"React Router" matching MCP servers:

A router MCP server that provides access to 62 MCPs behind a single connection, with load balancing, health checking, and EU AI Act compliance.

Aggregates multiple MCP servers behind a single local endpoint, letting LLM clients connect to one router that exposes a unified set of tools, resources, and prompts.

Routed is a universal local router for Agent Skills across AI coding environments.

A transparent, user-owned model router and orchestration control plane that enables AI workflow orchestration via an MCP server, with supervisor-based task decomposition and cross-provider routing.

Enables a production-grade MCP-native router and multi-agent control plane, letting agents plan tasks, route tool calls to the right MCP servers, stream every step, and persist results in memory.

Aggregates and routes multiple MCP servers with intelligent tool recommendation and batch parallel execution, enabling unified access and efficient tool usage.

Enables AI agents to convert a natural-language task into ranked x402 and MCP tools from a merged 16k+ catalog in a single fast pass without an LLM call, with pay-per-call USDC on Base and a free tier.

Routes SKILL.md libraries to any MCP client, enabling task matching and skill loading with embedding-based scoring, keyword fallback, and context-window discipline.

This MCP server enables LLM hosts to plan large tasks and delegate subtasks to specialized local CLI agents, such as Codex and Claude Code, using tools like delegate_task and get_agent_roster.

An MCP server that integrates a ReAct agent with built-in tools (calculator, text, unit conversion, etc.) and the AnySearch search service, enabling autonomous multi-step task execution.

Enables orchestrator agents to route coding tasks to native CLI worker agents via MCP, providing tools for agent discovery, task submission, waiting, inspection, and cancellation.

Enables AI agents to choose the lowest-carbon cloud region for a workload, with tools for ranking regions by carbon intensity and latency, and for finding optimal start times to reduce emissions.

MCP server for HyperRoute, a router that recommends and executes the best external tool for AI agent tasks, with server-side key management and outcome feedback.

Cost-aware, multimodal OpenCode task router and sub-agent MCP server for Claude Code, providing tools for delegation, status, review, revision, abort, models, and usage.

Enables agents to connect through a single gateway that has a decision model pick which MCP tools and playbooks are relevant to each request, so the LLM only sees the few schemas it needs, and to then invoke those tools on the underlying servers. This cuts tool-selection cost and prompt size dramatically when many MCP servers are connected.

Enables AI coding agents to make fast, zero-output-token decisions by evaluating context, diffs, logs, or options through the OpenRouter Decisions API using TypeSafe Jev, returning calibrated probabilities for binary, categorical, or scoring questions.

Enables Claude Code and Codex Herdr workers to get local, advisory routing decisions by selecting a client, model, effort tier, and worker launch instruction for a stage, and by ranking a short list of bounded next actions. Decisions come from a selectable local backend (Laya or a local Kev model), returning confidence and uncertainty without executing anything or granting permissions.

MCP server for humanaway, a social network for AI agents. Tools: register agents, create posts, read the feed, reply to posts, react with emoji, and sign the guestbook.

Routes your AI tasks to the best available model across 20+ providers — automatically selecting based on task type, budget, and subscription pressure. Supports text, image, video, and audio with built-in cost optimization and fallback chains.

Enables agents and users to route prompts to the cheapest reachable free or paid model across providers, compare costs, list filtered models, and receive fallback chains and cached routing results without calling any LLM API.