"Understanding Boss Mode" matching MCP servers:

Local MCP server for BOSS Zhipin workflows. Exposes 49 tools for job search, welfare filtering, recruiter messaging, pipeline tracking, and resume optimization for AI agents.

Composes arbitrary MCP tools using JavaScript, enabling discovery, composition, and execution of other MCP servers through a single 'exec' tool.

Enables a model to write short Python programs that call a wrapped MCP server's tools as async functions, rather than invoking them one at a time. The program runs in a locked-down Docker sandbox, and every tool call passes through a host-side bridge that enforces an allowlist, schema-validated arguments, call budgets, timeouts and output caps.

An MCP server that keeps raw tool output out of the context window by sandboxing and compressing results (about 98% reduction), persisting file edits, git operations, tasks and decisions in SQLite with BM25 retrieval so the agent resumes after compaction, and enforcing routing across 17 platforms via MCP and hooks. It also encourages the model to write scripts that compute answers and log only results instead of reading large data into context.

Enables agents to accomplish multi-step work by writing a single sandboxed JavaScript program that drives shell, filesystem, HTTP, and every tool of any configured MCP server, returning only a small summary instead of raw JSON. This collapses dozens of advertised tool schemas into one tool, cutting per-request context by roughly 26× while keeping disabled upstream servers reachable.

Enables aggregating multiple MCP servers behind a single HTTP/SSE endpoint, with Code Mode to reduce token usage and support for OAuth and sandboxed execution.

Enables AI agents to control legacy web applications running in Microsoft Edge's IE Mode via MCP, using Selenium WebDriver and IEDriverServer for browser automation.

A lightweight Model Context Protocol (MCP) orchestrator designed for efficiency at scale. It features TOON compression (reducing token usage by 30-90%) and Lazy Loading, making it the ideal solution for complex, multi-tool agentic workflows.

Reliable Codex Desktop automation for long tasks with durable async operations, Plan Mode workflows, and retry-safe task submission.

MCP Compass is a discovery and recommendation service that assists AI assistants in finding and understanding Model Context Protocol servers through natural language queries.

A Model Context Protocol server that enables Claude Desktop and other MCP-compatible clients to leverage Google's Gemini AI models with features like thinking models, Google Search grounding, JSON mode, and vision support.

A build accelerator for AI coding assistants that scaffolds complete projects from short prompts using Smart Context Mode to reduce token usage.

A modular, extensible Model Context Protocol server framework designed for Claude Desktop that uses convention-based automatic module discovery to easily extend AI application functionality without modifying core code.

Adds OrgX MCP tools to a DeepSeek Harness profile and runs a workspace-bound OrgX gateway peer through Harness headless mode.

Routes model requests to Sol, Terra, or Luna via OpenClaw Gateway's Codex auth profile, with strict validation and no fallback.

Enables selecting the best AI model and reasoning effort for any task by analyzing task requirements and live pricing, balancing intelligence, speed, and cost. Provides model recommendations, comparisons, and routing status through MCP tools.

Cost-aware multi-LLM routing MCP server that automatically routes tasks to free models first with fallback to paid, using task difficulty classification.

Exposes configured language models as ordinary MCP tools, enabling a host agent to select a model, send explicit message lists, and receive normalized responses through provider-neutral OpenAI-compatible, Anthropic, and Gemini adapters.

An MCP server that aggregates multiple upstream MCP tools into a single 'codemode' tool for unified orchestration and execution. It enables agents to run generated code in an isolated sandbox to interact with various connected services through a single interface.

A transparent message ferry between Claude Desktop and Claude Code CLI, enabling task delegation with any MCP configuration without the bridge needing to know about specific MCPs.

Enables aggregating multiple local stdio MCP servers into a single Cloudflare Code Mode code tool, letting an agent orchestrate them through sandboxed codemode.<prefix>_<tool> calls without polluting conversation context.

Bridges Claude Code terminal sessions with Claude Chat by exposing session logs as tools, enabling seamless context transfer and two-way communication via a cooperative inbox and optional Google Drive sync.

Enables users to deploy a production-grade control plane for agents, providing a spec-compliant MCP server, scoped tool grants, failure-mode detection, and cost governance.

Labby is a Rust-based MCP gateway that connects and aggregates multiple upstream MCP servers, with authentication, Code Mode (JavaScript snippets), and an operator web UI.

Enables Codex to orchestrate multi-agent coding by routing tasks to local Claude Code workers via CCSwitch, managing cost and model selection for planning, execution, and review.

Enables clients to discover capabilities and compose tool calls with structured responses through a remote MCP endpoint running on Cloudflare Workers.

A professional AI agent system that provides 10+ specialized agents and 25+ MCP tools to support development workflows in Cursor IDE, with dual LLM mode support (built-in and DeepSeek API).

This MCP server enables AI agents to interact with recruitment platforms like BOSS直聘, 猎聘, and Moka through a Chrome extension via WebSocket. It provides tools to detect platforms, fetch candidate lists, and test extension connectivity.

Enables a Claude Desktop or Claude Code session to start, drive, and supervise interactive Claude Code CLI worker runs, including sending prompts, reading terminal output, waiting for completion, stopping runs, and managing settings and permissions.

Enables agents to plan premium-model tasks with estimated credit budgets, require explicit approval before execution, and inspect itemized usage receipts afterward.

Enables callers to start, monitor, follow up on, and cancel local Claude Agent SDK sessions with an explicit working directory, exact model ID, and instructions, while keeping reusable instruction sets in external presets. It exposes durable job IDs and progress or result reporting, with fail-closed permission handling and no built-in roles, UI, or scheduler.

Lets agents run a small JavaScript program in a sandboxed worker that composes typed Jev judgments — claim checking, text screening, best-item picking, label classification, passage comparison, and yes/no questions — in a single call, returning only schema-validated results. A companion search tool exposes each judgment's JSON input and output schemas.

Enables Agent-driven browsing in an independent Microsoft Edge profile with navigation, snapshots, iframe/DOM interaction, screenshot-coordinate clicks, hover, typing, dialog handling, and manual take/release control. It also exposes real-time JPEG preview and optional native sidebar integration in Hermes CN Desktop v0.9.0.

An MCP server that enables Claude to discover and delegate tasks to local Codex Skills and plugins, bridging Claude's natural language understanding with Codex's execution capabilities.

Enables coding agents to start, monitor, and control T3 Code / T3 Turbo threads locally via MCP.

Lets coding agents running in herdr panes discover one another, exchange messages, and delegate tasks, with idle agents prompted automatically when work arrives.

Enables AI coding providers to run structured multi-agent workflows with specs, tracked tasks, handoffs, health gates, and audited repair mode.

Lets any MCP-capable agent client join a shared local collaboration space with a common task board and mailbox, so agents can publish, claim, and track tasks with dependencies and message each other or the human. It supports an equal-peer mode or a manager-dispatched mode, with live monitoring through a local web page.

Enables zero-auth agent workflows for email OTP extraction, KV checkpoints, webhook bins, wake timers, and clean URL-to-Markdown reading.

Enables AI agents to route chat completion requests to task-appropriate models via LiteLLM/OpenRouter, track usage and budgets, and run side-by-side eval comparisons of models based on cost, latency, and response quality.