Context-Engine

Overview

Context Engine is an MCP server that enhances AI coding assistants with 30+ tools for semantic code search, symbol intelligence, memory storage, and cross-repo tracing. It integrates with popular coding assistants like Claude, Cursor, and Codex, providing a bridge between development environments and AI capabilities. The server offers batch queries for token savings, pattern searches across languages, and git history functionality to significantly improve AI-assisted development workflows.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• search

  Default tool that auto-routes queries to the best backend (semantic search, Q&A, symbol graph, tests, config)

  Try:Find functions that handle user authenticationTry:Search for database connection code
• symbol_graph

  Navigate code by finding callers, callees, definitions, importers, and subclasses

  Try:Show all callers of the calculateTotal functionTry:Find all implementations of the PaymentProcessor interface
• batch_search

  Run multiple search queries in a batch for significant token savings

  Try:Batch search for: 1) error handling patterns 2) authentication methods 3) database connections
• batch_symbol_graph

  Execute multiple symbol graph operations in a single batch for efficiency

  Try:Batch symbol graph for: 1) all callers of function A 2) all implementations of interface B
• batch_graph_query

  Perform multiple graph queries simultaneously to reduce API calls and token usage

  Try:Batch graph queries to find: 1) dependency chains 2) inheritance hierarchies
• memory_store

  Store knowledge for persistent context across different sessions

  Try:Remember that this project uses JWT for authenticationTry:Store that the database connection uses connection pooling
• memory_find

  Recall previously stored knowledge across sessions

  Try:What authentication method did I tell you about earlier?Try:How do we connect to the database?
• cross_repo_search

  Search across multiple repositories with boundary tracing for multi-repo codebases

  Try:Find where the checkout process flows across the frontend and backend reposTry:Trace the user registration flow across microservices
• pattern_search

  Find structural patterns like retry loops, error handling, or singletons across languages

  Try:Find all retry loops in the codebaseTry:Search for singleton pattern implementations
• search_commits_for

  Search through git history for specific changes or patterns

  Try:Search commits for database schema changesTry:Find commits that modified the authentication system
• change_history_for_path

  Get the change history for a specific file or path in the repository

  Try:Show the change history for user.jsTry:List all commits that modified config/settings.py

Comparable tools

Installation

# Add the marketplace (one-time)
/plugin marketplace add Context-Engine-AI/Context-Engine

# Install the skill
/plugin install context-engine

# Install the MCP bridge
npm install -g @context-engine-bridge/context-engine-mcp-bridge

# Connect your codebase
ctxce connect <your-api-key> --workspace /path/to/repo --daemon

# Run as MCP server
ctxce mcp-serve --workspace /path/to/repo

FAQ

What AI assistants are supported by Context Engine?

Context Engine supports Claude Code/Claude Desktop, Cursor, Codex, Windsurf, Augment Code, Gemini, and any AI assistant that supports custom instructions.

How do I authenticate with Context Engine?

Sign up at context-engine.ai to get your API key, then use 'ctxce connect <api-key>' to authenticate your codebase.

Compare Context-Engine with