Acemcp

v1.0.0Search & Data Extractionstable

Provides code repository indexing and semantic search capabilities, allowing natural language queries to find relevant code snippets with automatic incremental indexing and multi-language support.

acemcpmcpai-integration
Share:
353
Stars
0
Downloads
0
Weekly
0/5

What is Acemcp?

Acemcp is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to provides code repository indexing and semantic search capabilities, allowing natural language queries to find relevant code snippets with automatic incremental indexing and multi-language support.

Provides code repository indexing and semantic search capabilities, allowing natural language queries to find relevant code snippets with automatic incremental indexing and multi-language support.

This server falls under the Search & Data Extraction category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Provides code repository indexing and semantic search capabi

Use Cases

Index and search code repositories.
Find relevant code snippets.
Support multi-language codebase search.
yeuxuan

Maintainer

LicenseISC License
Languagetypescript
Versionv1.0.0
UpdatedMay 21, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx acemcp

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Acemcp

Acemcp (Ace-Mcp-Node) is an MCP server that provides semantic code search and automatic incremental indexing for local code repositories, enabling AI assistants to find relevant code snippets, understand architecture, and investigate bugs using natural language queries. It indexes your project files, maintains an up-to-date search index automatically as files change, and exposes a single powerful search_context tool that returns matching code with file paths and line numbers. Developers use it to onboard to unfamiliar codebases, investigate how specific features are implemented, and give their AI assistant accurate context from large multi-language projects.

Prerequisites

  • Node.js 18.0.0 or later installed
  • npm 8.0.0 or later installed
  • Access to an Acemcp index service (requires BASE_URL and TOKEN configuration pointing to a compatible backend)
  • An MCP-compatible client such as Claude Desktop, Cursor, or Claude Code
  • A local code repository to index
1

Install acemcp-node globally

Install the acemcp-node package globally via npm so it is available as a command. Alternatively you can run it directly with npx without a global install.

npm install -g acemcp-node
2

Configure the Acemcp settings file

Create the settings file at ~/.acemcp/settings.toml and set the BASE_URL pointing to your index service and your authentication TOKEN. These are required for the server to communicate with the indexing backend.

# Create ~/.acemcp/settings.toml
mkdir -p ~/.acemcp

# Contents of settings.toml:
# BASE_URL = "https://your-acemcp-service.example.com"
# TOKEN = "your-api-token-here"
# BATCH_SIZE = 10
# MAX_LINES_PER_BLOB = 800
3

Configure your MCP client

Add acemcp-node to your MCP client configuration. No environment variables are required in the config if settings.toml is in place — the server reads configuration from ~/.acemcp/settings.toml automatically.

{
  "mcpServers": {
    "acemcp": {
      "command": "npx",
      "args": ["acemcp-node"],
      "env": {}
    }
  }
}
4

Restart your MCP client

Save the configuration and restart Claude Desktop or your MCP client to load the acemcp server.

5

Run a semantic search query on your codebase

Ask your AI assistant to search your project using natural language. Provide the absolute path to your project root and a description of what you are looking for. The server indexes the project on first use and keeps the index updated incrementally.

Acemcp Examples

Client configuration

claude_desktop_config.json configuration for the Acemcp server running via npx.

{
  "mcpServers": {
    "acemcp": {
      "command": "npx",
      "args": ["acemcp-node"],
      "env": {}
    }
  }
}

Prompts to try

Example semantic search queries for exploring and understanding your codebase with Acemcp.

- "Search my project at /Users/me/myapp for how user authentication is implemented"
- "Find all the code related to payment error handling and failure rollback in /home/dev/ecommerce-backend"
- "Show me how API routes are organized in /projects/my-api-server"
- "Search for database connection pooling logic in my project"
- "Find all places where the user session is validated or checked"

Troubleshooting Acemcp

search_context returns no results for a query

Verify the project_root_path argument uses an absolute path with forward slashes and that the directory exists and is readable. The first search triggers indexing which may take time for large repos. Try a broader query term. Check that the file extensions you are searching are included in the TEXT_EXTENSIONS setting.

Server fails to start with authentication error connecting to index service

Check that ~/.acemcp/settings.toml exists and contains valid BASE_URL and TOKEN values pointing to a running Acemcp index service. The BASE_URL must include the protocol (https://) and should not have a trailing slash. Regenerate your TOKEN if it has expired.

Large repositories cause slow indexing or timeouts

Add directories to EXCLUDE_PATTERNS in settings.toml to skip irrelevant paths like node_modules, .git, dist, and build directories. Reduce BATCH_SIZE from the default of 10 if uploads are timing out. The incremental indexer only re-indexes changed files after the initial index is built.

Frequently Asked Questions about Acemcp

What is Acemcp?

Acemcp is a Model Context Protocol (MCP) server that provides code repository indexing and semantic search capabilities, allowing natural language queries to find relevant code snippets with automatic incremental indexing and multi-language support. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Acemcp?

Follow the installation instructions on the Acemcp GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Acemcp?

Acemcp works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Acemcp free to use?

Yes, Acemcp is open source and available under the ISC License license. You can use it freely in both personal and commercial projects.

Browse More Search & Data Extraction MCP Servers

Explore all search & data extraction servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "acemcp": { "command": "npx", "args": ["-y", "acemcp"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Acemcp?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides