MCP Governance Overview

Field	Value
Document ID	ASCEND-MCP-001
Version	1.0.0
Last Updated	December 19, 2025
Author	Ascend Engineering Team
Publisher	OW-KAI Technologies Inc.
Classification	Enterprise Client Documentation
Compliance	SOC 2 CC6.1/CC6.2, PCI-DSS 7.1/8.3, HIPAA 164.312, NIST 800-53 AC-2/SI-4

Reading Time: 8 minutes | Skill Level: Advanced

Overview

ASCEND provides comprehensive governance for Model Context Protocol (MCP) servers, extending the same enterprise-grade security controls used for AI agents to MCP tool use. Every MCP server action is evaluated, approved, and audited using unified governance policies.

What is MCP?

Model Context Protocol (MCP) is a standard for AI models to interact with external tools and data sources. MCP servers provide capabilities like:

• File System Access - Read/write files
• Database Queries - Execute SQL queries
• API Calls - Interact with external services
• Code Execution - Run code in sandboxes

Why MCP Governance?

Without governance, MCP servers present significant security risks:

Risk	Without Governance	With ASCEND
Unauthorized file access	Unrestricted	Risk-assessed + approved
Database manipulation	Open access	Policy-controlled
Sensitive data exposure	No protection	PII detection + masking
Compliance violations	Unknown	Audit trail + evidence

MCP Governance Architecture

+---------------------------------------------------------------------------------+
|                          MCP GOVERNANCE SYSTEM                                   |
+---------------------------------------------------------------------------------+
|                                                                                  |
|   MCP CLIENT (Claude, etc.)                                                     |
|   +-------------------------------------------------------------------------+   |
|   |                                                                          |   |
|   |   Tool Request: filesystem.read_file("/etc/passwd")                     |   |
|   |                                                                          |   |
|   +-------------------------------------------------------------------------+   |
|                              |                                                   |
|                              v                                                   |
|   +-------------------------------------------------------------------------+   |
|   |                    ASCEND MCP GATEWAY                                    |   |
|   |                                                                          |   |
|   |   1. Intercept MCP request                                              |   |
|   |   2. Evaluate against policies                                          |   |
|   |   3. Calculate risk score                                               |   |
|   |   4. Route to approval workflow (if needed)                             |   |
|   |   5. Execute or deny                                                    |   |
|   |   6. Log to audit trail                                                 |   |
|   |                                                                          |   |
|   +-------------------------------------------------------------------------+   |
|                              |                                                   |
|          +-------------------+-------------------+                               |
|          |                                       |                               |
|          v                                       v                               |
|   +------------------+                   +------------------+                    |
|   | AUTO-APPROVED    |                   | PENDING APPROVAL |                    |
|   | Risk < threshold |                   | Risk >= threshold|                    |
|   | -> Execute       |                   | -> Human review  |                    |
|   +------------------+                   +------------------+                    |
|          |                                       |                               |
|          +-------------------+-------------------+                               |
|                              |                                                   |
|                              v                                                   |
|   +-------------------------------------------------------------------------+   |
|   |                    MCP SERVER                                            |   |
|   |   - Filesystem    - Database    - API    - Code Execution               |   |
|   +-------------------------------------------------------------------------+   |
|                                                                                  |
+---------------------------------------------------------------------------------+

Unified Governance

ASCEND provides a unified governance model for both AI agents and MCP servers:

Feature	AI Agents	MCP Servers
Risk Assessment	0-100 score	0-100 score
Policy Engine	Smart Rules	Smart Rules
Approval Workflow	Multi-level	Multi-level
Audit Trail	Immutable	Immutable
Kill Switch	Supported	Supported

Unified Authorization Center

# Get all AI actions (agents + MCP) in unified view
curl "https://pilot.owkai.app/api/mcp-governance/actions/all?action_type_filter=all" \
  -H "Authorization: Bearer <admin_jwt>"

Response:

{
  "total": 25,
  "actions": [
    {
      "id": "act_agent_001",
      "action_type": "agent_action",
      "title": "Agent trading-bot: trade_execution",
      "risk_score": 65,
      "status": "pending_approval"
    },
    {
      "id": "act_mcp_001",
      "action_type": "mcp_server_action",
      "title": "Filesystem: read_file",
      "server_id": "filesystem-server",
      "namespace": "filesystem",
      "verb": "read_file",
      "risk_score": 45,
      "status": "auto_approved"
    }
  ]
}

MCP Action Evaluation

Evaluate MCP Action

curl -X POST "https://pilot.owkai.app/api/mcp-governance/evaluate" \
  -H "Authorization: Bearer <jwt_token>" \
  -H "Content-Type: application/json" \
  -d '{
    "server_id": "filesystem-server",
    "namespace": "filesystem",
    "verb": "read_file",
    "resource": "/data/reports/financial.csv",
    "parameters": {
      "encoding": "utf-8"
    },
    "session_id": "session_abc123",
    "client_id": "claude-desktop"
  }'

Response:

{
  "action_id": "mcp_act_xyz789",
  "decision": "EVALUATE",
  "status": "PENDING_APPROVAL",
  "risk_score": 72,
  "risk_level": "HIGH",
  "requires_approval": true,
  "approval_level": 3,
  "reason": "Financial data access requires manager approval",
  "estimated_review_time_minutes": 15
}

Decision Types

Decision	Description	Action
ALLOW	Auto-approved	Execute immediately
DENY	Policy blocked	Return error
EVALUATE	Human review needed	Queue for approval

Risk Assessment

Risk Factors

# MCP-specific risk factors
MCP_RISK_FACTORS = {
    "sensitive_path": {
        "patterns": ["/etc/", "/var/secrets/", "*.pem", "*.key"],
        "weight": 30
    },
    "write_operation": {
        "verbs": ["write_file", "delete_file", "create_directory"],
        "weight": 25
    },
    "database_mutation": {
        "verbs": ["execute_query", "insert", "update", "delete"],
        "weight": 35
    },
    "external_api": {
        "namespaces": ["http", "api", "webhook"],
        "weight": 20
    },
    "pii_detected": {
        "data_types": ["ssn", "credit_card", "health_data"],
        "weight": 40
    }
}

Risk Score Calculation

Risk Score = Base Score + Sum(Applicable Risk Factors)

Example:
- Base Score: 20
- sensitive_path (/etc/): +30
- read_operation: +0
- Total: 50 (MEDIUM risk)

MCP Server Registration

Register Server

curl -X POST "https://pilot.owkai.app/api/mcp-governance/servers/register" \
  -H "Authorization: Bearer <admin_jwt>" \
  -H "Content-Type: application/json" \
  -d '{
    "server_id": "filesystem-server",
    "server_name": "Filesystem Access Server",
    "endpoint_url": "stdio://filesystem-server",
    "trust_level": "restricted",
    "capabilities": {
      "namespaces": ["filesystem"],
      "verbs": ["read_file", "write_file", "list_directory"]
    }
  }'

Trust Levels

Level	Description	Default Approval
trusted	Verified internal server	Auto-approve low risk
restricted	Standard server	Evaluate medium+ risk
sandbox	Untrusted/testing	Require approval for all

List Servers

curl "https://pilot.owkai.app/api/mcp-governance/servers?active_only=true" \
  -H "Authorization: Bearer <admin_jwt>"

Response:

{
  "total": 3,
  "servers": [
    {
      "server_id": "filesystem-server",
      "server_name": "Filesystem Access Server",
      "trust_level": "restricted",
      "is_active": true,
      "total_actions": 1250,
      "failed_actions": 5,
      "last_seen": "2025-12-15T10:30:00Z",
      "capabilities": {
        "namespaces": ["filesystem"],
        "verbs": ["read_file", "write_file", "list_directory"]
      }
    }
  ]
}

Approval Workflow

Get Pending Actions

curl "https://pilot.owkai.app/api/mcp-governance/actions/pending?risk_level=HIGH" \
  -H "Authorization: Bearer <admin_jwt>"

Approve/Deny Action

curl -X POST "https://pilot.owkai.app/api/mcp-governance/actions/mcp_act_xyz789/approve" \
  -H "Authorization: Bearer <admin_jwt>" \
  -H "Content-Type: application/json" \
  -d '{
    "action_id": "mcp_act_xyz789",
    "approval_decision": "APPROVE",
    "approval_reason": "Verified business need for financial report access"
  }'

Analytics Dashboard

curl "https://pilot.owkai.app/api/mcp-governance/analytics/dashboard?time_range_hours=24" \
  -H "Authorization: Bearer <admin_jwt>"

Response:

{
  "time_range_hours": 24,
  "summary": {
    "total_actions": 1250,
    "pending_approvals": 12,
    "auto_approved": 1180,
    "denied": 58
  },
  "risk_distribution": [
    {"risk_level": "LOW", "count": 850},
    {"risk_level": "MEDIUM", "count": 320},
    {"risk_level": "HIGH", "count": 70},
    {"risk_level": "CRITICAL", "count": 10}
  ],
  "server_activity": [
    {
      "server_id": "filesystem-server",
      "server_name": "Filesystem Access",
      "total_actions": 800,
      "avg_risk_score": 35.5
    }
  ]
}

Real-Time Monitoring

WebSocket Connection

const ws = new WebSocket('wss://pilot.owkai.app/api/mcp-governance/ws/realtime');

ws.onmessage = (event) => {
    const update = JSON.parse(event.data);
    console.log('MCP Governance Update:', update);
    // {
    //   type: 'mcp_governance_update',
    //   pending_actions: 12,
    //   high_risk_actions: 3,
    //   system_status: 'operational'
    // }
};

Best Practices

1. Defense in Depth

# Layer multiple controls
{
    "trust_level": "restricted",
    "require_approval_by_default": True,
    "path_allowlist": ["/data/public/", "/tmp/"],
    "path_denylist": ["/etc/", "/var/secrets/"]
}

2. Least Privilege

# Grant minimum necessary capabilities
{
    "capabilities": {
        "verbs": ["read_file"],  # No write access
        "path_patterns": ["/data/reports/*"]  # Specific paths only
    }
}

3. Monitor and Alert

# Set up anomaly detection
{
    "alerts": {
        "high_risk_spike": True,
        "new_path_access": True,
        "unusual_hours": True
    }
}

Next Steps

• MCP Policies - Configure governance policies
• Server Registration - Register MCP servers
• Unified Governance - Agents + MCP

---

Document Version: 1.0.0 | Last Updated: December 2025