CodeAlive MCP

## CodeAlive MCP: Deepest Context Engine for your projects (especially for large codebases) **Connect your AI assistant to CodeAlive's powerful code understanding platform in seconds!** This MCP (Model Context Protocol) server enables AI clients like Claude Code, Cursor, Claude Desktop, Continue, VS Code (GitHub Copilot), Cline, Codex, OpenCode, SourceCraft Code Assistant, SourceCraft CLI, Zed, KodaCode, GigaCode, Qwen Code, Gemini CLI, Roo Code, Goose, Kilo Code, Windsurf, Kiro, Qoder, n8n, and Amazon Q Developer to access CodeAlive's advanced semantic code search and codebase interaction features. CodeAlive is a Context Engine for large codebases, powered by graph-based retrieval and exposed through MCP. It gives AI agents like Cursor, Claude Code, Codex, and other MCP-compatible tools precise repository context instead of forcing them to read files blindly. In our RepoQA benchmark, CodeAlive + Qwen3.6 deep reached frontier-agent quality at ~25x lower model cost, and semantic search reduced captured tokens by 45%. It's like Context7, but for your (large) codebases. - **Find relevant code faster**with semantic search - **Understand the bigger picture**beyond isolated files - **Provide better answers**with full project context - **Reduce costs and time**by removing guesswork Once connected, you'll have access to these powerful tools: - **`get_data_sources`**- List your indexed repositories and workspaces - **`semantic_search`**- Canonical semantic search across indexed artifacts - **`grep_search`**- Exact literal or regex text search inside file content, plus literal file-name/path matching (returns files like`Form.xml`even when their content never mentions the name), with line-level previews for content matches - **`get_repository_ontology`**- Get repository-level orientation for one selected repository - **`get_file_tree`**- Inspect a bounded file tree for one repository - **`read_file`**- Read a repository-relative file path, optionally with a line range - **`fetch_artifacts`**- Load the full source for relevant search hits (missing or inaccessible identifiers are reported back, not silently dropped) - **`get_artifact_relationships`**- Expand call graph, inheritance, and reference relationships for one artifact - **`get_artifact_query_schema`**- Inspect supported ArtifactQuery entities, fields, and examples - **`query_artifact_metadata`**- Run read-only metadata analytics across selected repositories - **`chat`**- Stateless, slower synthesized codebase Q&A; call only when explicitly requested After setup, try these commands with your AI assistant: - *"Show me all available repositories"*→ Uses`get_data_sources` - *"Find authentication code in the user service"*→ Uses`semantic_search` - *"Find the exact regex that matches JWT tokens"*→ Uses`grep_search` - *"Explain how the payment flow works in this codebase"*→ Usually starts with`semantic_search`/`grep_search`, then optionally uses`chat` `semantic_search`and`grep_search`should be the default tools for most agents.`chat`is a slower stateless synthesis fallback that can take substantially longer than retrieval, and is usually unnecessary when an agent can run a multi-step workflow with ontology, search, fetch/read, relationships, ArtifactQuery, and local file reads. If your agent supports subagents, the highest-confidence path is to delegate a focused subagent that orchestrates`semantic_search`and`grep_search`first. For an even better experience, install the[CodeAlive Agent Skillalongside the MCP server. The MCP server gives your agent access to CodeAlive's tools; the skill teaches it the best workflows and query patterns to use them effectively. **For most agents**(Cursor, Copilot, Gemini CLI, Codex, and](https://github.com/CodeAlive-AI/codealive-skills)[30+ others) — install the skill: ``` `npx skills add CodeAlive-AI/codealive-skills@codealive-context-engine` ``` **For Claude Code**— install the plugin (recommended), which includes the skill plus Claude-specific enhancements: ``` `/plugin marketplace add CodeAlive-AI/codealive-skills /plugin install codealive@codealive-marketplace` ``` - ](https://agentskills.io/)[Agent Skill - ](#-agent-skill)[Quick Start (Remote) - ](#-quick-start-remote)[AI Client Integrations - ](#-ai-client-integrations)[Advanced: Local Development - ](#-advanced-local-development)[Community Plugins - ](#-community-plugins)[HTTP Deployment (Self-Hosted & Cloud) - ](#-http-deployment-self-hosted--cloud)[Windows & WSL - ](#-windows--wsl)[Available Tools - ](#-available-tools)[Usage Examples - ](#-usage-examples)[Troubleshooting - ](#-troubleshooting)[Publishing to MCP Registry - ](#-publishing-to-mcp-registry)[License **The fastest way to get started**- no installation required! Our remote MCP server at`https://mcp.codealive.ai/api`provides instant access to CodeAlive's capabilities. - Sign up at](#-license)[https://app.codealive.ai/ - Navigate to**MCP & API** - Click**"+ Create API Key"** - Copy your API key immediately - you won't see it again! Choose your client in the](https://app.codealive.ai/)[MCP integration guidesand follow the current setup instructions there. You may ask your AI agent to install the CodeAlive MCP server for you. - Copy-paste the following prompt into your AI agent. Do not include your API key in the prompt: ``` `Add the CodeAlive MCP server by following the guide for my client at https://docs.codealive.ai/integrations/mcp Prefer the Remote HTTP option when available. Do not ask me to paste an API key into chat. When the key is needed, ask me to create a CodeAlive API key and copy it to my clipboard. After I confirm, insert it directly from the clipboard into the required secure configuration without displaying, echoing, logging, or exposing it in command arguments, command output, or model context. If you cannot safely use the clipboard without exposing the value, tell me exactly where to paste it myself.` ``` Client-specific configuration is maintained in the CodeAlive documentation so file paths, transports, and authentication guidance stay current. For an unlisted client, use these generic connection details and adapt them to the client's MCP configuration format: - **Endpoint:**`https://mcp.codealive.ai/api` - **Transport:**Streamable HTTP - **Authentication header:**`Authorization: Bearer YOUR_API_KEY_HERE` For a private deployment, replace the endpoint with your server's`/api`URL. See](https://docs.codealive.ai/integrations/mcp)[Self-Hostingfor deployment guidance. **Connecting the server is half the setup.**Coding agents may continue using their built-in search unless project instructions tell them to prefer CodeAlive. Ready-made rules for`AGENTS.md`,`CLAUDE.md`, and client-specific instruction files are in](https://docs.codealive.ai/integrations/mcp/self-hosting)[Instructing Coding Agents. **For developers who want to customize or contribute to the MCP server.** ``` `# Clone the repository git clone https://github.com/CodeAlive-AI/codealive-mcp.git cd codealive-mcp # Setup with uv (recommended) uv venv source .venv/bin/activate # Windows: .venv\Scripts\activate uv pip install -e . # Or setup with pip python -m venv .venv source .venv/bin/activate # Windows: .venv\Scripts\activate pip install -e .` ``` After installing the server locally, point your MCP client at`.venv/bin/python`with`src/codealive_mcp_server.py`as the first argument and provide`CODEALIVE_API_KEY`in the process environment. Client-specific configuration belongs in the](https://docs.codealive.ai/guides/instructing-agents)[MCP integration guides. ``` `# Start local HTTP server export CODEALIVE_API_KEY="your_api_key_here" python src/codealive_mcp_server.py --transport http --host localhost --port 8000 # Test health endpoint curl http://localhost:8000/health` ``` HTTP transport validates`Host`and browser`Origin`headers. Loopback hosts (`localhost`,`127.0.0.1`,`::1`) work without extra configuration. For a shared hostname, configure an exact allowlist: ``` `export CODEALIVE_MCP_ALLOWED_HOSTS="mcp.codealive.yourcompany.com" # Only for browser callers; ordinary MCP clients do not send Origin. export CODEALIVE_MCP_ALLOWED_ORIGINS="https://mcp.codealive.yourcompany.com" python src/codealive_mcp_server.py --transport http --host 0.0.0.0 --port 8000` ``` The equivalent repeatable CLI options are`--allowed-host`and`--allowed-origin`. Do not use`*`for an Internet-facing server. After making changes, quickly verify everything works: ``` `# Match pyproject.toml exactly; older uv versions reject the locked setup. uv --version # expected: uv 0.11.28 uv sync --locked --extra test # Install the repository pre-push dependency audit once per clone ./scripts/setup-hooks.sh # Quick smoke test (recommended) make smoke-test # Or run directly python smoke_test.py # With your API key for full testing CODEALIVE_API_KEY=your_key python smoke_test.py # Run unit tests make unit-test # Run all tests make test # Equivalent direct locked test run uv run pytest src/tests/ -q` ``` - Server starts and connects correctly - All tools are registered - Each tool responds appropriately - Parameter validation works - Runs in ~5 seconds - ](https://docs.codealive.ai/integrations/mcp)[Gemini CLI — CodeAlive Extension - ](https://github.com/akolotov/gemini-cli-codealive-extension)[Gemini CLI setup guide ## 🚢 HTTP Deployment (Self-Hosted & Cloud) **Deploy the MCP server as an HTTP service for team-wide access or integration with self-hosted CodeAlive instances.** The CodeAlive MCP server can be deployed as an HTTP service using Docker. This allows multiple AI clients to connect to a single shared instance, and enables integration with self-hosted CodeAlive deployments. Create a`docker-compose.yml`file based on our example: ``` `# Download the example curl -O https://raw.githubusercontent.com/CodeAlive-AI/codealive-mcp/main/docker-compose.example.yml mv docker-compose.example.yml docker-compose.yml # Edit configuration (see below) nano docker-compose.yml # Start the service docker compose up -d # Check health curl http://localhost:8000/health` ``` - Remove`CODEALIVE_BASE_URL`environment variable (uses default`https://app.codealive.ai`) - For remote clients with OAuth support, configure only`https://mcp.codealive.ai/api`and complete the browser sign-in when prompted - Existing API-key clients remain supported via`Authorization: Bearer YOUR_KEY` - Set`CODEALIVE_BASE_URL`to your CodeAlive instance URL (e.g.,`https://codealive.yourcompany.com`) - Set`CODEALIVE_MCP_ALLOWED_HOSTS`to the exact hostname clients use for this MCP server - Clients must provide their API key via`Authorization: Bearer YOUR_KEY`header See`docker-compose.example.yml`for the complete configuration template. For example, current Codex and Claude Code clients can use browser OAuth without storing a CodeAlive API key: ``` `codex mcp add codealive --url https://mcp.codealive.ai/api codex mcp login codealive claude mcp add --transport http codealive https://mcp.codealive.ai/api # Start Claude Code and run /mcp to authenticate.` ``` Cursor and OpenCode also discover OAuth automatically from the same URL. Use`cursor-agent mcp login codealive`or`opencode mcp auth codealive`when their UI does not prompt automatically. API-key configuration remains available as a compatibility option. Remote HTTP deployments can enable browser authorization while keeping legacy API-key clients working during rollout. OAuth mode publishes MCP Protected Resource Metadata, validates exact issuer/resource-bound JWTs, and exchanges them for a separate short-lived Tool API token. The incoming MCP bearer token is never forwarded downstream. The authorization server and MCP service values must match exactly. In CodeAlive Web.Server the corresponding settings live under`McpOAuth`(`Enabled`,`Issuer`,`Resource`,`ToolApiResource`,`InternalClientId`, and`InternalClientSecret`). Persist the Web.Server Data Protection key ring and OpenIddict signing/encryption certificates across replicas and restarts. For a zero-downtime internal credential rotation, give the new credential a new client ID, deploy Web.Server with both current and`PreviousInternalClientId`/`PreviousInternalClientSecret`, roll MCP replicas to the new current pair, then remove the previous pair. Web.Server deliberately fails startup instead of changing a secret in place under an existing client ID. Enable the Web.Server and MCP flags in the same rollout; a half-enabled deployment is not a valid steady state. API-key credentials retain their explicit legacy grammar and are never used as a fallback after OAuth validation fails. ### Connecting MCP Clients to Your Deployed Instance Use the same generic connection details as CodeAlive Cloud, replacing the endpoint with your deployment's`/api`URL: - **Endpoint:**`https://your-server.example.com/api` - **Transport:**Streamable HTTP - **Authentication header:**`Authorization: Bearer YOUR_API_KEY_HERE` For the exact configuration format, open the relevant](https://docs.codealive.ai/integrations/mcp/gemini-cli)[client integration guide. Use the client-specific documentation for Windows and WSL setup: - ](https://docs.codealive.ai/integrations/mcp)[Claude Code - ](https://docs.codealive.ai/integrations/mcp/claude-code)[Claude Desktop - ](https://docs.codealive.ai/integrations/mcp/claude-desktop)[All MCP integration guides - ](https://docs.codealive.ai/integrations/mcp)[Troubleshooting For self-hosted servers running in WSL2, Windows clients must be able to reach the server's`/api`endpoint. Use mirrored networking on supported Windows 11 versions or connect through the WSL2 VM address. ``` `curl -H "Authorization: Bearer YOUR_API_KEY" https://app.codealive.ai/api/v1/data_sources` ``` **Enable debug logging:**Add`--debug`to local server args - **"Connection refused"**→ Check internet connection - **"401 Unauthorized"**→ Verify your API key - **"No repositories found"**→ Check API key permissions in CodeAlive dashboard - **Client-specific logs**→ See your AI client's documentation for MCP logs - **`docker: command not found`in WSL**→ Enable Docker Desktop WSL integration for your distro (Settings → Resources → WSL integration), or use the full path`/usr/bin/docker` - **`ENOENT`or`spawn error`for`npx`/`python`**→ Non-interactive WSL shells don't inherit`nvm`/`pyenv`paths. Use absolute paths in MCP configs - **`Connection refused`to self-hosted server in WSL2**→ WSL2 uses NAT networking;`localhost`differs between Windows and WSL2. Enable mirrored networking in`.wslconfig`or use the WSL2 VM IP (`hostname -I`) - **Claude Desktop can't connect to WSL MCP server**→ Claude Desktop doesn't support WSL subprocess spawning. Use Remote HTTP (`https://mcp.codealive.ai/api`), Docker Desktop, or the`wsl.exe`proxy pattern (see](https://docs.codealive.ai/troubleshooting)[Windows & WSL section) - 📧 Email:](#-windows--wsl)[support@codealive.ai - 🐛 Issues:](https://github.com/CodeAlive-AI/codealive-mcp/blob/HEAD/mailto:support@codealive.ai)[GitHub Issues For maintainers: see](https://github.com/CodeAlive-AI/codealive-mcp/issues)[DEPLOYMENT.mdfor instructions on publishing new versions to the MCP Registry. CodeAlive processes the repositories and queries you send through this extension in order to provide semantic search and codebase analysis. For complete privacy details, see](https://github.com/CodeAlive-AI/codealive-mcp/blob/HEAD/DEPLOYMENT.md)[CodeAlive Privacy Policy. MIT License - see](https://www.codealive.ai/privacy/)[LICENSEfile for details. **Ready to supercharge your AI assistant with deep code understanding?** ](https://github.com/CodeAlive-AI/codealive-mcp/blob/HEAD/LICENSE)[Get started now → This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases. Semantic code search for AI agents without indexing your codebase or storing any data. Fast and accurate. Create and read feature flags, review experiments, generate flag types, search docs, and interact with GrowthBook's feature flagging and experimentation platform. Word search, crossword, and sudoku generator MCP server with printable PDF worksheets, themed word banks, and verifiable LLM evals. Local-first, from the makers of puzzletide.com. Official MCP server for Stimulsoft Reports & Dashboards documentation. Semantic search across FAQ, Programming Manual, Server/User Manual, and Server/Cloud API for .NET, WPF, Avalonia, WEB, Blazor, Angular, React, JS, PHP, Java, and Python platforms. Searching and access your AI coding sessions from Claude Code, Gemini CLI, opencode, and OpenAI Codex. Search Apple's Developer Documentation with smart search and wildcard support. MCP server that exposes ast-grep (sg) as two tools for structural code search. Search everything your terminal ever printed. Local MCP server over per-command recorded output: full-text search, exit codes, diffs, secret redaction. Built and maintained by an AI agent (Soren Achebe). Let AI agents search, register, and manage domains via API Search, compare, and get docs for 210+ APIs ranked by CLI and agent relevance](https://app.codealive.ai/)