admin
Verified Safeby decocms
Overview
DecoCMS is a Context Management System (MCP Mesh) designed for building, managing, and deploying AI-native applications, agents, and workflows using the Model Context Protocol (MCP). It centralizes AI context, data access, tools, and policies for secure and observable AI operations.
Installation
npm run devEnvironment Variables
- SUPABASE_URL
- SUPABASE_SERVER_TOKEN
- DECO_CHAT_API_JWT_PRIVATE_KEY
- DECO_CHAT_API_JWT_PUBLIC_KEY
- LLMS_ENCRYPTION_KEY
- OPENROUTER_API_KEY
- WALLET_API_KEY
- STRIPE_SECRET_KEY
- CF_API_TOKEN
- CF_ZONE_ID
- CF_ACCOUNT_ID
- DATABASE_URL
- MESH_JWT_SECRET
Security Notes
The system utilizes extensive input validation with Zod and implements a sandboxing mechanism (QuickJS via `@deco/cf-sandbox`) for executing user-defined tool and workflow code, significantly mitigating direct code injection risks. Secrets (API keys, tokens) are managed via environment variables and an encryption vault (`CredentialVault`) for sensitive data at rest. Access control (RBAC) is granular, verifying user permissions per tool and connection. Potential risks inherent to any platform executing user-provided code are acknowledged, but strong countermeasures are in place.
Similar Servers
mcp-use
A full-stack framework for building Model Context Protocol (MCP) servers, MCP clients, and AI agents in both Python and TypeScript, supporting interactive UI widgets and robust debugging.
mcp-kit
A CLI tool for scaffolding Model Context Protocol (MCP) applications, either as servers providing tools, resources, and prompts, or clients consuming them.
boilerplate-mcp-server
This boilerplate provides a production-ready foundation for developing custom Model Context Protocol (MCP) servers in TypeScript to connect AI assistants with external APIs and data sources, exemplified by an IP geolocation lookup tool.
1xn-vmcp
An open-source platform for composing, customizing, and extending multiple Model Context Protocol (MCP) servers into a single logical, virtual MCP server, enabling fine-grained context engineering for AI workflows and agents.