🔍代码审查 / GitHub MCP 推荐

LLM cost optimization. Audit your calls, prove savings, route to the cheapest quality model. BYOK.

Generate app icons, favicons, OG images, and logos by routing across 30+ image models.

MT5 strategy development with 87 tools. Backtest, optimize, debug MQL5 EAs on macOS/Linux.

Local AES-256-GCM vault for AI agents. Secrets stay local, LLMs never see real API keys.

Static linter for AI prompts: contradictions, redundancy, ambiguity, and fluff.

Hosted MCP endpoint with realistic fake data for prototyping agents. 12 tools, no setup.

Local symbol ground truth MCP server for Unicode lookup and code-symbol linting.

Linux CVE prioritisation: 16 MCP tools for scan, fleet, runtime, and PR-able fix discovery.

Dynamic context loading for AI assistants with TDD workflow and AST analysis

MCP security trust layer: scan packages, inspect repos, check exposure, monitor changes.

Non-custodial Solana swap & limit order engine for AI agents.

Search engine and payment rail for AI agents. 2,300+ services, semantic ranking.

Local-first agentic memory for MCP agents — 25 tools, hybrid search, GDPR, no cloud.

Personalize AI coding assistants by analyzing local conversation history. Runs on your machine.

Model Context Protocol server for CiviCRM — AuthX-first, schema-introspected, write-gated.

EU AI Act + GDPR compliance scanner. One call, no arguments, 10 seconds. 22 AI frameworks detected.

Benchmark-first release surface with a read-only MCP endpoint and operator CLI.

Search and fetch 100+ Hermes Agent tools, skills, plugins, and integrations from hermesatlas.com.

AI real estate settlement with 5 specialized agents for blockchain transfers in 15 seconds.

AWS cloud security scanners for AI agents — S3, IAM, EC2, EKS, RDS, CloudTrail, CloudWatch Logs

BlackHawkMCP - connect AI to Google Sheets

Intelligence marketplace on Solana — 86 tools, 168+ endpoints, per-call USDC.

Inject deep domain knowledge into any AI agent

Structured execution trace and span logging for AI agents

Constitutional guardrails and loop detection for AI agents

Agent-to-agent communication bridge for multi-agent systems

ZATCA, UAE CT, EU AI Act regulatory compliance for AI agents

Output quality control and validation for AI agents

Multi-agent billing and cost allocation tracking

Record and replay AI agent execution for debugging

Context window token analysis and budget management

Encrypted secrets and credential management for agents

Professional document generation from structured data

Hard scope boundaries to prevent AI agent drift

MCP server discovery, indexing, and registration

Security scanning and threat detection for AI agents

GCC regulatory intelligence, ZATCA e-invoicing, and Arabic NLP for AI agents

Secure MCP server for Obsidian with OWASP Top 10 controls and full audit logging.

Open-source AI security agent: SAST, DAST, and policy-as-code over MCP.

35+ AI tools for TCG card grading, Monte Carlo pricing, 370K+ product search. BYOK.

MCP server for AiDataTaskRunner Panel (MT5) - Control data generation and ML model training via MCP

MCP server for SSH remote command execution

Residential proxy MCP server. 175M+ IPs in 195+ countries with anti-bot bypass.

Access your Apple Books library, annotations, reading progress, and highlights through Claude

List and fetch official Pine Labs SDK API documentation via MCP tools.

MCP server for Testkube - Manage test workflows, executions, and artifacts via AI assistants

AI API cost calculator, recommender & MCP server. 29 models across text/image/video/audio.

Deterministic Chinese divination APIs (BaZi/QiMen/ZiWei/MeiHua/LiuYao/LiuRen) x402 on Base.