🔍代码审查 / GitHub MCP 推荐

Persistent memory + FTS5 search MCP server for Claude Code conversation history.

Construction estimating MCP: 48 tools — materials, labor, cost, structural, MEP, estimates.

Dispatch litigation work to legal-services vendors from any MCP-compatible AI workflow.

Agent-callable creator intelligence: 952+ scored YouTube creators across 180 niches.

An MCP server that provides weather data

Live financial data MCP: FX, crypto, stocks, news, URL reader. x402 on Base: $0.001/call.

Query databases from AI agents using connections configured in DBX.

LLM access to Apple Mail and iCloud via AppleScript. Read, search, compose, reply, flag and delete.

Substack CLI + 26-tool MCP server. Your IDE drafts replies via propose_reply. No API keys.

Medium CLI + 23-tool MCP server. Your IDE drafts replies. No API keys.

Spring Boot example that exposes SpringDoc OpenAPI operations as safe MCP tools.

Post bounties, solve tasks, earn credits on Emergence Science — the agent economy.

Aurekai MCP server for akai doctor, manifests, artifacts, feature queries, and runtime inspection.

Execute bash commands with background job support.

Local MCP voice coach with English pronunciation, grammar, and fluency feedback.

Forensic FX audit. Detects hidden bank markups in real time. Returns spread bps + audit score 1-10.

Runtime budget authority for AI agents — reserve, enforce, reconcile spend across providers

Scores US metros on corporate investment catalysts and repricing signals for real estate investors.

Kindle niche intelligence (demand/competition/BSR/revenue) gated by x402 USDC on Base.

Pre-action attestation perimeter for AI agents — 8 primitives, signed C18 receipt per call.

Routes AI tasks to dynamic LLM-generated skills via an orbital classifier.

Canvas LMS integration for students and educators with FERPA-compliant analytics and workflows

Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.

OpenAPI lifecycle guard and MCP sidecar for policy-driven API orchestration.

MIT-licensed pip-installable MCP for Google Merchant Center on Merchant API v1 (126 tools).

Real-time Argentine open data: dollar rates, BCRA, INDEC, AFIP, INFOLEG, SEPA prices. 24+ tools.

Email deliverability for AI agents. 12 tools: verify, DNSBL, DMARC, spam-trap, finder.

Push HTML prototypes to DesignPin for team review and pull reviewer feedback into your AI.

RedM / RDR3 docs MCP server: native lookups, semantic search, VORP, RSGCore, oxmysql.

Generate Tableau .twb/.twbx workbooks: 47 tools for charts, dashboards, rules, CSV pipelines.

Tick-level Hyperliquid market data: fills, L4 book, funding, liquidations, smart triggers.

Discover and query 15,500+ classified subgraphs on The Graph Network

Visa eligibility matcher and immigration intelligence for MCP-compatible AI assistants.

MCP server that fetches YouTube video transcripts and optionally summarizes them

Zero-knowledge persistent memory layer for AI agents. Encrypted client-side, hosted in France.

High-performance knowledge graph MCP server for AI coding agents with semantic search.

PulseChain analytics: 28 tools — safety scores, signals, whale alerts, pair analytics, AML.

MCP server for Agon Protocol state reads and prepare-only payment-channel actions.

Query Sri Lankan businesses, doctors, and reviews from any MCP-aware AI agent.

MCP server for Agon Gateway x402, Helius Wallet, and Tokens API market data.

Structured execution for Claude Code — contracts, postconditions, gates, guardrails.

Surf park sessions schedule availability and notifications for wave park surfers worldwide

Wash-filtered intelligence for x402: categories, services, wash analysis, trends.

Search a billion+ documents — papers, books, code, legal cases, forums, Wikipedia, and more.

DataFood: 16 data sources (crypto/DeFi/security/news/finance) via one MCP. Bundles save ~92%.

MCP server for Financial Modeling Prep API with 250+ financial data tools

Classify products to official HS codes and validate supplier codes before customs submissions

AI URL safety validator: SAFE/SUSPICIOUS/DANGEROUS verdict, trust score, threat intel.