MCP servers · by job

Code intelligence MCP servers

179 MCP servers that search, analyse and review source code. 49 are SAFE, 43 CAUTION and 87 BLOCK. Ranked by trust score; each card opens the full audit.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Code intelligence MCP servers”. Retrieved 29 Oct 2026. https://modelsatlas.com/mcp/topic/code-intelligence/page/5

Verdicts · 179 servers

✓SAFE49!CAUTION43✕BLOCK87

Transports

A server can list more than one transport.

Tool risk

46

servers expose at least one destructive tool: delete, overwrite or run. The median server with a readable tool list exposes 12 tools.

Servers with no destructive tools →

179 code intelligence servers

97–120 of 179 · ranked by trust score, then stars

CodeRAG

jonnoc/coderag

✕BLOCK D

Advanced graph-based code analysis for AI-assisted software development

★ 283 destructivesse

roast-my-design-system

gregkozakiewicz/roast-my-design-system

✕BLOCK D

AI design system scanner + mcp server. Scores repos 0-100, writes fix prompts. 27K+ npm downloads.

★ 272 writestdio

Codex

x51xxx/codex-mcp-tool

✕BLOCK D

MCP server bridging AI assistants to OpenAI Codex CLI for code analysis and review

★ 244 writestdio

gitwarren-app

klarluft/gitwarren-app

✕BLOCK D

Code review for your own machines and your own agents. Reviews live where the code does — reached over SSH, WSL or your own tailnet. Desktop app or just a browser tab. No server, no account.

★ 183 destructivestdio

memex

STiFLeR7/memex

✕BLOCK D

Persistent memory for AI coding agents via MCP: a bitemporal knowledge graph of your codebase, served to Claude Code, Cursor, Gemini CLI, and any MCP client. Tree-sitter and Gemini Flash into Neo4j via Graphiti. 14 MCP tools, hierarchical clusters, three-regime confidence decay.

★ 123 writestdio

lain

spuentesp/lain

✕BLOCK D

High-performance MCP server for AI coding agents: persistent knowledge graph, blast radius analysis, semantic search. Built in Rust.

★ 94 writestdio

mcp-code-mode

Jame0077/mcp-code-mode

✕BLOCK D

🤖 Enable AI code generation using the Code Execution MCP Server, integrating large language models with the Model Context Protocol for seamless tool use.

★ 13 writestdio

mcprobe

Amalleheavy908/mcprobe

✕BLOCK D

Validate MCP servers by inspecting tools, schemas, and resource URIs to identify security risks before connection.

★ 01 write

geml

geml-spec/geml

✕BLOCK D

One format, two readers. People and AI agents now co-write the same document. Legible for people; addressable, verifiable, and versioned for machines. GEML is plain text — organized by one typed block for everything, remembered by a .gemlhistory sidecar.

★ 281 destructivestdio

vastlint

aleksUIX/vastlint

✕BLOCK D

IAB VAST, VMAP, and DAAST validator. Hosted MCP at https://vastlint.org/mcp (auth none).

★ 19Not listed in sourcesse

Metro

steve228uk/metro-mcp

✕BLOCK D

🚇 A plugin-based MCP server for React Native runtime debugging, inspection, and automation. Connects to Metro bundler via Chrome DevTools Protocol — no app code changes needed for most features.

★ 831 writestdio

chargehand

Egoushka/chargehand

✕BLOCK D

Runs your request on coding agents (Claude Code, OpenCode) and returns an answer whose every citation is checked against a pinned commit. CLI, HTTP and MCP.

★ 0Not listed in sourcestdio

dev-error-explainers

mahdibrr/dev-error-explainers

✕BLOCK D

Paste a developer error, get the real cause and the fix. Offline, zero-dependency explainers for CORS, ESM/CJS, npm ERESOLVE, ChunkLoadError, Postgres/Supabase DATABASE_URL and Next.js build errors.

★ 0Not listed in sourcestdio

codegraph

lzehrung/codegraph

✕BLOCK D

CLI, MCP and TS library that turns source code into a map of files, symbols, references, and dependencies using tree-sitter.

★ 83 writestdio

slop-chop

dcadolph/slop-chop

✕BLOCK D

Strip AI tells from text: em-dashes, slop words, and stock phrases, in one deterministic local pass. CLI, GitHub Action, Obsidian plugin, and MCP server.

★ 4Not listed in sourcestdio

Carrot AI PM

talvinder/carrot-ai-pm

✕BLOCK D

Carrot auto-writes specs and catches AI code drift. MCP server for Cursor that AST-validates every commit.

★ 292 destructivestdio

Ctxo

alperhankendi/ctxo

✕BLOCK F

MCP server for AI coding agents. Instead of reading files one by one, your agent gets dependency graphs, git intent, blast radius, and change health in a single call. Works with any language deep analysis for TypeScript,Java, Go, and C#.

★ 6914 readstdio

GitHits

githits-com/githits-cli

✕BLOCK F

CLI & MCP for GitHits - The Code Context Layer for AI Coding Agents

★ 1141 writestdio

Cynical Sally

w1ckedxt/cynical-sally

✕BLOCK F

Brutally honest senior-engineer code reviews for Claude Code, Cursor & Windsurf - and your terminal. Scores, evidence-backed issues, usable fixes.

★ 968 readstdio

Kage

kage-core/kage

✕BLOCK F

Persistent, verified memory for coding agents — so they stop re-explaining your codebase and never act on stale knowledge. Every memory is checked against your actual code; lives in your repo as plain files, shared via git. No account, no DB. Install: npx -y @kage-core/kage-graph-mcp install

★ 401 destructivestdio

Sqry

verivus-oss/sqry

✕BLOCK F

Semantic code search engine - by Verivus (sqry.dev)

★ 31Not listed in sourcestdio

Context Engine

kirachon/context-engine

✕BLOCK F

Local-native Context Engine MCP server for codebase indexing, semantic retrieval, planning, and review workflows.

★ 483 destructivestdio

SwiftLens

swiftlens/swiftlens

✕BLOCK F

SwiftLens is a Model Context Protocol (MCP) server that provides deep, semantic-level analysis of Swift codebases to any AI models. By integrating directly with Apple's SourceKit-LSP, SwiftLens enables AI models to understand Swift code with compiler-grade accuracy.

★ 1261 write

Sverklo

sverklo/sverklo

✕BLOCK F

Repo memory for coding agents. Local-first MCP for Claude Code, Cursor, Windsurf, and Codex CLI: symbol graph, blast radius, diff-aware review, and git-pinned decisions. MIT; no API keys or code upload.

★ 812 destructivestdio

Other jobs

By risk

Questions

How do you decide which servers are code intelligence servers?
By the categories each server's own repository declares, mapped onto this job by a hand-kept table. A server can belong to more than one job, and one whose repository declares no matching category is not listed here.
Which code intelligence MCP servers rank highest on trust?
Graft (nanonets/graft), Graft (trailhq/graft) and Graft (trailhq/Graft), by trust score and then stars. Ranking never uses popularity to change a verdict.
How many code intelligence servers only read?
39 of the 179 declare tools that all only read; 46 expose at least one destructive tool.

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.