MCP Gateway

Monitor and enforce policies for MCP tool calls between AI agents and external services.

The MCP Gateway sits as a transparent proxy between AI agents and MCP servers. Every tool call passes through the Palveron Verify flow: Policy Check → Budget Check → Trace → optional Flare Anchor.

Two Operating Modes

Mode	How it works	Use case
Enforcement Gateway	Palveron forwards HTTP/SSE traffic — tool calls are intercepted, inspected, and forwarded	Coding agents (Cursor, Windsurf, Claude Code), in-house MCP servers
Governance Control Plane	SaaS platforms are registered via MCP connector templates; their tool calls are governed by tool policies	Salesforce Einstein, Microsoft Copilot, ServiceNow (native agents that cannot be proxied)

How It Works

Register an MCP server in the dashboard or via API
Scan the server to discover available tools and their risk levels
Create policies that control which agents can use which tools
Route traffic through the Palveron proxy endpoint
Every tool call produces a tamper-evident trace with optional Flare blockchain attestation

Proxy Endpoint

Agents connect to the Palveron-generated proxy endpoint instead of directly to the MCP server:

POST /api/v1/mcp/proxy/{server_id}
Content-Type: application/json
Authorization: Bearer {project_api_key}

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": { "name": "query_records", "arguments": { "query": "SELECT Id FROM Account" } },
  "id": 1
}

Palveron forwards the JSON-RPC request to the actual MCP server after all checks have passed.

Policy Actions

Four enforcement actions available per tool:

Action	Behavior
`ALLOW`	Tool call is allowed (default when no policy matches)
`DENY`	Tool call is blocked — the agent receives a JSON-RPC error
`REQUIRE_APPROVAL`	Tool call is queued for manual approval (pending approvals expire)
`LOG_ONLY`	Tool call is allowed but produces a detailed audit trace

Security Features

Tool poisoning detection — SHA-256 hash of tool descriptions, alerts on changes (rug-pull detection)
Risk classification — Automatic CRITICAL/HIGH/MEDIUM/LOW based on tool capabilities
Emergency stop — Instantly block all MCP servers or a specific server/agent
Blockchain audit trail — BLOCKED decisions and HIGH/CRITICAL-risk calls are attested on Flare

Connector Templates

11 preconfigured setups for major SaaS platforms and coding agents: Salesforce, Microsoft Copilot, ServiceNow, Slack AI, Teams Copilot, Zendesk AI, Intercom Fin, AWS Bedrock, Azure AI, Cursor, Claude Code. Each template seeds recommended tool policies and triggers an immediate tool scan.

Create via API: POST /api/v1/mcp/servers/from-template { "template": "salesforce" }