cd /news/ai-agents/show-hn-mcp-sentry-v2-0-zero-depende… · home › topics › ai-agents › article
[ARTICLE · art-172758] src=github.com ↗ pub= topic=ai-agents verified=true sentiment=↑ positive

Show HN: MCP-Sentry v2.0 – Zero-dependency firewall and audit proxy for MCP

MCP-Sentry v2.0, a zero-dependency security proxy for the Model Context Protocol, was released as a Show HN project, positioning itself between AI clients such as Claude Desktop, Cursor and Windsurf and any MCP server to intercept JSON-RPC 2.0 traffic in both directions. The tool reports 0.031 ms average latency and blocks attacks in under 0.1 ms, defending against tool poisoning in tools/list, rug-pull schema mutation via SHA-256 hash-locking of each tool's name, description and inputSchema, cross-server secret exfiltration, destructive commands like rm -rf and DROP TABLE, and runaway tool-retry loops that the project says can burn $500+ in API credits overnight. MCP-Sentry v2.0 also adds a human-in-the-loop approval gate for high-risk tools, in-flight redaction of OpenAI, Anthropic, AWS, GitHub, Stripe, PEM, JWT and database-URI secrets, and a SHA-256 hash-chained audit ledger with HMAC and SQLite aimed at SOC2 and EU AI Act readiness.

key takeaway

MCP-Sentry v2.0 wraps any stdio or Streamable HTTP MCP server with one command and pins SHA-256 fingerprints of each tool's name, description and inputSchema to block post-approval rug-pull mutations at 0.031 ms average latency.

read4 min views2 publishedNov 19, 2026
Show HN: MCP-Sentry v2.0 – Zero-dependency firewall and audit proxy for MCP
Image: Michielbdejong (auto-discovered)

Zero external dependencies. Sub-millisecond latency (0.031 ms avg). Bidirectional JSON-RPC 2.0 interception for Claude Desktop, Cursor, Windsurf, and Enterprise MCP Servers.

AI Agents using MCP (stdio or Streamable HTTP) have direct access to your local shell, databases, filesystem, and external APIs — with zero native security boundary. A single poisoned third-party MCP server or stuck agent loop can:

  • Steal ~/.ssh/id_rsa, .env, and AWS/OpenAI keys via hidden Tool Poisoning instructions intools/list .
  • Silently mutate tool definitions after you approve them (Rug-Pull attacks).
  • Exfiltrate sensitive files across servers (read secret via Server A → send out viafetch /email on Server B).
  • Burn $500+ in API credits overnight in an infinite tool-retry loop.
  • Execute destructive rm -rf / or DROP TABLE with no human confirmation or audit trail.

MCP-Sentry v2.0 sits transparently between your AI client and any MCP server — blocking attacks in < 0.1 ms with zero code changes.

┌─────────────────────────────┐
│  Claude / Cursor / Windsurf │
│   or Enterprise AI Agent    │
└──────────────┬──────────────┘
               │ JSON-RPC 2.0 (stdio OR Streamable HTTP)
               ▼
┌─────────────────────────────────────────────────────────────┐
│                    MCP-SENTRY v2.0 GATEWAY                  │
│  ┌─────────────────────┐  ┌──────────────────────────────┐  │
│  │ Inbound (C -> S)    │  │ Outbound (S -> C)            │  │
│  │ • Policy-as-Code    │  │ • Tool Poisoning Scanner     │  │
│  │ • Destructive/SQLi  │  │ • Rug-Pull SHA-256 Lock      │  │
│  │ • Cross-Server DLP  │  │ • Secret Auto-Redaction      │  │
│  │ • Taint Enforcement │  │ • Session Taint Marking      │  │
│  │ • Loop & Cost Cap   │  └──────────────────────────────┘  │
│  │ • HITL Approval UI  │  ┌──────────────────────────────┐  │
│  └─────────────────────┘  │ Cryptographic Audit Ledger   │  │
│                           │ SHA-256 Chain + HMAC + SQLite│  │
│                           └──────────────────────────────┘  │
└──────────────┬──────────────────────────────────────────────┘
               │ Safe, Inspected JSON-RPC 2.0
               ▼
┌─────────────────────────────┐
│   Any Local or Remote MCP   │
│  (Postgres, GitHub, Bash…)  │
└─────────────────────────────┘
  1. Dual-Transport Bidirectional Proxy (stdio + HTTP) - Wrap any local stdio MCP server in 1 line:mcp-sentry wrap -- npx @modelcontextprotocol/server-postgres
  • Reverse-proxy remote HTTP MCP servers with a built-in Live Wireshark-style Firewall Dashboard (/sentry/ui ).
  1. Wrap any local
  2. Real OWASP MCP Threat Engine - Tool Poisoning Defense : Detects hidden<IMPORTANT> /<SYSTEM> tags, stealth exfil directives, and invisible Zero-Width / BiDi Unicode smuggling intools/list .
  • Rug-Pull / Schema Drift Hash-Lock : Pins SHA-256 fingerprints of every tool'sname + description + inputSchema on first sight and blocks post-approval mutation.
  • Cross-Server Taint Tracking & DLP : Scans responses for OpenAI/Anthropic/AWS/GitHub/Stripe/PEM/JWT/DB-URI secrets,redacts them in-flight , taints the session, and blocks subsequent outbound network tools (fetch ,curl ,send_email ).
  • Destructive Command & Path Traversal Blocker : Blocksrm -rf ,DROP TABLE ,TRUNCATE ,curl | bash , reverse shells, and../ traversal.
  1. Human-in-the-Loop (HITL) Approval Gate - In HTTP proxy mode, high-risk tools (execute_sql ,run_command ,transfer_funds ) are suspended in real time until an operator clicksAPPROVE orDENY in the live dashboard.
  2. In HTTP proxy mode, high-risk tools (
  3. Deterministic Infinite-Loop & Budget Circuit Breaker - Halts runaway identical tool-call retry loops and enforces per-minute / per-session hard caps.
  4. Tamper-Evident Cryptographic Audit Ledger (SOC2 / EU AI Act Ready) - Every allow/block/redact decision is hash-chained (SHA-256 ) and signed (HMAC-SHA256 ) into both JSONL and SQLite. Verify zero tampering anytime withmcp-sentry audit --verify .
  5. Every allow/block/redact decision is hash-chained (
  6. Hot-Reloaded Policy-as-Code (sentry.yaml) - Edit tool whitelists, denied paths, allowed domains, and HITL gates without restarting the gateway.
git clone https://github.com/yepinggu66/mcp-sentry.git
cd mcp-sentry
pip install -e .
mcp-sentry bench
{
  "mcpServers": {
    "postgres-guarded": {
      "command": "mcp-sentry",
      "args": ["wrap", "--policy", "sentry.yaml", "--", "npx", "-y", "@modelcontextprotocol/server-postgres", "postgresql://..."]
    }
  }
}
mcp-sentry init
mcp-sentry proxy --upstream http://127.0.0.1:9000/mcp --port 8787 --policy sentry.yaml
mcp-sentry audit --verify

Verified directly via mcp-sentry bench and python -m unittest discover -s tests -v:

Category Attack Vectors Tested Block Rate Avg Latency
Tool Poisoning & Unicode Smuggling Hidden <IMPORTANT> exfil, Zero-Width BiDi, stealth directives 3 / 3 (100%) 0.042 ms
Rug-Pull Schema Drift Post-approval SHA-256 tool mutation 1 / 1 (100%) 0.015 ms
Destructive & Shell/SQL Injection rm -rf / ,DROP TABLE ,TRUNCATE ,curl|bash , reverse shell,base64|sh 6 / 6 (100%) 0.017 ms
Secret Theft, DLP & Path Traversal .env ,~/.ssh/id_rsa ,../ , OpenAI/AWS/GitHub/PEM/Postgres URI 8 / 8 (100%) 0.016 ms
Response Redaction & Taint Exfil In-flight AWS/OpenAI masking + cross-server outbound block 2 / 2 (100%) 0.038 ms
Domain Firewall, HITL, Loop & Ledger Domain deny, HITL suspension, 4th-call loop trip, 1-byte tamper detection 4 / 4 (100%) 0.074 ms
TOTAL 24 Real MCP Attack Vectors 24 / 24 (100.0%) 0.031 ms
── more in #ai-agents 4 stories · sorted by recency
── more on @mcp-sentry 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/show-hn-mcp-sentry-v…] indexed:0 read:4min 2026-11-19 · —