MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Payment-risk triage with logistic regression, held-out precision metrics, grounded LLM decisions, bounded RAG prompts, audit storage, MCP and Docker.
MIT -
🔌 Exposes AI risk assessment over MCP — NIST AI RMF-aligned risk register with scoring, treatments, controls, and signed evidence trail.
pypi MIT -
AI-Act-Risk-Classifier-Agent-with-MCP-LangGraphgithub.com/Mehulupase01/AI-Act-Risk-Classifier-Agent-with-MCP-LangGraphupdated this year
Production-grade AI governance and EU AI Act assessment platform with deterministic policy rules, LangGraph review workflows, MCP servers, audit-pack exports, and OpenRouter/Ollama support.
-
meok-mcp-risk-assessmentgithub.com/meok-ai-labs/mcp-risk-assessmentupdated this year
MCP server for AI/ML risk assessment and scoring
npm MIT -
meok-mcp-model-riskgithub.com/meok-ai-labs/mcp-model-riskupdated this year
MCP server for AI model risk management
npm MIT -
meok-mcp-third-party-riskgithub.com/meok-ai-labs/mcp-third-party-riskupdated this year
MCP server for third-party AI vendor risk assessment
npm MIT -
MCP server that gives AI agents quantitative risk analytics tools: Value at Risk (VaR) and Expected Shortfall by 4 methods, GARCH volatility forecasting, extreme value theory (EVT) tail risk, Basel backtesting, stress testing, and a credit-risk PD scorecard. Python, FastMCP, works with Claude.
MIT ★ 1 -
An always-on, autonomous agentic risk platform demonstrating event-driven AI agents on Azure for continuous FX and interest rate contract risk monitoring.
MIT ★ 1 -
Systemic risk contagion analysis for financial networks, delivered as an MCP server your AI agent connects to directly.
MIT -
MCP server: deterministic treasury risk, FX exposure, liquidity & payment decisions for AI CFO agents - pay per call in USDC (x402)
npm ISC -
Open-source Barra-style US equity factor risk model — daily estimation, weekly builds, public validation. Free artifacts, MCP server for AI agents.
MIT ★ 13 -
open-source-supply-chain-risk-mcpgithub.com/apifyforge/open-source-supply-chain-risk-mcpupdated this year
Open source supply chain risk analysis via MCP — give your AI agent direct access to CVE records, CISA KEV exploits, maintainer bus-factor scores, and typosquat detection across 7 live intelligence sources.
MIT -
MCP server that turns UK Companies House public data into explainable risk signals — searches, scores and explains company risk for an AI assistant. Free stack: Python, DuckDB, Docker.
★ 1 -
aviation-safety-risk-mcpgithub.com/apifyforge/aviation-safety-risk-mcpupdated this year
Aviation safety intelligence for AI agents — this MCP server queries 8 live government data sources in parallel and returns a composite Aviation Safety Score (0-100) covering airline safety defects, airworthiness directives, route weather risk, sanctions exposure, and maintenance compliance.
MIT -
Deterministic credit portfolio risk: loss distribution, value-at-risk, expected shortfall, economic capital, risk contributions and risk-based loan pricing (RAROC, hurdle rate), by seeded simulation and by CreditRisk+. Checked against published examples. Read-only MCP server for AI agents.
pypi Apache-2.0 -
Give your AI agent a risk layer in 5 minutes: portfolio tail-risk guardian, dollar shock tester and contagion explainer on the Fahali MCP server. Observation, not advice.
MIT -
RiskLens — AI-powered lending risk intelligence platform: PostgreSQL Customer 360, XGBoost PD model with SHAP explanations, Early Warning System, behavioural anomaly detection, PSI model monitoring, and a tool-using AI Risk Analyst (Claude/OpenAI + MCP). FastAPI + Streamlit.
-
@quantrisk/mcp-servergithub.com/quantrisk/mcp-serverupdated this year
Portfolio risk analytics engine exposed as MCP tools — VaR, Monte Carlo, Markowitz optimization, options Greeks, and stress testing — for quant traders talking to AI assistants.
npm MIT -
senserity-mcp-serveractive
MCP server for Senserity risk intelligence platform — enables AI agents to perform company due diligence
npm UNLICENSED -
AI-powered security risk analysis via Model Context Protocol
npm MIT -
contractiq-mcpgithub.com/crawde/contractiq-mcpupdated this year
MCP server for ContractIQ — AI-powered contract analysis, risk scoring, and clause extraction
npm MIT -
BASTIONMCPgithub.com/bastionfintech-spec/BASTIONMCPupdated this year
Risk Intelligence MCP Server for Claude Agents. 49 tools. 560+ signals. 72B AI model.
MIT ★ 1 -
Automated EU AI Act Annex III risk classification and impact assessment engine
pypi MIT License -
mcp-deploy-intelgithub.com/vellankikoti/mcp-deploy-intelupdated this year
Kubernetes deployment intelligence — typed query tools + AI-synthesised risk briefs. CLI + MCP server.
pypi Apache-2.0 -
Risk guardrails for AI trading agents. Your agent proposes a trade; your policy decides.
pypi MIT ★ 3 -
Agentguard-github.com/xAPT42/Agentguard-updated this year
Discover and govern your AI agent fleet automatic inventory with risk scoring
Apache-2.0 -
Professional startup risk analysis using MCP and Google Gemini AI
pypi MIT -
pitchlense-mcp-fastmcpgithub.com/fastmcp-me/pitchlense-mcpupdated this year
Professional startup risk analysis using MCP and Google Gemini AI
pypi MIT -
DataNewton MCP server — Russian company data, financial analysis and risk indicators for AI assistants.
-
@smarttechnologyinvestments/riskbeforebuy-mcpgithub.com/smarttechnologyinvestments/riskbeforebuy-mcpupdated this year
RiskBeforeBuy MCP server — property risk assessment tools for AI agents
npm MIT -
stripe-alternatives-mcpgithub.com/val802/stripe-alternatives-mcpupdated this year
Payment processor comparison and risk assessment tools for AI agents. Find the right Stripe alternative based on industry, risk profile, and processing needs. Powered by StripeSwitch.
MIT -
meok-eu-aia-art-9-rms-mcpgithub.com/csoai-org/meok-eu-aia-art-9-rms-mcpupdated this year
MEOK EU AI Act Article 9 Risk Management System generator — 4-step iteration (identify / estimate / post-market / mitigate). 12 risk categories. Signed RMS for the Annex IV technical documentation bundle. By MEOK AI Labs.
pypi MIT -
@policyrisk/mcp-servergithub.com/pria-technologies/skunkworksupdated this year
PRIA MCP server — policy risk and assessment engine for AI agents (USC, CFR, federal bills, federal register, knowledge graph, Polipedia)
npm MIT -
rug-munch-mcpgithub.com/cryptorugmunch/rug-munch-mcpupdated this year
MCP server for Rug Munch Intelligence — 19 tools for crypto token risk analysis, rug pull detection, and AI forensics
pypi MIT -
dossier-mcpupdated this year
Dossier MCP server — onchain risk scoring for Base (token / deployer / wallet), callable by AI agents.
pypi MIT -
MCP server for AIR (AI Responsibly) — run risk assessments from Cursor, Claude Code, VS Code, and other MCP clients.
npm MIT -
@smarttechnologyinvestments/wildfirecost-mcpgithub.com/smarttechnologyinvestments/wildfirecost-mcpupdated this year
WildFireCost MCP server — wildfire risk scores, hardening ROI, and insurance savings for AI agents
npm MIT -
floodwisegithub.com/qinisolabs/floodwiseupdated this year
England flood-risk by postcode for AI agents — verified Environment Agency data, not guesses.
npm Apache-2.0 ★ 1 -
BASTION-MCPgithub.com/bastionfintech-spec/BASTION-MCPupdated this year
Risk Intelligence MCP Server for Claude Agents | 49 tools, 560+ signals, fine-tuned 72B AI model
MIT ★ 1 -
Autonomous Multi-Chain AI Agent Risk & Execution Protocol for Solana & DeFi with Model Context Protocol (MCP) | Colosseum Crypto World's Fair 2026
MIT -
BankShield AI is an agentic decision-support system for banking transaction risk investigation. Engineered with a LangGraph state machine and Model Context Protocol (MCP 2.0), it coordinates 4 specialized agents to automate evidence research, evaluate deterministic risk rules (0–100), audit math integrity, and generate 16-field regulatory dossiers.
MIT -
MCP server for SCF Controls Platform — security compliance controls, frameworks, evidence, and risk management for AI agents
npm MIT ★ 3 -
sentriagentgithub.com/Donyemiight/sentriagentupdated this year
Trust-as-a-Service for AI Agents. Risk-scoring MCP service on OKX.AI marketplace. x402/APP pay-per-call.
MIT -
contractiq-negotiation-mcpgithub.com/crawde/contractiq-negotiation-mcpupdated this year
MCP server for AI-powered contract negotiation — clause redlining, counter-proposal generation, risk tradeoff analysis, and negotiation strategy recommendations
npm MIT -
On-chain risk enforcement and behavioral analytics for autonomous AI trading agents on Solana. 19-tool MCP server with semantic routing, DR-CAM causal inference, and 3-layer evaluation suite.
MIT ★ 3 -
◉ Terra Pulse — open planetary nervous system: live USGS quakes + NASA disasters, explainable risk engine, MCP server for AI agents, quantum-resilient audit seals.
MIT -
war-dashboard-datagithub.com/cct15/war-dashboard-dataupdated this year
Futuristic Risk Intelligence — Geopolitical conflict risk data for AI agents (MCP/API)
pypi MIT ★ 2 -
codegraph-navgithub.com/efrenbl/codegraph-navupdated this year
Graph-intelligent, token-efficient code navigation for AI assistants. Surgical reading, execution flows, risk scoring, and micro-metadata rendering.
pypi MIT -
Free MCP server for developers adding human review gates, prompt risk checks, FAQ review, and CRM note safety to AI tools.
npm MIT -
自托管中国基金组合分析与风险管理工具 — 自动净值更新 / 收益与回撤 / AI 投顾 / 定投回测 / 基金筛选 / 分红检测 | Self-hosted China fund portfolio analyzer: auto NAV sync, returns/risk analytics, AI advisor, DCA backtest, fund screener, dividend detection
MIT ★ 29 -
kodeklaritygithub.com/vjvkrm/kodeklarityupdated this year
Shared knowledge & memory of your code, for AI agents. Code graph + persistent memory layer — impact analysis, risk scoring, cross-boundary tracing, agent-to-agent knowledge sharing.
npm AGPL-3.0-only -
Jaga - the risk guardian for agent-traded Binance subaccounts. Not a gate before the trade: a guard on the wallet behind it. 8 deterministic rules, MCP client + server, hash-chained audit. Code enforces, AI explains.
MIT -
ChainWard MCP server: check a counterparty on Base or BNB Chain before you pay it (risk reports + EAS attestations on Base), plus read-side intelligence on AI agents
npm MIT -
Wallex AI Trader: AI-led, risk-bounded algorithmic trading for the Wallex exchange (TMN markets), with paper/shadow arena, live engine with kill switch, MCP market data and a password-protected dashboard on Liara.
MIT -
Meta Global AI Developer Hackathon entry. Scan before you swap: evidence-based risk scanner for new Ethereum memecoins, with its own bytecode decompiler, proof traces and Meta Muse explanations. Web, REST and MCP.
Apache-2.0 -
Risk guardrail proxy for AI trading agents: an MCP server that checks every order against your loss limits, position caps and revenge-trade rules before it reaches the broker (simulation or Robinhood).
npm MIT -
GitPeak's MCP server: git context for AI agents. Repo status, staged diff, commit log with AI-agent detection, repo health, merge-risk prediction, line history and worktrees. Read-only, zero dependencies.
npm MIT -
leaseiq-analyze-mcpgithub.com/crawde/mcp-leaseiq-analyzeupdated this year
MCP server for AI lease document analysis — extract clauses, assess risk, score tenant protection, and generate compliance reports via LeaseIQ
npm MIT -
scytheradar-mcpactive
ScytheRadar MCP — read-only, bilingual (中文/English) on-chain risk screening, blacklist check, fund tracing and rug-pull forensics for AI agents. TRON dirty-USDT + EVM.
npm MIT -
Mishmar is a risk management layer for trading bots and AI agents: every order is checked against your limits before it reaches the exchange, large orders wait for your approval, and no key can trade alone.
npm Apache-2.0