Code Assistant MCP server
Gemini-powered MCP server for code analysis.
0 stars70 downloads/wk
Reviews
Write oneNobody has reviewed Code Assistant yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Code Assistant tools (13)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
analyze_pr_impactAssess impact and risk from cached diff. Prerequisite: generate_diff. Auto-infer repo/language.
analyze_time_space_complexityAnalyze Big-O complexity. Prerequisite: generate_diff. Auto-infer language.
ask_about_codeAnswer questions about a cached file. Prerequisite: load_file. Auto-infer language.
detect_api_breaking_changesDetect breaking API changes. Prerequisite: generate_diff. Auto-infer language.
detect_code_smellsDetect structural code smells in a cached file. Prerequisite: load_file. Auto-infer language.
generate_diffGenerate a diff of the current branch working changes and cache it for all review tools. You MUST call this tool before calling any other review tool. Use "unstaged" for working-tree changes not yet staged, or "staged" for changes already added with git add.
generate_documentationGenerate documentation stubs for all public exports in a cached file. Prerequisite: load_file. Auto-infer language.
generate_review_summarySummarize diff and risk level. Prerequisite: generate_diff. Auto-infer repo/language.
generate_test_planGenerate test cases. Prerequisite: generate_diff. Auto-infer repo/language/framework.
load_fileCache a single file for analysis tools (refactor_code, ask_about_code, verify_logic). Overwrites previous cache. Path is relative to server working directory (e.g. src/index.ts) or absolute (e.g. /home/user/project/src/index.ts).
refactor_codeAnalyze cached file for complexity, duplication, naming, and grouping improvements. Prerequisite: load_file. Set maxSuggestions to cap output (default 10).
verify_logicVerify algorithms and logic in a cached file using Gemini code execution sandbox. Prerequisite: load_file. Auto-infer language.
web_searchGoogle Search with Grounding. Set topic to scope results; responseStyle controls output length.
Public scan report
scanner v0.1.10 · 2026-09-28 · same rubric, same numbers if you re-run it
- Code scan91 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 203 days ago4/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Code Assistant compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 75/100
- higher than 45% of 48,255 servers
- Tools
- 13
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 70
- more than 54% of 12,191 servers with a package
What its tools let an agent do: 9 read · 4 create
Install Code Assistant in Claude Code, Cursor or VS Code
Runs npx -y @j0hanz/code-assistant on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add code-assistant -- npx -y @j0hanz/code-assistant
What the publisher says
From the Code Assistant repository's README, as published. We do not edit it. Read it on GitHub
<!-- mcp-name: io.github.j0hanz/code-lens -->
Code Lens MCP Server
Gemini-powered MCP server for automated code review, analysis, and documentation.
Overview
Code Lens is a Model Context Protocol server that uses Google Gemini to analyze diffs, review pull requests, detect code smells, generate documentation, and verify logic. It exposes 13 tools, 7 resources, and 5 prompts over stdio transport.
Key Features
- PR review pipeline — generate diffs, assess impact, detect breaking API changes, and produce review summaries with merge recommendations
- File analysis — load any source file for refactoring suggestions, code smell detection, documentation generation, and natural-language Q&A
- Logic verification — verify algorithms using Gemini's code execution sandbox
- Structured outputs — all tools return validated JSON via Zod v4 output schemas
- Web search — Google Search with Grounding for up-to-date information retrieval
- Task lifecycle support — every tool except load_file can run via MCP tasks with polling, cancellation, and progress updates
Requirements
- Node.js >= 24
- A Gemini API key (GEMINIAPIKEY or GOOGLEAPIKEY)
Quick Start
{
"mcpServers": {
"code-lens": {
"command": "npx",
"args": ["-y", "@j0hanz/code-lens-mcp@latest"],
"env": {
"GEMINI_API_KEY": "your-api-key"
}
}
}
}Docker
docker run -i --rm -e GEMINI_API_KEY="your-api-key" ghcr.io/j0hanz/code-lensOr with Docker Compose:
GEMINI_API_KEY=your-api-key docker compose upClient Configuration
Install in VS Code
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Code Assistant: common questions
- Is Code Assistant MCP server safe?
- Mostly: it is graded B (75/100). Read the Code Assistant safety report
- How do I install Code Assistant?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Code Assistant need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Code Assistant maintained?
- The last commit was 240 days ago (2026-03-09). The latest release is v2.0.0.
- How does Code Assistant compare with other MCP servers?
- safety score 75/100 (higher than 45% of 48,255 servers); tools 13 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.