"Keynote MCP (Model Context Protocol) Server" matching MCP servers:

A production-ready MCP server template that connects LLMs and AI agents to external data, tools, and services with built-in OAuth 2.1 authentication, Redis-backed session management, and a modular tools engine.

MCP server that pings 130+ free coding LLM models across 17 providers in real-time, ranks them by latency, and helps AI agents pick the fastest available model.

Discovers local model runtimes such as Ollama, LM Studio, and LocalAI, and exposes their endpoint metadata to MCP clients like Copilot.

Enables AI coding agents to offload large file reads and boilerplate code generation to cheaper or local worker models through MCP, reducing token consumption and keeping context clean.

Enables language models to receive external randomness so the same prompt can produce different answers while still following the user's request.

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

Routes subagent tasks across Claude and OpenAI lanes by task kind and quota state, deciding whether to spawn a single model, run a duel of both vendors, or run both and ship the merge. It records duels with attested proof-of-run session ids, grades sides blind with one judge per vendor, and tracks per-kind standings and lane pacing.

An MCP server that seats multiple LLMs as a council, letting your assistant query them in parallel or in sequence, relay answers for cross-critique, and merge conclusions within one conversation.

Routes questions to multiple AI models (local and cloud) and synthesizes their answers in individual, categorized, or deconflicted modes.

Trust, identity, and reputation infrastructure for AI agents. Register agents with W3C DID (Ed25519), check EigenTrust reputation scores, submit peer attestations, search agents by capability, and verify IPFS-anchored audit trails. 11 tools.

Local MCP server that lets Claude Code delegate bounded, read-only tasks to external AI models (Codex, Grok, local OpenAI-compatible servers) via CLIProxyAPI.

Enables MCP-compatible clients to call TokenHub's image generation and editing APIs through natural language, supporting text-to-image, image-to-image, and configurable model and endpoint settings.

Provides up-to-date AI model names and pricing from models.dev, solving model hallucination by fetching recently released models.

Exposes product-style completion tools (OpenAI chat-completions-shaped and Anthropic messages-shaped) that are fulfilled by sampling the host agent's own LLM over MCP, so no model API keys are ever needed. Also offers a model listing endpoint aliasing the host's model.

Enables users to scan Hugging Face for Apple-MLX models, estimate memory fit and decode speed for their Mac, and get ranked recommendations for a use case, with all agent work running locally.

Enables agents to trace any Hugging Face model's ancestry and descendants, find the most finetuned base models, and explore whole model families. It exposes tools for lineage, children, leaderboards, family views, and model search, answering from nightly-rebuilt index data.

Enables running a project's agent definitions from .github/agents/ against a model the user explicitly names, instead of inheriting whatever model the IDE session happens to use. It reads the agent file as the system prompt, executes a bounded tool loop against a configurable inference gateway, enforces a tiered model allow-list, and reports which model actually ran.

Enables bounded, local coding tasks to be delegated to OpenAI-compatible models with explicit working directory and read/write paths, pre-application unified-diff validation, and optional verification commands. It routes tasks by complexity and risk, while blocking sensitive changes such as auth, payment, secrets, migrations, database, deployment, or production environments.

Enables a Codex orchestrator to obtain a deterministic, local recommendation for a model and reasoning effort for a delegated coding task, without inference calls or API keys.

Provides AI agents with a toolset to query model inventories, trace dependencies, and analyze the impact of changes across machine learning models and data pipelines.

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.

Provides context management, task classification, and routing tools for small models (1B-12B) in production agentic workflows.

Enables users to route Codex desktop chats to subscription models or their own OpenAI-compatible providers by adding Base URLs, API keys, and model catalogs from an in-app settings panel. Keeps keys DPAPI-encrypted, supports Responses and Chat Completions with streaming and tool calls, and needs no separate configuration app or Windows autostart.

Recommends the right Claude model for a task — Haiku, Sonnet, Opus or Fable — at the start of work and reviews the choice afterward to suggest a lighter or stronger option, running locally with no API calls or token cost.

Enables AI agents to list, compare, and estimate exact costs for image, video, audio, and 3D generation models, including per-image, per-second, and per-run pricing with recoverable errors.

Configurable MCP server that lets you define LLM-powered tools via JSON, enabling easy integration of multiple models (GPT, Gemini, Claude, etc.) as MCP tools without writing Python code.

Enables AI assistants to see which model IDs each provider's API has started listing since the last check, and to list the models a given provider currently serves with optional substring filtering, all without spending tokens.

Enables inspecting ONNX models, probing the deployment environment, and benchmarking inference latency and FPS either locally or on remote SSH targets such as Linux workstations and Jetson devices. Benchmark results are validated against FPS, P95 latency and model-size constraints to produce PASS/FAIL deployment gates.

Enables local-first management of OpenCode model routing, letting users discover, enable, and assign orchestrator/specialist roles to models while safely connecting the chosen policy to OpenCode via a local MCP bridge.

One MCP server that routes to 12+ AI providers for text, image, and video generation, with smart task delegation, web search, and model comparison—all from the terminal.