gofannon
by The-AI-Alliance
Overview
A web application for subject matter experts to rapidly prototype AI agents and their corresponding web UIs.
Installation
cd gofannon/webapp/docker/infra && docker compose up --buildEnvironment Variables
- APP_ENV
- STORAGE_PROVIDER
- ADMIN_PANEL_ENABLED
- ADMIN_PANEL_PASSWORD
- S3_ENDPOINT_URL
- AWS_ACCESS_KEY_ID
- AWS_SECRET_ACCESS_KEY
- AWS_DEFAULT_REGION
- S3_BUCKET_NAME
- DATABASE_PROVIDER
- COUCHDB_URL
- COUCHDB_USER
- COUCHDB_PASSWORD
- CLOUDWATCH_LOG_GROUP_NAME
- GCP_PROJECT_ID
- OPENAI_API_KEY
- GEMINI_API_KEY
- ANTHROPIC_API_KEY
- FRONTEND_URL
- APP_ROUTER_CONFIG
- LITELLM_LOGGING_MODE
- VITE_APP_ENV
- VITE_ADMIN_PANEL_ENABLED
Security Notes
The system allows user-provided Python code to be executed directly via `exec` in a sandboxed environment (`_execute_agent_code`), which is an extremely high-risk operation, as robust sandboxing in Python is notoriously difficult to achieve. Wildcard CORS is enabled in local/development environments, which poses a risk if not strictly managed. The ability to specify arbitrary MCP server URLs (`/mcp/tools` endpoint) could lead to Server-Side Request Forgery (SSRF). Hardcoded default credentials for local MinIO and CouchDB (`minioadmin:minioadmin`, `admin:password`) are present in `docker-compose.yml` and `couchdb-init.sh`, which are critical if these defaults are used in production or exposed. The demo application generation, which uses LLM-generated HTML/CSS/JS in an iframe with `allow-scripts` and `allow-same-origin` attributes, introduces a significant XSS risk if the LLM generates malicious code.
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.
npcpy
A comprehensive Python library and framework for building, evaluating, and serving LLM-powered agents and multi-agent systems, integrating fine-tuning capabilities, knowledge graphs, and scalable model operations, with a built-in Flask API server for deployment.
arcade-mcp
A framework and collection of toolkits for building and deploying AI agent servers that integrate with various external services.
volcano-sdk
A TypeScript SDK for building multi-provider AI agents that chain LLM reasoning with external tools and orchestrate multi-agent workflows.