MCP Server Directory

Philidor DeFi Vault Risk Analytics io.philidor/defi-vaults

Search 700+ DeFi vaults, compare risk scores, analyze protocols. No API key needed.

Local encryption and project setup plugin for CoSync. Keys never leave your machine.

scoring io.sentinelsignal/scoring

Hosted MCP for denial, prior auth, reimbursement, workflow validation, batch scoring, and feedback.

Secure MCP server for YouTube intelligence — 18 tools, OAuth2, OWASP Top 10 controls.

MCP gateway: bounded tool shortlists + artifact-backed result firewall. Deterministic, no model.

MCP conformance test harness. JSON-RPC, OAuth 2.1 PKCE, schemas, smoke, annotations. CLI + lib.

cybershield io.tooloracle/cybershield

CyberShield - 12 cybersecurity tools: NIS2 mapping, MITRE ATT&CK, vulns, threat intel.

AI-Powered Security Scanner for LLMs. Detects vulnerabilities and syncs with SynapseAudit.

BezBaseina lv.bezbaseina/mcp

Latvian property portal: search rentals, sales & nightly stays; market stats; owner tools via OAuth.

lookup-disclose-io io.github.disclose/lookup-disclose-io

Find the right security-disclosure contact for any internet asset (domain, IP, package, repo, app).

HoneyLabs net.honeylabs/mcp

Honeypot probe data: IP reputation, scanners, CVE probing, TLS and SSH fingerprints.

Connects AI agents with CrowdStrike Falcon for security analysis and automation.

Conta Azul MCP io.github.douglac/contaazul-mcp

Conta Azul ERP MCP — sales, customers, finance and NF-e via OAuth 2.0. Read + write, 35 tools.

PaperLink online.paperlink/mcp

Document sharing, invoicing, and personal finance platform. 15+ AI tools via OAuth 2.1.

OntoRamp Decision Intelligence com.ontoramp/decision-intelligence

Log, evaluate, and ground AI decisions against authority context. Returns PASS, WARN, or BLOCK.

hypernatt-terminal io.github.DIALLOUBE-RESEARCH/hypernatt-terminal

BTC/USDC decision context for AI agents from a live Hyperliquid vault; $0.001/call via x402.

Decompose text into classified semantic units. Authority, risk, attention. No LLM.

Intent-bound action authorization for AI agents: policy, human approval, and a signed audit trail.

Skew site.skew/skew

Authored design service: one-of-one landing pages, pitch decks, and research-grounded briefs.

PromptGuard Scan MCP space.promptguardscan/promptguardscan-mcp

Paid remote MCP for LLM security scans, jailbreak checks, analytics, checkout, and readiness.

MCP server for t-rush. Exposes TODO/FIXME scanning and streak tracking to AI agents.

MCP server for self-hosted Jira instance with Personal Access Token authentication

Local GitHub Actions/CI maintenance check (action pinning, token perms). Not a full security audit.

MCP server for AI agent read/write access to Obsidian vaults via EVC Team Relay.