"A server or tool for local-only resources or information" matching MCP servers:

MCP router that fronts your other MCP servers behind a few small generic tools, so their tool definitions stay out of the context window and are discovered on demand.

Enables centralized proxy and orchestration of MCP servers, providing unified tool discovery, authentication, and secure request routing. It adds a human-in-the-loop approval gate for high-risk actions and audit logging.

MCP server that routes natural language requests to structured tool calls using a LoRA-tuned small language model, with built-in validation, retry, and fallback recovery.

Enables AI coding agents to request a second opinion from a different frontier model via a single tool call, with PII scrubbed before transit, live web search, and support for Claude, ChatGPT, Cursor, and Gemini.

Enables agents to send only the handful of tool definitions relevant to each question, ranking a large catalog by keywords and optional embeddings to cut context cost and wrong-tool picks. It can also run in front of any mcpServers config as a proxy that exposes just search_tools and call_tool instead of the whole catalog.

Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.

Enables AI agents to request an independent second opinion from a different frontier model, with PII scrubbing before transit, live web search grounding, caching, and multi-provider failover.

Enables agents to search across the pooled tools of many connected MCP servers and invoke them through a single endpoint, returning only the handful of tools relevant to each request. Filters by the caller's permissions before ranking, so agents never see or plan around tools their user is not allowed to use.

A configurable MCP gateway that runs multiple Streamable HTTP MCP servers and exposes all their tools through a single endpoint, enabling tool aggregation and routing for MCP clients.

Enables delegating mechanical or high-volume subtasks to a local LLM through an MCP tool, letting the assistant query the local model without using its own output tokens for content.

A framework for building hot-loadable MCP tools that feature conversational negotiation, graduated permissions, and zero-downtime updates. It enables persistent state continuity across server restarts and provides a hypothetical evaluation system for tool actions.

Enables Claude to fetch web pages from the user's own local network connection instead of AI datacenter IPs, including optional authenticated sessions, with verdicts for bot challenges, login walls, and other failures.

Evaluates task suitability for local models before cloud API calls, routing to Ollama or similar to reduce costs.

An MCP proxy that embeds tool definitions and returns only the top-k semantically relevant tools per query, reducing context usage and routing calls to upstream MCP servers.

A thin MCP server that delegates lightweight tasks from Claude Code or any MCP-compatible client to local or cloud LLMs via LiteLLM, supporting models like Ollama and cloud APIs as subagents.

A local MCP server that lets Claude Code orchestrate Codex CLI and OpenCode CLI as sub-agents with strict security, concurrency, and output limits.

Central registry for AI tools with vector search and knowledge graph, enabling intelligent tool discovery, chaining, and execution via MCP.

Graph-based tool retrieval for LLM agents. Builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy from 12% to 82% with 79% fewer tokens. Also works as an MCP Proxy to aggregate multiple servers behind 3 meta-tools.

Enables AI agent hosts to exchange durable, local sender/receiver messages through a SQLite mailbox exposed as MCP tools (connect, send, receive, reply, ack, status, disconnect), so a coordinator can dispatch commands and an executor can return results without model polling while idle. A configured host wake adapter is still required to turn an incoming event into an Agent turn.

Enables a cloud orchestrator to query a local Ollama model over Tailscale or a LAN as a side-channel for drafts, summaries, and other helper output, with tools to list available models and to redact text. Answers leaving the server are passed through output-only DLP that masks card numbers, IBANs, emails, phone numbers, API keys, and similar secrets before they reach the cloud.

A single MCP server that provides dynamic access to thousands of APIs through discovery and proxy, eliminating the need to install and configure multiple separate MCP servers.

Enables coding agents like Claude Code and Codex to offload boilerplate generation, summarization, and other bounded text tasks to local or cheap cloud LLMs, keeping the frontier agent in charge of judgment and code edits.

Enables Claude Code to offload mechanical development work—tests, git operations, pull requests, summaries, project search, code review, and browser or screen control—to local Ollama models with optional free cloud fallbacks. It returns concise results to reduce token usage while keeping execution on the user's own machine.

Enables ZCode to control a real Chrome browser, including tabs, navigation, page content, clicks, form filling, keyboard input, scrolling, screenshots, and JavaScript evaluation through a local MCP bridge.

Enables AI coding agents to route tasks to local GPU models via a dynamic heuristic classifier, tracking real-time token dollar savings.

Enables declaring a catalog of tools for LLMs, filtering them by role, validating arguments, guarding sensitive calls with server-side confirmations, and recording an audit log.

Enables OpenAI-compatible clients to access external tools, APIs, repositories, and data sources through MCP with allowlisting, approval, and argument validation, deployable as a FastAPI service or Python library.

A persistent local MCP relay that caches tool discovery, keeps upstream servers warm, and allows agents to hot-add or refresh MCP servers through management tools.

Routes external MCP tools behind a small on-demand discovery interface for Codex agents, using Jev to select relevant tools and providing fallback to the full inventory when confidence is low.

Enables locally configured MCP servers to be called over stdio and mixed with xAI server-side tools, without relying on hosted xAI MCP.