# ShadowGate MCP
> Defensive MCP security gateway for AI agents. Gates tool calls, responses, schemas, manifests, trust identity, drift detection, and security reports before agents trust external MCP activity.

## MCP Server URL
https://shadowgate-mcp.mcp.xpay.sh/mcp?key=YOUR_XPAY_KEY

## Tools
- health_check: Return ShadowGate MCP health, version, and active policy. ($0.00/call)
- scan_text: Scan arbitrary text for leaked secrets, prompt injection, risky commands, and sensitive file paths. ($0.00/call)
- analyze_text: 
    Professional public text-analysis tool.

    This merges the practical outputs of:
    - scan_text
    - redact_secrets
    - get_risk_score
    - decide_policy
    - simulate_policy_modes

    Use this as the main public text safety tool.
     ($0.00/call)
- redact_secrets: Return the text with detected secrets and sensitive path snippets redacted. ($0.00/call)
- get_risk_score: Return a 0-100 risk score for a text payload. ($0.00/call)
- decide_policy: Return the policy decision for a payload: allow, redact, or block. ($0.00/call)
- inspect_mcp_response: Scan a response returned by another MCP server before the agent trusts it. ($0.00/call)
- inspect_mcp_tool_call: Scan an outgoing MCP tool call before execution. ($0.00/call)
- gate_mcp_tool_call: Gateway decision for an outgoing MCP tool call. ($0.00/call)
- gate_mcp_response: Gateway decision for an MCP response. ($0.00/call)
- evaluate_mcp_transaction: 
    Evaluate both sides of an MCP interaction:
    1. outgoing tool call arguments
    2. incoming MCP response
     ($0.00/call)
- inspect_tool_schema: Scan an MCP tool schema/description before allowing agents to use it. ($0.00/call)
- review_mcp_manifest: 
    Review a simplified MCP server manifest.

    This is now protected by client_key when SHADOWGATE_CLIENT_KEY is set.
     ($0.00/call)
- scan_batch: 
    Scan multiple text items in one call.

    This is now protected by client_key when SHADOWGATE_CLIENT_KEY is set.
     ($0.00/call)
- simulate_policy_modes: Show how the same text would be handled under monitor, balanced, and strict modes. ($0.00/call)
- get_policy: Return the active ShadowGate policy configuration. ($0.00/call)
- set_policy_mode: Change ShadowGate policy mode: monitor, balanced, or strict. ($0.00/call)
- get_recent_audit_events: Return recent ShadowGate audit events. Raw scanned text is never stored. ($0.00/call)
- get_audit_summary: Return a summary of ShadowGate audit decisions, actions, categories, and severities. ($0.00/call)
- create_security_report: Create a compact security report from recent audit events. ($0.00/call)
- get_server_registry: Return the ShadowGate MCP server trust registry. ($0.00/call)
- get_mcp_server_trust: Return trust status for a specific MCP server. ($0.00/call)
- set_mcp_server_trust: 
    Set trust level for an MCP server.

    Allowed trust levels:
    - trusted
    - untrusted
    - monitor
    - blocked
     ($0.00/call)
- approve_mcp_manifest_identity: Admin tool to approve and persist a manifest trust identity baseline. ($0.00/call)
- get_data_paths: Return ShadowGate data directory paths for policy, registry, and audit logs. ($0.00/call)
- get_security_config: Return ShadowGate admin-auth security configuration without exposing the raw key. ($0.00/call)

## Get Started
1. Get an API key at https://xpay.tools
2. Add the MCP server URL to your MCP client config (Claude, Cursor, Windsurf, etc.)
3. Pay per tool call from your XPay wallet — no subscriptions

## Connection Config
```json
{
  "mcpServers": {
    "shadowgate-mcp": {
      "url": "https://shadowgate-mcp.mcp.xpay.sh/mcp?key=YOUR_XPAY_KEY"
    }
  }
}
```

## Pricing
- health_check: $0.00/call
- scan_text: $0.00/call
- analyze_text: $0.00/call
- redact_secrets: $0.00/call
- get_risk_score: $0.00/call
- decide_policy: $0.00/call
- inspect_mcp_response: $0.00/call
- inspect_mcp_tool_call: $0.00/call
- gate_mcp_tool_call: $0.00/call
- gate_mcp_response: $0.00/call
- evaluate_mcp_transaction: $0.00/call
- inspect_tool_schema: $0.00/call
- review_mcp_manifest: $0.00/call
- scan_batch: $0.00/call
- simulate_policy_modes: $0.00/call
- get_policy: $0.00/call
- set_policy_mode: $0.00/call
- get_recent_audit_events: $0.00/call
- get_audit_summary: $0.00/call
- create_security_report: $0.00/call
- get_server_registry: $0.00/call
- get_mcp_server_trust: $0.00/call
- set_mcp_server_trust: $0.00/call
- approve_mcp_manifest_identity: $0.00/call
- get_data_paths: $0.00/call
- get_security_config: $0.00/call

Note: Searching and listing content is free. Reading full articles in markdown is charged. All tools require a valid API key.

## About
Powered by XPay — pay-per-use API access for AI agents.
https://xpay.tools