Managed Secure MCP -- MCPS -- Build. Secure. Scale.
Now in Public Beta

Secure MCP. Zero Trust for AI Agents. End-to-End Security.

Zero trust identity for autonomous AI agents. Every action signed. Every tool gated. Every agent verified. No identity, no trust.

Message integrity verification, replay protection, tool definition monitoring, and agent identity -- all with one URL change.

0
Requests Signed
0
Replays Blocked
0
Active Agents
0
Tool Mutations Detected

What MCPSaaS does

🔒

Message Integrity

Every message is verified end-to-end. If anything is modified in transit -- by proxies, middleware, or compromised dependencies -- it's detected and blocked.

🔄

Replay Protection

Every request is unique. Captured messages cannot be re-sent. Centralised tracking across all your agents with automatic expiry.

🛡

Tool Integrity

Tool definitions are fingerprinted at discovery. If a server silently changes a tool after you approved it (rug pull), the call is blocked before execution.

🎯

Agent Identity

Every agent gets a verifiable identity with trust levels L0-L4. Servers set minimum trust requirements. No more anonymous tool calls.

📄

Audit Trail

Full structured logging in JSON and syslog (RFC 5424). Feed directly into Cribl, Splunk, Datadog, or any SIEM. Complete non-repudiation.

Zero Friction

Change one URL in your MCP config. No SDK, no library, no key management. Your MCP server doesn't know we exist.

The MCP Security Problem

MCP (Model Context Protocol) is the standard for connecting AI agents to external tools. Adopted by Anthropic, OpenAI, Google, Microsoft, and AWS. But it was built for functionality, not security. Here's what's missing.

No Message Integrity

Every JSON-RPC message between agent and tool server travels without any integrity verification. Any intermediary -- corporate proxies, CDN workers, compromised dependencies -- can modify parameters without detection.

No Replay Protection

Captured MCP messages can be re-sent by an attacker to repeat sensitive operations. There is no nonce, sequence number, or timestamp binding to detect duplicates.

No Tool Verification

Tool definitions can change after initial approval. A tool called 'read_file' today could silently become 'read_file_and_exfiltrate' tomorrow. No hash-pinning, no mutation detection.

No Agent Identity

Agents authenticate with bearer tokens or API keys. A stolen token means full impersonation. There is no way to verify which specific agent made a request.

TLS Is Not Enough

Transport security terminates at every hop. Corporate HTTPS inspection proxies (Zscaler, Palo Alto, Fortinet) routinely decrypt, inspect, and re-encrypt traffic. After termination, messages are plaintext.

OAuth Doesn't Cover It

OAuth proves who you are but doesn't protect what you send. A valid OAuth token with a modified message body is accepted without question. No message signing, no payload integrity.

30 CVEs in 60 Days

MCP has the fastest-growing attack surface in AI infrastructure. Critical vulnerabilities including RCE (CVE-2025-6514, CVSS 9.6), authentication bypass, and unauthenticated API exposure.

38% Have No Auth

Industry scans of 500+ MCP servers found that 38% lack any form of authentication. Anyone who can reach the endpoint can invoke any tool.

MCPSaaS closes every one of these gaps. One URL change. Zero code modifications.

See How

Get started in 30 seconds

Change your MCP endpoint URL. That's it.

Copy
// Before (no security) endpoint: "https://your-mcp-server.com/mcp" // After (fully signed, verified, audited) endpoint: "https://mcpsaas.co.uk/proxy?target=https://your-mcp-server.com/mcp"

Why MCPSaaS?

Existing security standards leave critical gaps in agent communication. MCPSaaS closes all of them.

RequirementTLSOAuthJWTJWSDPoPmTLSMCPS
Identity Server only Yes Yes No Key bind Both Passport (L0-L4)
Message Integrity No No Token only Yes No No Every message
Replay Protection No No Expiry No Partial No Nonce + timestamp
Tool Integrity No No No No No No SHA-256 hash-pin
Trust Levels No No No No No No L0-L4 hierarchy
Revocation CRL Expiry Expiry No No CRL Real-time
Non-repudiation No No No Yes No No Yes

Test Results

180
Security tests across 19 attack categories
21
Attack surfaces identified in standard MCP
0
Unsigned messages when MCPSaaS is enabled
100%
Replay attacks blocked

Real-World Threats Blocked

🚫

Corporate Proxy MITM

TLS-terminating proxies can modify messages after decryption.

CDN/Edge Worker Injection

Cloudflare Workers or CDN scripts can intercept and modify MCP traffic.

📦

Supply Chain Compromise

Compromised npm dependencies can intercept from inside your MCP server.

🔄

Replay Attacks

Captured requests can be re-sent to repeat sensitive operations.

🛠

Tool Rug Pulls

MCP servers can silently change tool definitions after approval.

🌐

DNS Hijacking

Fake servers at hijacked domains proxy traffic while modifying it.

Ready to secure your MCP connections?

Start free. No credit card required.

Start Free

Documentation

Everything you need to secure your MCP connections.

Quick Start

# 1. Sign up and get your API key curl -X POST https://mcpsaas.co.uk/api/signup \ -H "Content-Type: application/json" \ -d '{"email":"you@company.com","password":"secure123"}' # 2. Add a proxy endpoint curl -X POST https://mcpsaas.co.uk/api/proxies \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"name":"My MCP Server","target":"https://mcp-server.com/mcp"}' # 3. Use the proxy URL in your MCP config endpoint: "https://mcpsaas.co.uk/proxy/PROXY_ID"

API Reference

MethodEndpointDescription
POST/api/signupCreate account
POST/api/loginGet API key
GET/api/dashboardDashboard stats
POST/api/proxiesCreate proxy endpoint
GET/api/proxiesList proxy endpoints
GET/api/auditAudit log (JSON)
GET/api/audit/syslogAudit log (RFC 5424 syslog)
POST/api/keys/rotateRotate API key
GET/proxy/:idProxy endpoint (use in MCP config)

Security Model

MCPSaaS implements the MCPS protocol as defined in IETF Internet-Draft draft-sharif-mcps-secure-mcp.

LayerControlStandard
Message SigningECDSA P-256 per-message signaturesNIST FIPS 186-5
CanonicalizationDeterministic JSON serializationRFC 8785 (JCS)
Replay ProtectionNonce + timestamp windowMCPS SEP-2395
Tool IntegritySHA-256 hash-pinningMCPS SEP-2395
Agent IdentityCryptographic passports (L0-L4)MCPS SEP-2395
Audit OutputStructured JSON + syslogRFC 5424

Simple, transparent pricing

Start free. Scale as you grow.

Free
$0
Forever free
5 agents
1,000 signed requests/mo
7-day audit retention
Community support
1 proxy endpoint
Get Started
Popular
Pro
$29/mo
For growing teams
50 agents
100,000 signed requests/mo
90-day audit retention
Email support
10 proxy endpoints
Custom trust levels
Start Free Trial
Enterprise
$299/mo
For security teams
Unlimited agents
Unlimited requests
1-year audit retention
Priority support + SLA
Unlimited proxy endpoints
Custom trust authority
SIEM integration
SSO / SAML
Contact Sales

Dashboard

Real-time overview of your MCP security posture.

Requests Signed
0
All signed
Replays Blocked
0
Protected
Active Agents
0
Tool Mutations
0
Clean

Request Volume (24h)

Security Posture

Agent Trust Levels

Activity Timeline (7 days)

Recent Activity

No activity yet. Configure a proxy endpoint to start.