Seraph
Seraph MCP
Seraph is a hosted remote Model Context Protocol (MCP) server operated by Kondux. It gives AI agents access to crypto transaction firewall and risk tools through a managed, OAuth-protected MCP endpoint.
Public name:
SeraphRegistry ID:
io.kondux/seraphMCP endpoint:
https://seraph.kondux.io/mcpTransport: Streamable HTTP
Authentication: OAuth 2.1 through Seraph/Privy. API-key access remains available for existing integrations.
Operator: Kondux,
https://kondux.io
This repository contains public registry metadata and installation examples only. The production service implementation is proprietary and is not included here.
Quick Start
Create or sign in to a Seraph account at
https://seraph.kondux.io.Complete onboarding in the Seraph console.
Add the hosted MCP endpoint to your MCP client or registry submission:
https://seraph.kondux.io/mcpClients that support MCP OAuth discovery should start authentication automatically from the Seraph MCP endpoint.
Related MCP server: actiongate
Registry Metadata
The official MCP Registry manifest is in server.json. It uses the branded DNS-owned namespace:
io.kondux/seraphInstallation Examples
Notes for Registries
Use this public repository URL when a registry asks for a GitHub repository:
https://github.com/Kondux/seraph-mcp-publicUse this URL when a registry asks for the hosted MCP server endpoint:
https://seraph.kondux.io/mcpSeraph is a remote hosted MCP server. There is no local package to install from this repository.
License
The documentation, examples, and registry metadata in this repository are MIT licensed. The hosted Seraph service and its private implementation are separate proprietary Kondux software.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityAmaintenanceA security proxy and active firewall for the Model Context Protocol that protects host systems from malicious intent, prompt injection, and data exfiltration. It acts as an interception layer between AI agents and tools, providing real-time verification and multi-layered defense mechanisms.Last updated12MIT
- Alicense-qualityCmaintenancePre-execution safety layer for autonomous agent wallets. Risk scoring, transaction simulation, and policy enforcement via MCP.Last updatedMIT
- Alicense-qualityFmaintenanceReal-time DeFi analytics MCP server for AI agents. Provides token risk analysis, yield scanning, and wallet exposure checking across Base, Ethereum, and Arbitrum.Last updated271MIT
- Alicense-qualityAmaintenanceWeb3 MCP proxy server for AI agents: EVM execution, DeFi swaps, bridges, advanced orders, market data, wallet management, and confirmation-gated writes.Last updated83MIT
Related MCP Connectors
KYC, KYB, AML, wallet screening, transaction monitoring, and fraud workflows for AI agents.
Solana token risk-scoring MCP server for AI trading agents with insider wallet cluster detection.
Pay-per-call cybersecurity for AI agents: vuln scans, threat intel, compliance, code security.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Kondux/seraph-mcp-public'
If you have feedback or need assistance with the MCP directory API, please join our Discord server