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.
-
Go MCP server for codebase analysis using tree-sitter, with AST inspection, symbol extraction, and structural search.
MIT -
MCP server for code structure analysis across 20+ languages. Tree-sitter powered. Works with Claude Code and Claude Desktop.
MIT ★ 3 -
Save 6-8× tokens on AI code reviews. Builds a structural call graph via Tree-sitter + MCP. Works with Claude, Kimi, Gemini, ChatGPT, Cursor, Windsurf — any AI assistant.
MIT ★ 2 -
Zero-LLM structural code retrieval for AI coding agents — tree-sitter index, BM25+dense+structural fusion, served over MCP.
MIT ★ 7 -
aptu-coder: MCP server for AST analysis, call graphs, and code structure (tree-sitter)
Apache-2.0 ★ 7 -
iflow-mcp_angrysky56-ast-mcp-servergithub.com/angrysky56/ast-mcp-serverupdated this year
An MCP server that provides code structure and semantic analysis capabilities through Abstract Syntax Trees (AST) and Abstract Semantic Graphs (ASG)
pypi MIT License -
MCP server that gives AI coding agents persistent, structured repository knowledge — incremental tree-sitter indexing, dependency & call graphs, semantic summaries, hash-driven cache. C++23.
MIT -
nanocontextgithub.com/demirmusa/nanocontextupdated this year
Lightweight code indexing and semantic search engine that helps AI agents write code faster while using fewer tokens. Parses codebases with Tree-sitter AST to generate structured headers, with optional LLM insights and vector embeddings. Integrates via MCP server or CLI. Supports TypeScript, JavaScript, C#
NOASSERTION -
AST-targeted code editing MCP server with 28 surgical tools for structural edits across 11 languages (Python, JS, TS, C, C++, Ruby, Go, Java, JSON, YAML, TOML), built on tree-sitter — replaces brittle search/replace with byte-correct edits keyed by symbol names.
MIT -
Code structure for coding agents: classes, functions, callers and headings with line numbers, as an MCP server and the sct shell command. 20+ languages, tree-sitter, no index.
pypi MIT -
Tree-structured session guide & checklist as an MCP server
Apache-2.0 -
Structure-aware tools for AI agents. Tree-sitter code editing, web page navigation, search. No daemon, no JSON, just stdin.
MIT ★ 5 -
deep-reasoning-mcpgithub.com/mauriziomocci/deep-reasoning-mcpupdated this year
MCP server for recursive deep reasoning — structured what-if analysis trees for Claude Code
MIT -
memos-enginegithub.com/TAskMAster339/memos-engineupdated this year
Memos builds a structural index (symbols, call edges, imports) of a codebase using tree-sitter and stores it in SQLite. It is the first layer of a larger Memory OS for AI coding agents — instead of grep-ing text, agents query structure (definitions, callers, callees).
MIT ★ 2 -
mcp-server-codetreegithub.com/thinkyminer/codetreeupdated this year
MCP server with 23 tools for structured code understanding via tree-sitter
pypi MIT -
MCP server with 23 tools for structured code understanding via tree-sitter. 10 languages. 999 tests. One-command install.
MIT ★ 30 -
codesteward-graphgithub.com/Codesteward/codesteward-graphupdated this year
Structural code graph server for AI agents — parses repositories into a Neo4j graph via tree-sitter and exposes it as an MCP tool interface with lexical, referential, semantic, and dependency queries.
Apache-2.0 ★ 1 -
Run a project's tests and get small structured results over MCP: pytest, unittest, jest, vitest. Failures with trimmed tracebacks, rerun-failed, flaky detection, hard timeout that kills the whole process tree.
MIT -
Structured code retrieval for AI agents — index once with tree-sitter, query symbols precisely via MCP. Cut code-reading token costs by up to 99%.
NOASSERTION ★ 4 -
Structural code-intelligence engine in Zig — tree-sitter across 40+ languages, trigram and inverted indexes, dependency graph, exposed as an MCP server
npm MIT ★ 3 -
Vectorless, structure-first retrieval over large Markdown libraries for agents: section trees, mixed Chinese/English BM25 in SQLite, five read-only tools (AI SDK, MCP) and a built-in evidence loop
npm MIT -
ui-to-hierarchygithub.com/dovanhuy2298/ui-to-hierarchyupdated this year
MCP (Model Context Protocol) server that parses a Next.js App Router project and returns its UI component hierarchy as structured output (markdown tree + JSON), so AI coding agents can ground image/description-based UI edits in exact file/component locations.
MIT -
Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.
MIT ★ 149 -
Alcove is an MCP server that gives AI coding agents on-demand access to your private project docs — BM25 + vector hybrid search for precision retrieval, tree-sitter code indexing so agents understand your codebase structure, and policy enforcement for doc consistency.
Apache-2.0 ★ 16 -
ui-hierarchy-mcpgithub.com/dovanhuy2298/ui-to-hierarchyupdated this year
MCP server that returns a Next.js App Router project's UI component hierarchy as a structured tree (markdown + JSON) so AI coding agents can ground image/description-based UI edits in exact file/component locations.
npm MIT -
rhizophoragithub.com/punic-pillars/rhizophoraupdated this year
MCP server for React Native spatial integrity and layout audit. Provides Ground Truth for your component tree by detecting margin pollution, token deviations, bridge crossings, and render traps. 15 tools for structural analysis, layout auditing, performan
npm MIT -
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 -
SSH MCP Servergithub.com/hypnosis/ssh-mcp-serverno update data
**An SSH MCP server — a multitool that saves you and your AI agent time and tokens on debugging, development and server maintenance.** Run commands, move files, read logs and audit machines over SSH: a cloud VPS, a bare-metal box, or the BusyBox router in your closet. It uses the OpenSSH client already on your machine — your keys, your `~/.ssh/config`, your jump hosts, your agent forwarding. Nothing bundled, nothing to compile, no native bindings. **18 tools:** run commands and detach long ones as background jobs, move files and whole trees with sha256 verification, search and tail logs, snapshot load and disk, audit a machine in one round trip, check TLS certificates, inspect services. **Built for agents, not for humans.** Answers come back structured, a truncated result is reported as truncated instead of passing for a complete one, and destructive commands are stopped before they run. Works with Claude Code, Codex CLI, opencode, Gemini CLI, Qwen Code, Hermes and any MCP client.
smithery -
Contextualno update data
## Contextual — Persistent Memory for AI Coding Agents AI coding agents forget everything the moment your session ends. **Contextual** fixes that by giving any MCP-capable AI client — for developers who use multiple AI coding tools at once — a real, persistent memory of your codebase: not just what the code says, but what changed and why. It's a **local-first MCP server**: your code, your index, and every query stay on your machine. The only network call is a lightweight, infrequent license check — no code, ever, leaves your device. Under the hood, Contextual builds a real understanding of your repository, not a text-similarity guess: - **Structural search** — tree-sitter AST parsing + call-graph resolution, so agents reason about how your code actually connects. - **Bitemporal history** — tracks not just when your code changed, but when the AI learned about it. Ask "did this bug fix happen before or after the agent's understanding of this function?" and get a real answer. - **Git-aware retrieval** — temporal, history-grounded context instead of a stale snapshot. - **Fast, self-contained** — index a 50k-line repository in about 5 minutes, then query it in ~94ms median, from a single ~0.8GB install. This extension connects Claude Desktop (or any MCP-capable client) to a Contextual installation already set up and activated on your machine — it does not provision Contextual from scratch.
smithery -
Map and manage human skills with a structured system designed to track learning and development alongside AI capabilities.
-
MCP code-intelligence server for AI agents — a more complete and more correct call graph with classified, cross-file edges. 8 facade MCP tools, 13 curated skills, structured JSON output, 100% local.
pypi MIT -
Context governor and between-commit activity surface for coding agents
npm Apache-2.0 -
memos-enginegithub.com/taskmaster339/memos-engineupdated this year
Memory OS for AI coding agents — structural code index with episodic memory
pypi MIT -
Zero-LLM structural code retrieval for AI coding agents, served over MCP
pypi MIT -
cctx-mcpgithub.com/nikondrat/cctx-mcpupdated this year
MCP server for AI agents — structured code analysis that cuts token usage by 87%
pypi MIT -
MCP server for semantic code search and codebase analysis — AST parsing, Tree-sitter, embeddings and vector search for AI assistants and LLMs
MIT ★ 3 -
ariadne-mcpgithub.com/madan2248c/ariadneupdated this year
MCP server that gives coding agents a structural map of a codebase
npm MIT -
Local code-context engine for AI coding agents: structural answers within a token budget.
Apache-2.0 ★ 4 -
pi-shazamgithub.com/gjczone/pi-shazamupdated this year
Pi coding agent native codebase awareness toolkit — 7 structural analysis tools. Also supports MCP (Cursor, Claude Desktop, Windsurf, etc.)
npm MIT -
AST-aware file reading and code search MCP server - Intelligent code exploration with structure understanding
npm MIT -
trace-forge-mcpgithub.com/mdfifty50-boop/trace-forge-mcpupdated this year
MCP server for writing structured traces, spans, and decisions — the only write-path observability MCP for EU AI Act traceability compliance
npm MIT -
Local-first repository analysis engine: code structure, dependency impact, and data lineage via CLI, Python API, and a read-only MCP server. Deterministic by default.
Apache-2.0 ★ 1 -
A knowledge graph of your codebase, exposed as an MCP server — so AI coding agents stop re-deriving structure from grep and Read on every request.
npm MIT -
Sub-millisecond AST structural & lexical BM25 code intelligence for AI coding agents. Ask your codebase a question, get exact file + symbol + line span in milliseconds.
npm MIT -
What your agents know about your system: a 114-language code graph, memory and knowledge, in a local CLI and MCP server (33 MCP tools, 3 domains). Holds your data sources' structure, never their rows.
MIT ★ 2 -
A high-performance code intelligence graph for LLMs and AI agents. Sub-second structural queries, impact analysis, and cross-repo API contracts for autonomous coding workflows.
MIT ★ 10 -
Descriptions for your project's files and directories: ls / tree / find with descriptions, as a CLI and an MCP server
MIT -
MCP server for sentinel-ir: lets AI agents (Claude Desktop, Cursor, Windsurf, ...) read a compact structural IR of JavaScript, TypeScript, Python and Rust files instead of the raw source. Read-only, sandboxed to allowed folders.
npm Apache-2.0 -
Structural code intelligence for AI coding agents over MCP: find a definition, read one function, see what calls a symbol, trace imports and judge a change's blast radius across 40+ languages — in tens of tokens instead of the ~1,563 a file read costs.
npm MIT -
openvisiogithub.com/syntaxpriest/openvisio-ossupdated this year
Cut your AI coding agent's token usage. MCP server + CLI that turns any codebase into a deterministic code graph and serves Claude Code, Cursor, Codex & Windsurf a ranked, token-budgeted query surface — agents query structure (symbols, imports, call edges
npm MIT