"Official MCP server that runs locally without an API key or paid plan" matching MCP servers:

Specialized MCP server for coding workflows with web search and image analysis tools.

An MCP server that enables users to manage Google's Jules AI coding agent sessions directly from MCP-compatible clients. It supports creating sessions, approving execution plans, and interacting with session activity to streamline autonomous coding workflows.

MCP server that automates the generation of production-grade async FastAPI services following Clean Architecture, with self-healing pytest-based verification and OpenAPI spec ingestion for rapid CRUD API development.

Context compiler for AI coding agents that indexes TypeScript codebases to extract and serve only the relevant symbols and files for a task, reducing token usage and search overhead.

A multi-agent system for code rules management using MCP, supporting search, generation, and architectural validation through specialized agents.

Lets an MCP client hand coding tasks, second-opinion reviews, and image-asset generation to the official OpenAI CLI agent running locally, returning final messages, session IDs, and saved files. Jobs run sandboxed with prompts over stdin, work asynchronously with polling, and expose a live model catalog without needing an API key.

Persistent memory for AI coding agents. Store coding standards, architecture decisions, and project context across sessions with AES-256 encryption.

Enables Codex Desktop or CLI to delegate tasks to an already running DeepSeek Harness Desktop over an authenticated local socket, reusing that Desktop's model configuration, Skills and allowed tools without a separate API key or runtime. Each delegated session runs in its own isolated directory or Git worktree so Codex can review results before integration.

Enables external MCP clients like Claude Desktop, Claude Code, Cursor and Zed to hand work to a local crew of AI agents that plan, write, check and fix code in a folder, while also acting as an MCP client that can use their tools. Runs locally with user-supplied keys, approval-gated commands, diffable and undoable runs.

AI-native open-source 2D game engine whose MCP server exposes every editor operation to coding agents as typed commands, so an agent can build, run, and verify a game inside the editor. It runs locally on macOS, Windows, and Linux with no cloud service or API key.

An interactive coding agent and MCP server that provides access to various AI models via the Tsinghua University lab proxy API. It enables users to inspect files and execute shell commands within their local directory using models like DeepSeek, GLM, and Qwen.

An MCP server giving coding agents context-window-aware code search and safe, atomic multi-file edits — built to cut token usage on large codebases without sacrificing correctness.

Enables AI coding agents to retrieve relevant execution context before a task, compare candidate paths, log outcomes, and search past experiences stored locally in SQLite. It lets agents reuse what worked on similar tasks and get live alerts when a run stagnates or repeats failures.

Enables delegating coding tasks to isolated Claude Code subprocesses billed against a GLM Coding Plan, with tools to delegate, await, continue, list, cancel, and inspect runs.

An MCP server that allows coding agents to search the Swift Package Index and retrieve GitHub READMEs without requiring an API key. It features comprehensive search filters for stars, platforms, and licenses, providing token-efficient responses optimized for LLM comprehension.

This server lets MCP clients delegate coding tasks to a locally installed Qwen Code CLI, enabling second opinions, parallel work, and clean separation from the main context.

AI code review against your team's own rules from your repository, before the pull request: two tools, review_changes and get_team_rules. Closed-source binary distributed via GitHub Releases; published in the official MCP Registry as dev.reviewgate/reviewgate.

MCP server that lets Claude Code, Codex or opencode hand coding work to cheaper models run by opencode.

A stdio MCP server that lets Claude Code delegate coding tasks to an OpenCode instance (optionally attached to an internal LLM gateway), with follow-up replies, status polling, output/diff retrieval, cancellation, and cleanup handled in a single session. It supports managed or attach modes, sandbox and approval policies, parallel fan-out delegations, and read-only review workflows.

An enhanced sequential thinking tool optimized for programming tasks that helps break down complex coding problems into structured, self-auditing thought steps with branching and revision capabilities.

An MCP server that lets AI coding assistants delegate work to Capy's cloud agents and wait for results, all within the editor.

Lets Claude Code delegate bounded coding tasks to a GLM model as a sub-agent through a single MCP tool that reads, writes, edits, lists directories, and runs shell commands inside a specified project folder. Each run returns only a short report with changed files and token usage, keeping GLM's intermediate tool traffic out of Claude's context.

Enables delegating bounded development tasks to a locally installed DSH harness and returns a structured handoff covering file writes, command exit codes, missing checks, blockers, and evidence.

A minimal local MCP server that lets Claude Desktop or Claude Code delegate coding tasks to Grok Build running headless as a subagent.

An MCP server that connects Claude Desktop to an interactive Claude Code session running in a tmux terminal.

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.

Provides AI coding agents a full abap2UI5 development loop—writing ABAP classes, validating views, deploying, and running apps headless with screenshots—all locally without an SAP system.

Delegates coding tasks to the locally installed DeepSeek Harness CLI, enabling MCP clients to run prompts through dsh and receive results with exit code and timing.

A secure MCP server that gives AI coding assistants direct access to the shadcn/ui registry, enabling fetching, installing, and wiring up components without switching context.

Enables any LLM to drive your local Codex CLI in a sandboxed workspace, running coding tasks and generating images without needing an API key.