Alimenter votre agent
Installation de l'éditeur. Ce n'est pas un endpoint PlugMCP.
Host a copy with our keys and logs.
Pas encore de version packagée dans le registre. Suivez le README du dépôt.
URL distante ou commande sur votre machine ? Ce qui distingue les deux installations
Exécuter sur PlugMCP
A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.
LancerDe l'éditeur
Context SherpaContext Sherpa is a specialized platform for Context Engineering. It bridges the gap between developers and AI coding agents by providing LLMs with the precise, high-fidelity signals they need to operate with expert-level accuracy while dramatically reducing token consumption.
Context Sherpa MCP server provides code mapping, deterministic feedback loops, and tiered inference for AI coding agents to increase accuracy and optimize token usage.
Agentic coding tools often struggle with either "hallucinating" codebase relationships or overwhelming their context windows with irrelevant files. Context Sherpa solves this through two primary goals:
Traditional tools like grep are fast but lack symbol awareness, while semantic search often returns noisy, over-processed results. Context Sherpa's tool suite is designed as a high-fidelity alternative:
Of course the benefit of text embeddings in a vector database and other traditional methods is that they are more of a one size fits all solution. They can be used for many programming languages and even non-code files. Remember that a different SCIP tool must be used for each programming language. Lucky for you, you can use both. Context Sherpa will add SCIP tools for more languages in the future.
ast-grep and natural language feedback.Context Sherpa is not just a toolset; it's an intelligent environment. There are some specialized resources for AI agents found in the .agents/ directory:
For a deep dive into best practices, see our Agent Guidelines for Context Engineering.
Context Sherpa is a single executable that adapts to your needs:
Download the latest version for your platform from GitHub Releases.
.exe and run it./Applications, and clear quarantine if necessary:
xattr -d com.apple.quarantine /Applications/Context-Sherpa.app
chmod +x).[!IMPORTANT] Security Notice: Pre-built binaries are currently not signed. When running the application for the first time, you may encounter OS security warnings (e.g., Windows SmartScreen or macOS Gatekeeper). You will need to manually allow the application to run.
This is a known limitation of the current release process. Future pre-built binaries will undergo formal code signing for convenience. Building from source (instructions below) avoids these security warnings.
Context Sherpa is built with Go and Wails. For detailed building instructions, please see BUILDING.md.
cd frontend && npm install && npm run build && cd ..
# Install Wails CLI if not already present
go install github.com/wailsapp/wails/v2/cmd/wails@latest
# Build the binary
wails build
AI agents connected to Context Sherpa gain access to a powerful set of tools for structural, symbolic, and semantic analysis.
For a full list of available tools and their parameters, see TOOLS.md.
Add Context Sherpa to your AI agent's mcp_settings.json:
{
"mcpServers": {
"context-sherpa": {
"command": "context-sherpa",
"args": ["--projectRoot", "/path/to/your/project"]
}
}
}
Context Sherpa is built on a three-layer "Tiered Inference" strategy that balances speed, cost, and intelligence:
By offloading Tier 1 and Tier 2 tasks to Context Sherpa, you save up to 90% in token costs while significantly increasing the accuracy of Tier 3 strategic work.
Context Sherpa uses 3rd party tools to provide high-fidelity intelligence. These can be managed directly in the GUI Settings area:
Context Sherpa leverages several incredible open-source projects:
scip-go, scip-typescript, and scip-python.This project is licensed under the MIT License - see the LICENSE file for details.
Context Sherpa MCP server provides code mapping, deterministic feedback loops, and tiered inference for AI coding agents to increase accuracy and optimize token usage.
Outils
Pas encore de liste d'outils. Les serveurs distants en obtiennent une après le premier contrôle d'état.
FAQ
Copiez sur cette page la configuration stdio pour Cursor, Claude Desktop, Claude Code ou VS Code. Elle utilise l'installation de l'éditeur, pas un proxy PlugMCP.
Aucune variable d'environnement requise n'est indiquée sur cette fiche.
Context Sherpa s'exécute en local via stdio.
Dernière vérification : 2026-11-05. Context Sherpa MCP server provides code mapping, deterministic feedback loops, and tiered inference for AI coding agents to increase accuracy and optimize token usage.
