Security MCP Servers

Ping-only MCP origin for claude.ai, Desktop, Cursor, and Grok Connectors.

Encrypted LangChain Session Agent

Encrypted OAuth LLM Agent

Google OAuth LangChain Agent

AI scam-shield for Web3: screen token contracts for honeypot/drain patterns. Aegis AI group admin.

Portable AI memory shared across models and harnesses - plain markdown you own.

Encrypted LangChain Token Agent

Google OAuth Credential Service

Defensive vulnerability intelligence search across public CVE/NVD and GitHub advisory APIs with CVSS

Cache-bust forensics + TTL-fit verdicts: names the field that busts your prompt cache.

MCP smart contract scanner with NEAR-focused security context.

Read your own vehicles' OBD-II scans, fault codes, telemetry and trips stored in OBD Vault.

Inspect the certificate and TLS versions served by a public endpoint.

In-band MCP sleeper sentinel — mid-session diff and quarantine inside your own client's session.

中文内容合规检查：广告法违禁词 + AI 标识规则，逐条给出法条依据。Chinese content compliance: ad-law banned terms + AI labeling.

In-Band DLP Engine, PII Redaction & Threat Firewall for AI Agents

Zero-key security toolkit: grade sites A+ to F, check CVE exploits, plain-English attack defenses

Amazon Seller Central + Ads: settlement-accurate P&L, full PPC, every write staged for approval.

Free front-end security check for any website: a grade plus the secrets and keys it exposes.

Figma designs pulled once into a local vault; AI agents read them offline with no rate limits

Find public biomarker education, available blood tests, panels, and budget-aware starting points.

Crypto signals, public ledger, BTC chart read, news, your strategies and backtests. No trading.

Regulatory intelligence for AI agents across jurisdictions

OSINT investigations with traceable evidence: domains, URLs, IPs, scams and business records.

Honeypot detection & token risk scan for ERC-20s. Risk score 0-100, tax, source verification.

Go vulns: CVEs per module, fixed versions. $0.01/query. Register in-session — free testnet funds.

Obsidian vault structural health: broken links, orphans, missing frontmatter, safe auto-repair.

KVKK/GDPR/CCPA compliance checks for codebases

US stock attack/defense macro signals: 4-dimension framework, 26-year backtested. Research only.

Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup

CISA KEV catalog: active-exploit alerts, hourly. Register in-session — free testnet funds.

Read and update your Hardcover library, progress, lists, and goals. Sign in with Hardcover OAuth.

Add a cookie consent banner that blocks trackers before consent and records proof of consent.

Prove real MCP clients can connect: 5-client x 3-IdP OAuth matrix with shim fixes.

Debian Security Advisories (DSA). $0.01/query. Register in-session — free testnet funds.

9 utility tools for agents: DNS, WHOIS, email, IP, URL, headers, QR, text, tech. x402 on Base.

Affiliate marketplace for AI agents: find tools, publish verified guides, earn. OAuth, no keys.

Encrypted local vault for API keys. Your AI fetches keys on demand and scans code for leaks.

Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.

Audit Python and npm dependency licenses before you ship, judged against how you distribute.

AWS pricing and cost estimates with no signup, plus read-only idle-resource scans of your account.

The family's agent reads the record, drafts the filing from verified rules, asks for a signature.

Usage-adaptive Obsidian vault search: Hebbian + PageRank + BM25 hybrid ranking.

Map financial identifiers (ISIN, CUSIP, SEDOL, Ticker) to FIGIs via OpenFIGI API

Operate Linux, macOS and Windows from your LLM. Every action runs through an auditable allowlist.

AI-controlled algorithmic trading engine exposing 40 MCP tools across 9 namespaces.

Classify data safety before storing or sharing. GDPR, HIPAA, PCI-DSS, CCPA. AI-powered.

Sequence sentinel: wall events + channel-switch scoring; HALT, hold, signed receipt.