MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
🔧 MCP server for refactoring and deobfuscating
-
@tac0de/refactoring-mcpgithub.com/tac0de/refactoring-mcpupdated this year
Refactoring MCP server that exposes prompt generation via @modelcontextprotocol/sdk tools.
npm ISC -
Semantic Java refactoring for AI coding agents. Rename, move, extract, inline, pull up/push down and more — backed by Eclipse JDT, the same engine as IntelliJ and Eclipse. The IDE your coding agent never had.
Apache-2.0 ★ 3 -
FSharp refactoring tool - The tool clarifies the (agent-generated or old) code's intent, reduces non-alphanumeric noise, and uses built-in .NET libraries more efficiently.
Unlicense ★ 16 -
codeguardian-studiogithub.com/phuongrealmax/code-guardianupdated this year
AI-powered code refactor engine for large repositories, built on Claude Code + MCP.
npm MIT -
AI Agent skill & MCP server for SOLID compliance, code smells, refactoring techniques, and GoF design patterns with bundled offline Refactoring Guru knowledge base.
-
Compiler-accurate Java analysis & refactoring for AI agents — JDT-backed MCP server: parity-gated reversible refactoring, whole-workspace scope, grounded memory, agent enforcement. No Eclipse required.
AGPL-3.0 ★ 1 -
aibolit-mcp-servergithub.com/cqfn/aibolit-mcp-serverupdated this year
MCP Server for Aibolit Java Static Analyzer: Helping Your AI Agent Identify Hotspots for Refactoring
MIT ★ 27 -
TypeScript CLI for markdown file operations with intelligent link refactoring
npm MIT -
Roslyn-powered C# MCP server for AI agents. Enables semantic code analysis, precise diagnostics, and safe refactoring without full rebuilds.
MIT ★ 8 -
MCP server for semantic Java code analysis, built on Eclipse JDT. Provides 63 tools for navigation, refactoring, and code intelligence.
npm MIT -
code-guardiangithub.com/phuongrealmax/code-guardianupdated this year
Code Guardian Studio – AI-powered code refactor engine for large repositories, built on Claude Code + MCP.
★ 9 -
repforgithub.com/hegner123/repforupdated this year
MCP server tool for safe, exact-match string replacement across files. Designed for AI-driven refactoring workflows with compact JSON output.
MIT -
brain-devgithub.com/mcp-tool-shop-org/brain-devupdated this year
MCP server for AI-powered code analysis — test generation, security audits, coverage analysis, and refactoring suggestions
pypi MIT -
AI-assisted git history refactoring via MCP — safe interactive rebase, fixup commits, and amendments without leaving your repo in a broken state
MIT -
importsgithub.com/hegner123/importsupdated this year
Dependency/import mapper MCP tool. Scans directories for import statements across 11 languages and outputs structured JSON for blast radius analysis before refactoring.
MIT -
mcp-readeditgithub.com/abnersajr/mcp-readeditupdated this year
MCP server that combines Read+Edit operations into single tool calls — 80-95% fewer tool calls for multi-file refactoring
MIT ★ 3 -
Roslyn MCP server for C#/.NET AI coding agents. Compiler-aware analysis, code fixes, refactoring and safe, reviewable source changes.
MIT ★ 2 -
mcp-readeditgithub.com/abnersajr/mcp-readeditupdated this year
MCP server that combines Read+Edit operations into single tool calls — 80-95% fewer tool calls for multi-file refactoring
npm MIT -
MCP server providing semantic Java code analysis for AI agents. Built on Eclipse JDT with tools for navigation, refactoring, search, and metrics.
npm MIT ★ 48 -
AI-agent-driven refactoring platform. MCP server + class diagram over C# (Roslyn) + C++/CLI. Fowler catalog + smell detection. PolyForm NC + Pro.
NOASSERTION -
Lock a notebook's outputs with a test, catch its hidden state, then let your agent refactor it into a pipeline that provably gives the same results.
MIT -
Atlas IDE Expert – a RAD Studio IDE plugin with its own language server for smarter code completion, navigation and refactoring in Object Pascal projects
MIT ★ 6 -
⚡ Semantic Coding Agent IDE Toolkit & Live Documentation MCP Server — Symbol-level AST navigation, surgical code refactoring & live API docs for Claude Code, Cursor, VS Code, Codex & Antigravity.
MIT ★ 1 -
150-tool MCP server for codebase analysis — dependency graphs, architecture layers, security scanning, refactor plans, git history, and more. Works with GitHub and GitLab repos (cloud + self-hosted) and local directories.
npm Elastic-2.0 -
A production-ready knowledge graph system for software engineering that connects design patterns, refactoring techniques, and software laws through semantic relationships. Built for AI agents first — integrate software engineering expertise directly into Claude Code, Cursor, and other MCP-compatible tools.
Apache-2.0 ★ 6 -
Change guard and refactoring engine for coding agents: catches broken callers, schema and endpoint gaps after an edit, and does rename, change-signature and move-symbol across 14 languages - local code graph, over MCP, CLI and a web UI
pypi FSL-1.1-ALv2 -
Rust source file summaries and refactoring
Apache-2.0 -
sylvangithub.com/darki73/sylvanupdated this year
Code intelligence MCP server for token-efficient code retrieval, analysis, and refactoring
pypi Custom Non-Commercial -
agentic-dotnetgithub.com/Hookyns/agentic-dotnetupdated this year
Roslyn-powered MCP server that exposes diagnostics, navigation, and refactoring tools for a .NET solution.
AGPL-3.0 ★ 4 -
An MCP for AI Agents to automate code refactoring, and android app testing
Apache-2.0 -
MCP server that lets your coding agent see the squiggles — LSP diagnostics, navigation, refactoring, and each server's custom superpowers
MIT ★ 7 -
MCP server for persistent SSH sessions but refactored version.
MIT ★ 1 -
MCP server that lets your coding agent see the squiggles — LSP diagnostics, navigation, refactoring, and server-specific extras
npm MIT -
Roslyn-powered MCP server for C# diagnostics, code navigation, and refactoring
AGPL-3.0 ★ 2 -
clawnavgithub.com/hashi-ai-dev/clawnavupdated this year
OpenClaw-native MCP server for semantic file search, project awareness, and intelligent refactoring — runs entirely offline
npm MIT -
agentic-bookmarksgithub.com/super-mega-lab/agentic-bookmarksupdated this year
Durable code bookmarks with self-healing anchors, so you and your agents can create local bookmarks or Git-friendly shared groups that survive refactors and code movement.
NOASSERTION ★ 1 -
@collegue/mcpupdated this year
Un assistant de développement intelligent et serveur MCP fournissant des outils d'analyse de code, refactoring, documentation, sécurité et bien plus.
npm ISC -
MCP (Model Context Protocol) server that enables AI assistants to interact with Storybook design systems. Extract component HTML, analyze styles, and help with design system adoption and refactoring.
MIT ★ 73 -
zigarsgithub.com/oly-wan-kenobi/zigarsupdated this year
Deterministic MCP server for Zig: structured compiler diagnostics, ZLS code intelligence, and preview-first refactors for AI coding agents
MIT -
Auditable code intelligence for AI agents - map dependencies, predict change impact, select the right tests, and verify refactors before they ship.
AGPL-3.0 ★ 32 -
@myelixlabs/synapse-mcpgithub.com/myelixlabs/synapse-mcpupdated this year
Cuts AI token costs, eliminates hallucinated refactors and answers in <2ms — AST code-knowledge graph for Cursor, Claude Code, Windsurf, Warp, Continue & Zed. Runs fully local.
npm MIT -
Remote code intelligence and build server for AI coding agents via MCP: semantic navigation, safe refactoring, builds and tests on remote nodes.
Apache-2.0 ★ 7 -
Bring Anthropic's MCP to Lazarus IDE. Let AI assistants natively code, refactor, debug, and design forms in Object Pascal.
BSD-3-Clause ★ 9 -
🧠 Python MCP Server for AST Codebase Intelligence, Symbol Extraction, Cyclomatic Complexity & Refactoring Analysis — compatible with Cursor, Claude Code, Windsurf & AI Agents.
MIT ★ 1 -
Quiet MCP executor for Claude Code and Codex. Offload edits, tests, refactors, and commits to cheaper local or flat-rate models.
MIT ★ 4 -
clean-ml-engineeringgithub.com/GeorgiosLymperis/clean-ml-engineeringupdated this year
Jupyter notebooks applying clean code and design patterns to ML engineering. Each notebook shows an anti-pattern and its refactored solution. Ships as an MCP server so Claude can reference the exercises while you code.
-
An MCP server that gives AI agents the code navigation and refactorings of an IDE in ten languages, and states the evidence behind every answer
MIT ★ 3 -
MCP server that gives AI agents ~90 tools to build and govern real Elementor sites: read/build/refactor pages, HTML→Elementor conversion, design system, Pro widgets — every write validated server-side, backed up and reversible.
npm MIT -
mcp-dev-assistantgithub.com/ghoshp83/mcp-dev-assistantupdated this year
Developer-tooling agent exposed as an MCP server with diff review, prompt optimisation, and refactor proposals, powered by a LangGraph reflection loop and a LangMem-style persistent feedback store.
MIT -
anchor-dbgithub.com/jolovicdev/anchor-dbupdated this year
MCP server that gives AI coding agents persistent memory of your codebase: notes pinned to files, spans, and symbols that survive refactors. Works with Claude Code, Cursor, and any MCP host.
MIT -
NTS_MCP_FSgithub.com/Nefrols/NTS_MCP_FSupdated this year
Transactional File System server for Model Context Protocol (MCP). Enterprise-grade tools for AI agents: atomic edits, undo/redo, code navigation, refactoring, git integration. Docker ready.
Apache-2.0 ★ 13 -
Universal Model Context Protocol (MCP) gateway for autonomous AI coding agents. Delegate pair-programming, refactoring, and code analysis to Claude Code, Antigravity, Codex, and Cursor with connection-scoped memory and zero tool bloat.
MIT -
Voice-operated Software Carbon Intelligence Engine powered by Amazon Alexa+, Amazon Bedrock AI, and AWS. Measures real hardware energy, calculates ISO/IEC 21031 SCI scores, and auto-fixes energy waste with verified AI bedrock refactoring.
Apache-2.0 -
Roslyn-based MCP server giving AI agents deep semantic understanding of .NET/C# codebases — 67 tools for navigation, call graphs, diagnostics & code fixes, safe refactoring, code-quality auditing, test intelligence, DI graphs, and IL/external-assembly inspection.
npm MIT ★ 74 -
MCP server for 1C/BSL code analysis: project-wide diagnostics + per-method cyclomatic/cognitive complexity with refactor triage. Streamable HTTP, bearer auth, built on onec-hbk-bsl (no Java). RU: MCP-сервер для 1С/BSL — диагностика по проекту и сложность по методам, без Java.
★ 4 -
🧠 Save 70–95% tokens in Claude Code, Cursor, Windsurf & Cline. Local Tree-sitter code graph MCP server: surgical edit context instead of full-file reads, refactor safety checks, and a hook that blocks large file reads. Reduce token usage & cost, zero LLM indexing.
MIT ★ 4 -
mcp-subconductorgithub.com/PaulBenchea/mcp-subconductorupdated this year
Subconductor is an MCP server that acts as a Persistent State Machine for AI agents. It prevents "context drift" during long refactors by externalizing the task list into a physical manifest. It enables non-linear execution, allowing agents to handle dependencies dynamically while maintaining a transparent, resumable audit trail.
Apache-2.0 ★ 2 -
SAP ABAP MCPgithub.com/Coaspe/sap-abap-mcpno update data
SAP ABAP MCP is a local-first Model Context Protocol server that enables AI coding agents to develop, test, analyze, and operate SAP ABAP systems through the official ABAP Development Tools HTTP services. It supports repository search and source editing, structured DDIC workflows, enhancement inspection, paged package navigation, source-backed object creation, semantic services, activation, ABAP Unit and ATC, transports, abapGit, RAP generation, debugging, bounded class and executable-program profiling, runtime dumps, traces and feeds, cross-system comparison, dependency analysis, guarded refactoring, and an opt-in same-origin Screen/GUI Status bridge. Curated compact, development, and assurance presets reduce tool-schema token use without removing capabilities from the default surface. The default local stdio mode can be extended with governed self-hosted Streamable HTTP, API-key roles, OIDC/JWT authentication, request-scoped SAP bearer forwarding, per-session isolation, rate limits, structured audit logs, or a side-effect-free embeddable Node.js API. It also includes browser OAuth Authorization Code with PKCE, a read-only transport assurance CLI and GitHub Action, BTP service-key profile import, and live-SAP evidence tooling. SAP profiles and credentials remain on the user's computer, with passwords and OAuth credentials protected by macOS Keychain or Windows DPAPI. SAP-dependent capabilities are validated against the user's own SAP release, configuration, and authorizations.
smithery -
agentedgithub.com/frane/agentedno update data
A text editor for LLMs, not humans. Take ed, the line editor that nobody has voluntarily used since about 1975, and rebuild it for an environment where the typing user is a language model. Short verbs, line addresses, no modes, no TUI. What an editor optimises for changes when the user is the model: round trips per task, tokens per command, an editing buffer with a long memory, and an undo tree that remembers the branches the agent abandoned, because that's often where the interesting work was. ## Features - **Fewer round trips.** Read-before-Edit is unnecessary; on conflict the response carries the new content so you reconcile in one call instead of pre-reading every time. - **Branching undo.** Walked-back work stays addressable instead of being thrown away when you pick a different path. - **Three-way merge.** Concurrent agents get a structured conflict response instead of a silent overwrite. - **Atomic batches.** Multi-file refactors run all-or-nothing instead of leaving half-applied state on failure. - **Cross-file moves and regex replace as primitives.** Operations the built-in tools can't express cleanly become single calls. - **Drift detection.** External edits to an open file are folded into the tree instead of being clobbered by the next write. - **Inline diagnostics.** Type errors and lint findings surface on save, not at the next build many edits later. - **Cross-session memory.** Per-file notes persist between sessions and surface inline on the next open. - **Audit log.** Every operation recorded with actor and timestamp, so two agents in one workspace can't argue about who moved the head. ## Multi-workspace (v0.4.0) One MCP server registration handles every project you mention. Tool calls route to the workspace owning the absolute path you pass; each project gets its own SQLite, its own undo tree, its own LSP daemon — lazily spawned on first touch. Desktop hosts (Claude Desktop, Codex Desktop, Cursor) install the server once globally and use it across projects without per-project config. ## Install `ae` must be installed locally; this MCP bundle registers `ae serve` as a stdio server. ```sh brew tap frane/tap && brew install agented # or curl -sSL https://raw.githubusercontent.com/frane/agented/master/install.sh | sh ``` Pure Go, single static binary, Apache 2.0. Source: https://github.com/frane/agented
smithery