Code mode for MCP tools in Claude Code: one sandboxed JavaScript program instead of many tool calls
View on GitHub ↗Stop flooding Claude's context with MCP results.
code-mode is a Claude Code plugin. Claude writes one JavaScript program that calls your MCP tools in a sandbox, filters and joins the data there, and sends back only the answer.
Install · Demo · Example · How it works · Config
Needs Claude Code and Node.js 22.13+. No dependencies. In a Claude Code session:
Start a new session and ask for anything that needs several MCP calls. Using auto mode? Add allow rules first: Permissions.
https://github.com/user-attachments/assets/468c412f-ecae-4e04-a53b-8a291561a052
Without code-mode With code-mode --- --- Claude calls tools one by one Claude writes one program Every full result lands in context Results are filtered in a sandbox Context fills with raw JSON Only the answer comes back
- Fewer tokens. Intermediate data never enters the context. - Sandboxed. Separate Node process, no file system, CPU limit. No network on macOS and on Linux where unshare -rn works. - Learns your tools. Hints per MCP server (formats, required args, limits). Claude proposes fixes. You approve. - Reusable functions. Programs that work can become saved functions for later sessions, after you read and approve the code. - Your permissions still apply. Every MCP call inside the program gets the normal permission check.
"Which of my open Jira issues have no update in the last 14 days?"
Claude sees a short list of keys and titles, not every full issue.
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/gabe4coding--claude-code-mode.html)
MCP server exposing TypeSafe Jev as typed, calibrated judgment tools: classify, score, check, batched ask. Ships as a Claude Code plugin.
noteflowai/dsh-skills-anywhereReuse Agent Skills across DeepSeek Harness and MCP. Check local SKILL.md files in the browser or CI, with parser diagnostics, file hashes and clear exit codes. Try the Hugging Face playground.
coffeecoproject/layermapLayerMap MCP: a layered map of your codebase for coding agents: callers, callees and the impact of a change, for TypeScript, JavaScript, Go, Python and Java. MCP server, CLI, and plugins for Claude Co
Winterrks/telepathyAllow your coding agents to self discover and collaborate with eachother (Claude Code, Codex, open code and other 9 supported)
adityajha2005/decisionkitFast, cheap, probability-scored decisions for coding agents, scripts and CI. CLI + MCP server + Claude Code plugin for the OpenAI Decisions API and Jev (TypeSafe AI).
osaxyz/sepiaceLong-term memory for coding agents. The sepiace plugin for Claude Code and Codex.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.