QWEN · DEEPSEEK · MCPS · AGENTPASS

Run low-cost AI locally.
Secure, zero-trust, end-to-end.

Free open models — Qwen, DeepSeek — on your own machine or cloud. A cryptographic identity on every agent, a signed-and-verified gate on every tool call. Your data never leaves. Your API bill is zero.

🏢 RUNS IN YOUR DC OR CLOUD💸 ZERO API COST🛡️ SIGNER + VERIFIER INCLUDED
The gap

The protocol every agent speaks has no security.
We built the secure version.

730M+

MCP SDK downloads in the last 12 months (npm, @modelcontextprotocol/sdk). The agent world runs on MCP.

May 2026

The NSA warned MCP ships with no security model — serialization, trust-boundary and agent-misuse risks.

MCPS

The cryptographic layer that closes that gap: agent identity, per-message signing, integrity, replay protection.

MCP exploded to hundreds of millions of installs before it had an authentication or integrity layer — and in May 2026 the NSA said so out loud.

MCPS is that missing layer — authored by CyberSecAI and submitted to the IETF. Pair it with a free local model and you get powerful AI that's cheap, private, and provable — end to end.

Why local

Local Qwen + MCPS solves what cloud AI can't

Your stack. Your data. All local and compliant.

🔒

Data sovereignty

The model runs on your machine or in your own cloud. Prompts, documents, and tool data never leave your perimeter — nothing is sent to a third-party API.

📋

Compliance by design

Data residency, signed audit trails and per-action attribution map straight onto SOC 2, GDPR and the OWASP/NSA MCP guidance — see the mapping below.

💸

Zero API cost

Open weights, run free on hardware you already own. No per-token bill, no rate limits, no vendor lock-in. Scale without scaling cost.

🛡️

Zero-trust, enforced

Every tool call is signed by the agent's identity and verified at the gate. Unsigned, tampered or replayed calls are rejected before they run.

Compliance, mapped

Aligned to the standards that matter

How a local-Qwen + MCPS + AgentPass deployment helps you meet each control. Links go to the source standard.

Security challengeHow this stack answers itAligned standard
Agent identityAgentPass signed passport (P-256), L0–L4 trust levels OWASP MCP Cheat Sheet · AISVS (C10)
Per-message integrity + replayMCPS signs every tool call; verifier checks signature, nonce & identity at the gate NSA MCP CSI (May 2026) · OWASP MCP Cheat Sheet
Tool poisoning / tamperingTool-definition signatures detect altered or malicious tools OWASP MCP Cheat Sheet · AISVS
Data residency / sovereigntyModel + data stay on-premise or in your own cloud — nothing leaves SOC 2 (Confidentiality)GDPR
Audit & non-repudiationSigned, tamper-evident transcript of every agent action SOC 2 (CC monitoring) · AISVS
The building blocks

What you're building on

🔐

MCPS — the secure layer for MCP

The "HTTPS of the agent era." Adds agent identity, per-message signing, tool-integrity and replay protection to MCP without changing the protocol. Authored by CyberSecAI, submitted to the IETF (draft-sharif-mcps-secure-mcp).

🪪

AgentPass — identity for agents

A signed passport that says who an agent is — alias, public key, L0–L4 trust, revocation. Self-signed locally (no PKI), or registry-attested for cross-org trust. agentpass.co.uk.

Architecture

End-to-end security.
Fully aligned with modern governance frameworks.

Everything runs inside your perimeter — no request ever leaves it. Each tool call is signed by the agent, then verified at the gate before it touches your tools.

Runs locally · all under your control · no external calls Cloud APIs · never called

Local model

Qwen / DeepSeek via Ollama

FREE
prompt

Your agent

carries an AgentPass passport (signed ID)

signs · MCPS

The gate — verifier

checks signature + nonce + identity

INCLUDED
✓ verified

Your tools & data

only trusted calls ever reach them

✓ signed & fresh → runs  ·  ✗ unsigned / tampered / replayed → rejected at the gate Bad calls never reach your tools — the verifier enforces it; you don't trust the agent blindly.

Trust gating L0→L4 Signing ECDSA P-256 Compliance IETF · OWASP · NSA
Quickstart

Build it in 3 steps — all free, all local

We ship both halves — the signer and the verifier.

1

Run a free model

Qwen or DeepSeek via Ollama — OpenAI-compatible, offline.

# on your machine
ollama pull qwen3:14b
ollama serve
2

The agent — signs

SDK gives it an AgentPass identity, MCPS-signs every call.

# SDK by request: contact@agentsign.dev
from secure_qwen import SecureQwenAgent
a = SecureQwenAgent(model="qwen3:14b",
  mcp_servers={"tools":{...}})
a.run("add 17 and 25")
3

The verifier — enforces

One line wraps your MCP server. Unsigned / tampered / replayed → rejected.

from mcp_secure import secure_mcp
secure_mcp(server)
# ← boom. gated.
Read the standards

Don't take our word — read theirs

Build on Qwen.
Build secure.
Build to comply.

Free local AI, cryptographic agent identity, and compliance-ready audit — one stack, end to end, entirely under your control.

© 2026 CyberSecAI Ltd · BUSL-1.1 · free to use, self-host & build on · contact@agentsign.dev