Getting Started
Prerequisites
Section titled “Prerequisites”- An MCP-compatible client — Claude Code, Codex CLI, Gemini CLI, GitHub Copilot, Cursor, Windsurf, or any other MCP host
- An Obsidian vault (or any directory of Markdown files) — see Vault Structure for the expected layout
- Optional for worker delegation: any OpenAI-compatible
/v1endpoint — a hosted service or a runtime on your own machine. You need its base URL, a credential if it requires one, and a model id. Hive names no provider.
Install
Section titled “Install”One command. No cloning, no venv, no config files.
claude mcp add -s user hive -- uvx --upgrade hive-vaultAdd to ~/.codex/config.toml:
[mcp_servers.hive-vault]command = "uvx"args = ["--upgrade", "hive-vault"]gemini mcp add -s user hive-vault uvx -- --upgrade hive-vaultAdd to .vscode/mcp.json in your project:
{ "servers": { "hive-vault": { "command": "uvx", "args": ["--upgrade", "hive-vault"] } }}Add to ~/.config/opencode/opencode.jsonc:
{ "mcp": { "hive": { "type": "local", "command": ["uvx", "--upgrade", "hive-vault"], "enabled": true } }}The --upgrade flag ensures you always get the latest version from PyPI on each session start. uvx handles the Python environment automatically.
Updating a persistent installation
Section titled “Updating a persistent installation”The uvx configurations above resolve the current release for each new session. If you use a
persistent installation for daemon mode, upgrade it deliberately:
# Linux / macOSuv tool upgrade hive-vault
# Windows (the version is optional; omitted selects the latest PyPI release)hive self-upgrade [version]On Windows, self-upgrade builds the new release beside the active files and atomically switches
the managed runtime, so it does not modify files held by a running Hive process. Open a new
terminal after the first managed upgrade so the launcher added to your user PATH is available.
Start a new MCP session after any upgrade; an existing session keeps its current server process.
First Query
Section titled “First Query”Once registered, your AI assistant can use Hive tools. Try asking:
“Use vault_list to see my vault”
The assistant will call vault_list() and list all projects with file counts and available shortcuts.
Configure Vault Path
Section titled “Configure Vault Path”By default, Hive looks for your vault at ~/Projects/knowledge. If this path doesn’t exist, vault tools will return a helpful error with setup instructions — the server still starts, so worker tools remain available.
To point Hive to your vault:
claude mcp add -s user hive -e VAULT_PATH=/path/to/your/vault -- uvx --upgrade hive-vault[mcp_servers.hive-vault]command = "uvx"args = ["--upgrade", "hive-vault"]
[mcp_servers.hive-vault.env]VAULT_PATH = "/path/to/your/vault"gemini mcp add -s user -e VAULT_PATH=/path/to/your/vault hive-vault uvx -- --upgrade hive-vault{ "servers": { "hive-vault": { "command": "uvx", "args": ["--upgrade", "hive-vault"], "env": { "VAULT_PATH": "/path/to/your/vault" } } }}{ "mcp": { "hive": { "type": "local", "command": ["uvx", "--upgrade", "hive-vault"], "environment": { "VAULT_PATH": "/path/to/your/vault" }, "enabled": true } }}Configure Worker (Optional)
Section titled “Configure Worker (Optional)”To enable task delegation, point Hive at one OpenAI-compatible endpoint with HIVE_WORKER_BASE_URL, HIVE_WORKER_API_KEY and HIVE_WORKER_MODEL. Without a base URL the worker stays disabled and delegate_task tells the host to handle the task itself:
# Export HIVE_WORKER_API_KEY from your secret store first.claude mcp add -s user hive \ -e VAULT_PATH=/path/to/your/vault \ -e HIVE_WORKER_BASE_URL=https://api.your-provider.example/v1 \ -e HIVE_WORKER_API_KEY="$HIVE_WORKER_API_KEY" \ -e HIVE_WORKER_MODEL=<model-id> \ -- uvx --upgrade hive-vault[mcp_servers.hive-vault]command = "uvx"args = ["--upgrade", "hive-vault"]
[mcp_servers.hive-vault.env]VAULT_PATH = "/path/to/your/vault"HIVE_WORKER_BASE_URL = "https://api.your-provider.example/v1"HIVE_WORKER_API_KEY = "<your-key>"HIVE_WORKER_MODEL = "<model-id>"# Export HIVE_WORKER_API_KEY from your secret store first.gemini mcp add -s user \ -e VAULT_PATH=/path/to/your/vault \ -e HIVE_WORKER_BASE_URL=https://api.your-provider.example/v1 \ -e HIVE_WORKER_API_KEY="$HIVE_WORKER_API_KEY" \ -e HIVE_WORKER_MODEL=<model-id> \ hive-vault uvx -- --upgrade hive-vault{ "servers": { "hive-vault": { "command": "uvx", "args": ["--upgrade", "hive-vault"], "env": { "VAULT_PATH": "/path/to/your/vault", "HIVE_WORKER_BASE_URL": "https://api.your-provider.example/v1", "HIVE_WORKER_API_KEY": "<your-key>", "HIVE_WORKER_MODEL": "<model-id>" } } }}{ "mcp": { "hive": { "type": "local", "command": ["uvx", "--upgrade", "hive-vault"], "environment": { "VAULT_PATH": "/path/to/your/vault", "HIVE_WORKER_BASE_URL": "https://api.your-provider.example/v1", "HIVE_WORKER_API_KEY": "<your-key>", "HIVE_WORKER_MODEL": "<model-id>" }, "enabled": true } }}See Configuration for all environment variables.
Verify
Section titled “Verify”Run a health check:
“Use vault_health to check my vault”
You should see project counts, file counts, and staleness metrics for each project in your vault.
Next Steps
Section titled “Next Steps”- Use Cases — real-world workflows with Hive
- Configuration — full environment variable reference
- Vault Tools — all vault tools
- Worker Tools — task delegation and worker status
- Vault Structure — how to organize your vault
- Troubleshooting — common issues and fixes