yihui-context-modecontext-mode is an MCP server that saves 98% of your context window by sandboxing tool outputs. It routes large file reads, shell outputs, and web fetches th...
Install via ClawdBot CLI:
clawdbot install 1yihui/yihui-context-modeGrade Limited — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://github.com/mksglu/context-modeAudited Apr 30, 2026 · audit v1.0
Generated May 21, 2026
An AI agent analyzing a monolithic repository with thousands of files uses ctx_batch_execute to run grep and counting commands across the codebase, saving 90%+ tokens compared to reading each file. Ideal for rapid refactoring or migration planning.
A legal analyst researching multiple case law URLs uses ctx_fetch_and_index to index all content into FTS5, then queries via ctx_search. This prevents context overflow from raw web fetches and enables fast cross-referencing.
A quantitative analyst runs complex financial scripts with ctx_execute, receiving only computed results (e.g., NPV, IRR) instead of full file contents. Session continuity across context compactions preserves intermediate variables.
A researcher indexes dozens of PDF abstracts and web pages using ctx_fetch_and_index, then performs iterative BM25 searches. The 90%+ token savings allow fitting more citations and analysis in the context window.
A support bot indexes product documentation and ticket histories, then uses ctx_search for fast retrieval during conversations. Context compaction does not lose session state, enabling coherent multi-turn support.
Offer a free tier with limited operations per day (e.g., 100 tool calls) and a Pro tier with unlimited usage and higher priority. Revenue from monthly subscriptions.
License context-mode to enterprises for internal use, with custom integration, dedicated support, and usage analytics. License fee based on team size or number of agents.
Charge per megabyte of token savings or per 10,000 tool calls. Ideal for high-volume users like SaaS companies with many AI agent deployments.
💬 Integration Tip
Install via a single openclaw command (openclaw mcp set context-mode ...) and immediately start using ctx_batch_execute to replace multiple exec/read calls. For best results, prefix file-heavy queries with 'use batch' to trigger context-mode routing.
Scored May 21, 2026
Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Look up concert setlists and live-music history via setlist.fm. Use when the user asks what songs an artist played at a show, their tour setlists, what was p...
Use this skill whenever you need to store, retrieve, search, or view persistent context using the Alchemyst AI MCP server at mcp.getalchemystai.com/mcp/sse....
Performs safe, platform-aware system cleanup without dependencies, supports dry-run, targeted groups, and optional elevated cleanup on request.
Create and manage AI-powered smart forms, surveys, and quizzes through the Dashform MCP server. Supports open-ended, single-choice, multiple-choice, and rati...