"Local and free services or resources" matching MCP servers:

An MCP server exposing 21 tools so Claude, ChatGPT and Cursor can search 15.5M US businesses and people, enrich rows through waterfalls, manage People and Companies databases, run AI agents and workflows, and watch signals. It runs on the user's own Cloudflare account with provider keys they control.

Enables delegating bounded execution loops—such as failing test suites, large CI logs, build/diagnose/fix/rerun cycles, and routine repo exploration—to OpenCode, which inspects and iterates on the raw output internally. Returns only a compact structured result to the primary model, with inspect and fix modes and an escalation flag when a primary-model decision is required.

Enables AI agents to delegate simple text subtasks such as summarising, translating, classifying, extracting, and reformatting to free web AIs through the user's own Edge/Chrome browser, returning only plain-text answers to save the main model's context and tokens.

Enables a Claude Code cloud session to run shell commands inside a chroot jail on your own computer and to call the MCP servers already installed there, with every request authenticated and relayed over a Cloudflare quick tunnel so no router port is opened and no SSH key or tunnel is ever handed to the cloud VM.

Exposes free-tier AI APIs as MCP tools for AI agents, enabling text generation, web search, embeddings, and vision analysis with automatic failover and capability routing.

A dedicated server for Oracle Cloud Infrastructure (OCI) Core Services that enables management of compute instances and network operations with LLM-friendly structured responses.

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.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

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.

Enables AI agents to access DDG's payable services including checkout/payment conformance, MCP/tool security audits, agent-discovery repair, and buyer-agent smoke probes, with structured payment challenges.

MCP server that enables AI agents to drive your real, logged-in browser via accessibility snapshots, with hardened credential brokering and local workflow memory.

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

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.

Exposes a multi-model council (panel-judge-synthesizer) and a build/check loop as MCP tools, enabling Claude Code or any MCP client to perform structured multi-model analysis and synthesis locally.

Enables Claude Code to offload bulk reading and first drafts to a local Ollama model on your GPU, and to draft weekly devlogs from merged pull requests.

Pluggable local agent capability hub that gives web-based DeepSeek local Agent capabilities (MCP/file operations/skills/desktop automation) and lets local agents reuse the same tools.

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.

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.