- ABAP @palimkarakshay/abap-mcpOffline SAP ABAP/RAP tools for AI agents: lint, Cloud readiness, released APIs, knowledge.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Code Sanitizer @notasandy/mcp-code-sanitizerStrict AI code reviewer powered by Groq. Finds bugs and vulnerabilities.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- repoctx @nugehs/repoctxLocal-first code context, impact analysis, and merge-readiness verdicts for AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Codexa @mirnoorata/codexaCodex-native codebase intelligence context compiler and query-only MCP server.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Batch Review @hevangel/batch-review-mcpGit diff and markdown review with a web UI plus MCP stdio for AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.2 GitHub stars.
- Ohm @murugarajr/ohm-mcpAST-based Python refactoring MCP server with safe automated refactorings and rollback5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Cli Bridge @joaoberne/cli-bridge-mcpOther AI CLIs (Gemini, GPT, Claude, opencode, Ollama) as a council — ban-safe, no API keys.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Amicus @bourbondog/amicusMulti-model LLM Council and parallel AI window for Claude Code. Fork any model, fold results back.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Aikido @bajuzjefe/aikido-mcpSecurity analysis for Aiken smart contracts on Cardano. 75 vulnerability detectors.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- onsystem @dgesteves/onsystemKeeps coding agents on your design system: knows your real components, props, variants and tokens.Not assessed yet.Runs on your machine, installed from npm.1 GitHub stars.
- Design System MCP @dgesteves/design-system-mcpGround truth about your React design system for coding agents, plus a UI linter they can run.Not assessed yet.Runs on your machine, installed from npm.1 GitHub stars.
- Unicode-LE @nolindnaidoo/unicode-leFind the Unicode that hides meaning: bidi controls, invisibles, homoglyphs and mixed scripts.Not assessed yet.Runs on your machine, installed from npm.1 GitHub stars.
- Contribos @adityatiwari101104/contribosHelp open-source contributors earn maintainer trust: repo rules, briefs, and pre-submit checks.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Code Quality @ryudi84/code-qualityMCP server for code quality: complexity, duplicates, naming, refactoring.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- AI Disclosure Lint Sb942 @jmshinhwa/ai-disclosure-lint-sb942Finds the generative-AI code that drops the disclosures California SB 942 has required since August7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Ai Model Retirement Lint @jmshinhwa/ai-model-retirement-lintFinds the LLM model IDs pinned in your code that vendors have already switched off, or have dated to4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Skimless @pedroofrancaa/skimlessReading order for big pull requests: what to read first, what can wait. Offline, no model.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Predictive Debugger @speedosdk/predictive-debuggerPredicts where JavaScript and TypeScript code will fail at runtime, for coding agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- CodeZaiku @wyrdsekai/codezaikuA coding and development harness on local models or hosted APIs, for code, review, research and ops.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- SecHelix @omarmohelal/sechelixEvidence-first security review of authorized repositories. Read-only, root-confined, no shell.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- HEIDES @abduljabbarbxr/heidesDeterministic code analysis harness giving AI agents senses, memory and judgment for code.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
- crapkit @jeanfrancoisgagne/crapkitTwelve tools to inspect CRAP scores, find work, and check edited functions against their ceiling.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Signalint @tranqui004/signalintLocal stdio MCP server for cached, loop-aware JS/TS diagnostics (Oxlint, tsc, Biome, ESLint).4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Scopewalker @timohaa/scopewalker-mcpCodebase analysis tools for AI agents: complexity, prop drilling, doc coverage, code smells.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
