providers (Featherless, ClawRouter), implements conversational onboarding through an agent-loop setup, and enhances mobile experiences with offline caching, voice capabilities, and improved session management across iOS, Android, and Apple Watch.

OpenClaw v2026.7.1-beta.5 introduces major features including conversational AI-guided onboarding through Crestodian, a new ClawRouter provider for dynamic model discovery and quota management, redesigned Control UI with session-first navigation, offline/spoken capabilities for mobile platforms, and support for GPT-5.6 models. The release emphasizes improved user experience across web, iOS, Android, macOS, and Apple Watch with features like auto-generated session titles, external harness attachment via Claude Code, and Telegram workflow enhancements.

Claude Code v2.1.207 introduces auto mode availability without opt-in on Bedrock, Vertex AI, and Foundry, while fixing critical issues including terminal freezing during long streaming responses, security consent dialog bypasses, and various UI/workflow bugs. The release improves agent view functionality, Remote Control session handling, and Deep Research labeling, plus enhances security by rejecting shell-injection patterns in plugin hooks and preventing unintended settings persistence.

LangChain v1.3.13 release introduces support for Meta models through a new `meta` extra package, adds explicit prompt caching for OpenAI models to improve performance and reduce costs, and includes dependency updates. This minor release enhances integration capabilities with Meta's language models and optimizes OpenAI API usage patterns.

Claude Code v2.1.206 introduces enhanced directory navigation with `/cd` suggestions, a `/doctor` check for optimizing CLAUDE.md files, and improved git workflow automation via `/commit-push-pr`. The release fixes critical issues including expired login error handling, MCP server timeout configuration, OAuth re-authentication, and keyboard input responsiveness across multiple platforms. Performance improvements include background agent auto-upgrades and better model picker accuracy.

Release 2026.7.10 of the Model Context Protocol servers package includes updates to four core server implementations: filesystem, time, fetch, and git. This release updates all packages to version 2026.7.10, providing improvements and fixes across the MCP server ecosystem. The release maintains compatibility with the Model Context Protocol standard for AI agent development.

langchain-fireworks version 1.4.4 is released with a critical fix for cached prompt token usage reporting. The update includes dependency refreshes (pytest, langsmith), model profile data updates, improved documentation on prompt-cache session affinity, and enhanced test coverage for request-level extra headers.

Claude Code v2.1.205 introduces critical bug fixes and improvements across session management, file handling, and auto mode functionality. Key enhancements include blocking tampering with session transcripts, fixing JSON schema validation issues, improving background agent state tracking, and optimizing memory usage during auto-updates. The release also strengthens security by preventing fabricated approvals and adds better diagnostics with the enhanced `/doctor` command.

langchain-core version 1.4.9 is a maintenance release that includes bug fixes for output parsers, error message improvements, async context handling, and dependency updates. Key improvements address langsmith loader errors, XML/Pydantic parser bugs, Google docstring parsing issues, and code quality enhancements. The release also updates langsmith to 0.8.18, jupyterlab to 4.5.9, and vcrpy to 8.2.1.

LangChain v1.3.12 release includes critical bug fixes for tool retry middleware interrupt propagation, shell middleware process-group handling, and Anthropic cache marker sanitization on fallback retries. The release also improves code quality through ruff style fixes and enhanced type annotations in agent middleware tests. These changes enhance reliability and stability of LangChain's middleware and agent execution systems.

Claude Code v2.1.203 is a maintenance release focused on stability, performance, and user experience improvements. Key fixes address background session reliability, memory/CPU regressions, environment variable handling, and UI responsiveness. The release includes better login expiration warnings, improved subagent delegation behavior, and reduced binary size by ~7 MB through lazy loading optimization.

Google ADK Python v2.4.0 introduces significant enhancements including mTLS support across multiple tools, OpenAI Responses API integration, Managed Agents API backing, and streaming improvements for thoughts and media. The release adds workflow-as-tool capabilities, enhanced database session management, and improved analytics with thinking/tool-use token tracking. Multiple bug fixes address security concerns, path traversal prevention, and SDK compatibility updates.

Claude Code v2.1.202 introduces dynamic workflow size configuration, enhanced OpenTelemetry telemetry attributes for workflow tracing, and fixes 17+ critical bugs spanning interactive sessions, Remote Control integration, voice dictation, and workflow parsing. Key improvements include better sign-in URL handling over SSH, improved workflow agent list UI, and enhanced MCP error messaging. The release also optimizes session resumption performance in repositories with many git worktrees.

langchain-mistralai version 1.1.6 release introduces citation metadata surfacing from chat responses, adds support for stop sequences, and includes dependency updates (vcrpy, langsmith). The release also features package version tracking for tracing metadata, documentation refreshes, and model profile data updates across the LangChain ecosystem.

OpenClaw v2026.7.1-beta.2 introduces GPT-5.6 support, external harness attachment via `openclaw attach`, Telegram Codex workflows with login and steering, event-driven cron runs with `on-exit` scheduling, and native app improvements including iOS 26 visual system adoption. The release also adds ClawRouter for dynamic model discovery with credential-scoped routing, richer iMessage messaging with native polls, safer scoped conversations via capability profiles, and enhanced Control UI navigation with reasoning-effort controls. Extensive fixes address Telegram durability, agent reliability, provider safety, channel delivery, cron correctness, and memory recovery across multiple platforms.

Release 2026.7.4 of modelcontextprotocol/servers updates four core server packages to version 2026.7.4. The release includes updates to the everything server, filesystem server, sequential-thinking server, and memory server. This is a coordinated release across multiple MCP server implementations.

Claude Code v2.1.200 introduces significant stability and usability improvements, including changes to user interaction defaults (manual permission mode, no auto-continue dialogs), fixes for background session crashes and daemon management issues, and enhancements to accessibility features. The release addresses critical bugs in MCP server handling, subagent rate limiting, and terminal rendering, while improving screen reader support and installation robustness.

This cookbook demonstrates how to reproduce Claude's published agentic search benchmark scores (DeepSearchQA, BrowseComp) using the Messages API with programmatic tool calling, server-side compaction, and task budgets. The key is proper harness configuration—API parameters that become critical for agents running 30+ tool calls across hundreds of thousands of tokens. By following this guide, you'll build an agentic search loop that matches Claude's official benchmark performance and understand why each configuration choice matters for long-horizon tasks.

Claude Code v2.1.196 introduces organization-level default model settings, improved session management with readable names, and enhanced security for MCP server handling. The release includes numerous bug fixes for background jobs, PowerShell compatibility, agent panel functionality, and streaming reliability. Key improvements focus on session persistence across restarts, better file attachment handling, and reduced token usage in code review workflows.

OpenClaw v2026.6.11-beta.2 introduces enhanced channel control with Slack relay mode and native Mattermost commands, richer operator workflows via file-driven message handling and remote wake-up paths, safer plugin distribution with externalized plugins and icon metadata, stronger mobile operations with improved Android settings, and more reliable agent turns through Codex partial deltas and prompt-cache stability. The release includes 308 merged PRs addressing gateway tooling, provider coverage, channel delivery reliability, WhatsApp message identity preservation, gateway session safety, agent fallback behavior, and configuration guardrails across multiple integrations.