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/7

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

145–168 of 179 · ranked by trust score, then stars

Trail-Code

trailhq/Trail-Code

✕BLOCK F

Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.

★ 10,6753 write

Gopls

xieyuschen/gopls-mcp

✕BLOCK F

MCP server for golang projects development: Expand AI Code Agent ability boundary to have a semantic understanding and determinisic information for golang projects.

★ 59Not listed in sourcestreamable-http

Codesteward

codesteward/codesteward

✕BLOCK F

Agentic code review with structural graph intelligence — PR gate + branch stewardship. Self-hosted. Apache-2.0.

★ 213 writestreamable-http

astria

Nodesify/astria

✕BLOCK F

Turn any folder into a queryable knowledge graph

★ 3Not listed in sourcestdio

Remindb

radimsem/remindb

✕BLOCK F

An agentic memory database that cuts session tokens by 82–99%. One portable SQLite file — your agent's memory, anywhere.

★ 1291 writestreamable-http

sfdt

scoobydrew83/sfdt

✕BLOCK F

Salesforce DevTools — CLI, VS Code extension, sf plugin, MCP server, and web dashboard for Salesforce DX deploy, test, org health, and release management. AI-optional, CI-ready.

★ 12 destructivestdio

arkgate

pedroknigge/arkgate

✕BLOCK F

If the AI writes an illegal import, the write is rejected. The same check fails the pull request.

★ 11 destructivestdio

Code-Graph-RAG

vitali87/code-graph-rag

!CAUTION F

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

★ 5,169Not listed in sourcestdio

code-graph-rag

vitali87/code-graph-rag

!CAUTION F

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs

★ 5,157Not listed in sourcestdio

octocode-mcp

bgauryy/octocode

✕BLOCK F

Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI

★ 9509 writestdio

Drift

dadbodgeoff/drift

✕BLOCK F

Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.

★ 7892 write

AIWorkHub

shrec/AIWorkHub

✕BLOCK F

Open-source, local-first control plane for multi-model AI coding agents in VS Code and MCP: task DAGs, source intelligence, durable context and evidence-based review.

★ 93 destructivestdio

Octocode

bgauryy/octocode-mcp

✕BLOCK F

Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI

★ 9449 writestdio

deepPairing

mitchjablonski/deepPairing

✕BLOCK F

Review what Claude Code is about to change on a rich visual surface — inline comments, evidence, and a gate that remembers the approaches you rejected.

★ 15 readstdio

Sourcebot

sourcebot-dev/sourcebot

✕BLOCK F

Sourcebot is a self-hosted tool that helps humans and agents understand your codebase.

★ 3,9471 destructivestreamable-http

rag-rat

cq27-dev/rag-rat

✕BLOCK F

Local repo-intelligence index + MCP server: semantic search, symbol/graph navigation, impact-surface preflight, git + GitHub papertrail, and a source-anchored memory graph.

★ 24Not listed in sourcestdio

Mex

mex-memory/mex

✕BLOCK F

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

★ 1,7032 writestdio

Claude Delegator

antonbabenko/claude-delegator

✕BLOCK F

Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures the models' usefulness, too.

★ 1697 writestdio

Deliberation

antonbabenko/deliberation

✕BLOCK F

Ask Codex, Gemini, Grok, and 400+ OpenRouter models (Qwen, Kimi, DeepSeek) for second opinions or arbiter-mediated consensus. One MCP server for Claude Code, Codex, Cursor, Kiro, OpenCode. Measures the models' usefulness, too.

★ 1697 writestdio

agentic-hil

agentic-hil/agentic-hil

✕BLOCK F

Let your coding agent develop firmware on the real board, with the hardware as the gate.

★ 171 destructivestdio

SDL

glitterkill/sdl-mcp

✕BLOCK F

Symbol Delta Ledger (SDL-MCP) is a policy-centered context budget layer for coding agents: Symbol-graph intelligence combined with precision tools. It turns sprawling codebases into compact, high-signal context that saves tokens, speeds up workflows, and improves agent output.

★ 4901 destructivesse

CodeNib

sysevol-ai/CodeNib

✕BLOCK F

Find source context and trace calls across languages in Claude Code, Codex and other MCP agents.

★ 863 readstdio

MarkuprPlus

hashfunction/MarkuprPlus

✕BLOCK F

Record your screen, narrate the bug, and hand your AI coding agent structured Markdown - one annotated screenshot per mark. Desktop app, CLI, and MCP server for Claude Code, Cursor, Codex, and Windsurf. On-device Whisper transcription, local-first, MIT.

★ 794 writestdio

code-graph

cyberchronos00/code-graph

✕BLOCK F

A deterministic code graph for codebases: every caller, route, page and table a change touches, with file:line evidence. CLI, MCP server and web view for AI agents and reviewers.

★ 42 destructive

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.