Model Context Protocol (MCP)

Overview

Model Context Protocol (MCP) is an open standard developed by Anthropic that enables AI assistants to connect with external tools and data sources. MCP is now generally available across major development platforms including VS Code, JetBrains IDEs, and more. CodeAlive’s MCP server provides your AI assistant with deep, contextual understanding of your entire codebase through semantic search and intelligent code analysis.

Why Use CodeAlive MCP?

Deep Context

AI understands relationships across your entire codebase, not just individual files

Semantic Search

Find code by meaning and intent, not just keywords

Multi-Repository

Work seamlessly across multiple repositories in one session

Real-Time Updates

Always work with the latest indexed version of your code

Deployment Options

CodeAlive MCP can be deployed in three ways, depending on your needs:

1. Remote Service (Recommended)

URL: https://mcp.codealive.ai/api/
Best for: Quick setup, no infrastructure management
Requirements: CodeAlive API key
Supported Clients: All MCP-compatible AI assistants

2. Docker Container

Image: ghcr.io/codealive-ai/codealive-mcp:main
Best for: Enterprise environments, local development
Requirements: Docker, CodeAlive API key
Benefits: Network isolation, custom configuration

3. Self-Hosted Instance

Repository: CodeAlive MCP Server
Best for: Complete control, custom modifications
Requirements: Python 3.11+, infrastructure management
Benefits: Full customization, on-premise deployment

Getting Started

Add at least one repository to CodeAlive before creating an API key. You do not need to wait for indexing to finish to create the key, but MCP queries become useful only after the repository is indexed.

Add a repository

Sign up or log in at app.codealive.ai
Go to Repositories in your dashboard
Click Add Repository
Connect your GitHub/GitLab/Bitbucket account
Select at least one repository to add

Create your API key

Navigate to MCP & API
Click ”+ Create API Key”
Copy your key immediately (it won’t be displayed again)
Store your API key securely

Wait for indexing

CodeAlive starts indexing after the repository is added. Wait for initial indexing to complete before expecting useful chat or search results. Initial indexing typically takes 5-15 minutes.

Choose Your Integration

Quick setup: Run npx @codealive/installer to auto-configure CodeAlive for your agents. See the Installation Guide for details.Or select your AI assistant to see manual setup instructions:

Claude Code

Remote MCP with OAuth support

VS Code + GitHub Copilot

Native MCP support (GA)

Cursor

MCP with elicitation & resources

Windsurf

Streamable HTTP with serverUrl

Continue

Full MCP feature support

Cline

Auto-tool creation capabilities

Claude Desktop

Desktop app with MCP

Codex

OpenAI Codex CLI with TOML config

Gemini CLI

One-command setup

Amazon Q

CLI and IDE integration

OpenCode

Terminal AI with remote transport

ChatGPT

Custom GPTs with Actions

Other Agents

Roo Code, Zed, Goose, and more

Available MCP Tools

CodeAlive exposes four powerful tools through MCP:

`get_data_sources`

Lists all indexed repositories and workspaces available for querying. Use cases:

Verify repository access
Check indexing status
List available codebases

`codebase_search`

Semantic search across your indexed codebase. Find code by meaning and intent, not just keywords. Use cases:

Find implementation patterns
Locate specific functionality
Discover related code
Trace data flows

`fetch_artifacts`

Retrieve full source code content for specific artifacts found via search. Use this to get the actual code after reviewing search descriptions. Use cases:

Get full content for external repo search results
Inspect specific functions or classes in detail
Follow the search → review → fetch workflow

Workflow: Call codebase_search first, review the descriptions and identifiers in the results, then call fetch_artifacts with the identifiers you want to inspect (max 20 per request). For repositories in your working directory, use local file reads instead.

`codebase_consultant`

AI consultant with full project expertise. Enables contextual conversations about your code with deep understanding. Use cases:

Architecture explanations
Code reviews
Bug analysis
Documentation generation

Common Use Cases

Code Understanding
Bug Investigation
Code Generation
Architecture Analysis

You: "Explain how user authentication works in our system"

AI: [Searches for authentication code across repositories]
    [Maps out the complete auth flow]
    [Explains with actual code references]

You: "Debug why payments are failing intermittently"

AI: [Searches for payment processing code]
    [Analyzes error handling and retry logic]
    [Identifies potential race conditions]

You: "Create a new API endpoint following our patterns"

AI: [Analyzes existing API endpoints]
    [Identifies conventions and patterns]
    [Generates code matching your style]

You: "What would be impacted if we change this database schema?"

AI: [Searches for all references to the schema]
    [Maps dependencies across services]
    [Lists required migrations and updates]

Security & Privacy

CodeAlive MCP follows security best practices:

All connections are encrypted with TLS
API keys are never logged or stored in plain text
Repository access is controlled at the API key level
Self-hosted options available for sensitive codebases

Best Practices

Keep Repos Updated

Regularly sync repositories in your dashboard for accurate context

Use Specific Queries

Be precise with technical terms for better search results

Organize by Project

Use separate API keys for different projects or environments

Monitor Usage

Track API usage in your dashboard to optimize queries

Troubleshooting

Connection Issues

Common causes:

Invalid or expired API key
Network connectivity problems
Incorrect MCP server URL

Solutions:

Regenerate API key in dashboard
Check network/firewall settings
Verify URL is https://mcp.codealive.ai/api/

No Repositories Found

Common causes:

Repositories not indexed
API key lacks permissions
Indexing still in progress

Solutions:

Check indexing status in dashboard
Wait 5-15 minutes for initial indexing
Verify API key has repository access

Slow Response Times

Common causes:

Large codebase searches
Broad/vague queries
Network latency

Solutions:

Use more specific search queries
Limit search to specific repositories
Consider Docker or self-hosted deployment

For more solutions, see the Troubleshooting Guide.

Next Steps

Choose Your Client

Set up CodeAlive with your preferred AI assistant

Self-Hosting Guide

Deploy CodeAlive MCP on your infrastructure

API Reference

Explore the full CodeAlive API

GitHub Repository

View source code and contribute

Getting Started

Features

Model Context Protocol

Agent Skills & Plugins

​Overview

​Why Use CodeAlive MCP?

Deep Context

Semantic Search

Multi-Repository

Real-Time Updates

​Deployment Options

​1. Remote Service (Recommended)

​2. Docker Container

​3. Self-Hosted Instance

​Getting Started

Claude Code

VS Code + GitHub Copilot

Cursor

Windsurf

Continue

Cline

Claude Desktop

Codex

Gemini CLI

Amazon Q

OpenCode

ChatGPT

Other Agents

​Available MCP Tools

​get_data_sources

​codebase_search

​fetch_artifacts

​codebase_consultant

​Common Use Cases

​Security & Privacy

​Best Practices

Keep Repos Updated

Use Specific Queries

Organize by Project

Monitor Usage

​Troubleshooting

​Next Steps

Choose Your Client

Self-Hosting Guide

API Reference

GitHub Repository

Overview

Why Use CodeAlive MCP?

Deployment Options

1. Remote Service (Recommended)

2. Docker Container

3. Self-Hosted Instance

Getting Started

Available MCP Tools

`get_data_sources`

`codebase_search`

`fetch_artifacts`

`codebase_consultant`

Common Use Cases

Security & Privacy

Best Practices

Troubleshooting

Next Steps