universal-tool-calling-protocol/code-mode
🔌 Plug-and-play library to enable agents to call MCP and UTCP tools via code execution.
This project helps AI agents, such as those used for automation or complex analysis, execute multiple steps and access various tools much more efficiently. It takes a description of a task requiring several tools and, instead of the AI making many individual tool calls, it provides a single block of code that the agent can execute. This makes AI agents faster and more cost-effective when dealing with multi-step workflows.
1,364 stars.
Use this if you are a developer building AI agents that frequently interact with multiple tools or APIs and want to reduce execution time and computational costs.
Not ideal if you are a non-developer or your AI agent only needs to perform simple, single-step actions with one or two tools.
Stars
1,364
Forks
91
Language
Python
License
MPL-2.0
Category
Last pushed
Feb 08, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/mcp/universal-tool-calling-protocol/code-mode"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Related servers
gradion-ai/ipybox
Python code execution sandbox with programmatic MCP tool calling (PTC)
BlackSnufkin/LitterBox
A secure sandbox environment for malware developers and red teamers to test payloads against...
Kiln-AI/Kilntainers
MCP server to give every agent an ephemeral Linux sandboxes for executing shell commands.
buremba/1mcp
Let your agent write code and execute code directly in the browser with WASM
JohanLi233/mcp-sandbox
Python sandboxes for llms