agentor
by CelestoAI
Overview
Deploy scalable AI agents with tool integrations (weather, email, GitHub, etc.) and support for A2A and MCP communication protocols.
Installation
python examples/community/litserve_integration/main.pyEnvironment Variables
- CELESTO_API_TOKEN
- CELESTO_API_KEY
- OPENAI_API_KEY
- LLM_API_KEY
- WEATHER_API_KEY
- GEMINI_API_KEY
- GOOGLE_USER_CREDENTIALS
Security Notes
The framework offers powerful tools (e.g., PostgreSQLTool, GitTool, FetchTool, GitHubTool, SlackTool, GmailTool) that can execute arbitrary code, modify file systems, perform network requests (SSRF, internal scanning), and interact with external services based on LLM outputs. These tools accept direct string inputs from the LLM, making the system highly vulnerable to prompt injection attacks if not carefully configured with strict input validation, sandboxing, and access controls. An LLM could be coerced to perform unauthorized actions or exfiltrate data.
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.
toolsdk-mcp-registry
A unified registry and API gateway for discovering, managing, and executing Model Context Protocol (MCP) servers, supporting local and secure sandbox execution with OAuth 2.1 integration.
AgentUp
A developer-first framework for building, deploying, and managing secure, scalable, and configurable AI agents, supporting various agent types (reactive, iterative) and the Model-Context Protocol (MCP) for seamless interactions.
Polymcp
A comprehensive toolkit and agent framework for building Model Context Protocol (MCP) servers and orchestrating them with Large Language Models (LLMs) across Python and TypeScript environments.