MCP Server
Cyphrex is available as a remote MCP server, listed in the official MCP registry. Any agent running in Claude, Cursor, or any MCP-compatible tool can connect directly.
Connect
Add this to your Claude Desktop or Cursor config:
{
"mcpServers": {
"cyphrex": {
"url": "https://mcp.cyphrex.io/mcp",
"headers": {
"Authorization": "Bearer cprx_live_..."
}
}
}
}Available Tools
register_agent(name, type, description)- Register a new agent and get a Cyphrex agent IDcheck_action(agentId, action)- Check if an action is allowed against the agent behavior profilelog_action(agentId, action, metadata)- Log an action to the audit trailget_audit_log(agentId, limit)- Retrieve recent actions for an agentset_behavior_profile(agentId, profile)- Define what the agent is and is not allowed to doverify_agent(agentId)- Look up an agent identity and blockchain SSN statusscan_mcp_tools_list(agentId, serverUrl, tools)- Scans all tools exposed by an MCP server for threats before useproxy_mcp_request(agentId, upstreamUrl, message)- Proxies an MCP request through Cyphrex threat enforcement
Authenticate with Authorization: Bearer cprx_live_... on the MCP session. Do not pass apiKey in tool arguments; that parameter is deprecated because many MCP clients persist tool arguments in conversation history.
MCP Threat Scanner
Cyphrex scans every MCP tool call in real time and enforces policy at the point of action. When your agent connects to an MCP server through Cyphrex, the gateway checks:
- Tool description scanning detects prompt injection attempts embedded in tool descriptions and names. Poisoned tool lists are not returned to the agent when severity meets the agent
gateway_block_severity(defaulthigh). - Tool poisoning detection diffs tool schemas against stored snapshots. A changed definition at or above the block threshold is withheld from the caller.
- Server URL validation checks MCP server URLs against your agent behavior profile allowed domains. Unauthorized servers are blocked before
tools/callis forwarded, and logged. - Tool result scanning is post execution detection of PII patterns, prompt injection in response content, and unexpected data volumes. It cannot prevent the upstream call; findings are logged as detection, not as a block.
Per agent settings on the behavior profile: gateway_block_severity (default high) and gateway_fail_mode (default closed; a scanner error blocks rather than forwarding).
To use the gateway, route MCP tool calls through:
POST https://mcp.cyphrex.io/mcp/gateway
{
agentId: your-agent-id,
upstreamUrl: https://your-mcp-server.com/mcp,
message: { jsonrpc: "2.0", id: 1, method: "tools/list", params: {} }
}The response includes outcome: "blocked" or "forwarded". Blocked requests have upstream: null. Threats are logged in the dashboard under Security → MCP Threats with severity levels, tool names, and server URLs.
MCP Gateway
Route an agent's MCP tools/call and tools/list traffic through Cyphrex so policy is enforced at the point of action. On tools/call the order is:
- Policy check via the Cyphrex check endpoint, using action type
tool_use - Upstream server validation
- Forward, only if both pass
- Result scan (post execution detection, not prevention)
A block returns a JSON-RPC error with upstream: null. The upstream request is never made. The response includes blockSource: policy when the check endpoint denied the action, or threat when server validation or tool poisoning stopped it.
Two settings on the agent behavior profile control gateway behavior:
gateway_block_severitydefaults tohigh. Threats at this severity and above are blocked.gateway_fail_modedefaults toclosed. Fail closed means a scanner error blocks rather than forwarding. A scanner that cannot run is not evidence that the request is safe. Setopenonly if you want a scanner error to forward with a warning.
Coverage: routing through tool_use means the gateway evaluates off limits actions, rate limits, freeze, and prompt injection, but not allowed_apis or blocked_apis, which apply only to http_call, nor data_scopes, which apply only to data_access. MCP server URL policy is enforced separately by server validation.
Registry
Listed in the official MCP registry as io.github.getcyphrex/cyphrex-mcp