ObsidianCorps Umami Analytics runs on your own machine — the client starts it, so there is no endpoint to ping. 47 installs a week from npm. Last commit 15 Sep 2026.
Umami v3 MCP for Cloud or self-hosted analytics, with read-only, privacy-conscious defaults.
Today is the operative word: we check ObsidianCorps Umami Analytics every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add umami-mcp -- npx -y @obsidiancorps/umami-mcp
{
"mcpServers": {
"umami-mcp": {
"args": [
"-y",
"@obsidiancorps/umami-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.umami-mcp]
command = "npx"
args = ["-y", "@obsidiancorps/umami-mcp"]
{
"mcpServers": {
"umami-mcp": {
"args": [
"-y",
"@obsidiancorps/umami-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"umami-mcp": {
"args": [
"-y",
"@obsidiancorps/umami-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
UMAMI_API_KEY (Umami Cloud API key. Configure this or one self-hosted authentication mode.), UMAMI_BASE_URL (Base URL of a self-hosted Umami instance, for example https://analytics.example.com.), UMAMI_TOKEN (Pre-issued self-hosted Umami token. Use with UMAMI_BASE_URL instead of login credentials.), UMAMI_USERNAME (Self-hosted Umami username. Use with UMAMI_BASE_URL and UMAMI_PASSWORD.), UMAMI_PASSWORD (Self-hosted Umami password. Use with UMAMI_BASE_URL and UMAMI_USERNAME.), UMAMI_TWO_FACTOR_SECRET (Optional Base32 TOTP setup secret for automatic Umami 3.3+ two-factor login.), UMAMI_DEFAULT_WEBSITE_ID (Optional default website UUID used when a tool call does not select a website.).
The author declared them in the registry entry; get the values from the project itself.
MCP server for Obsidian vaults - AI tools with consistent canonical context. Local-first.
Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings.
Self-hosted multi-user memory for AI agents: a human-readable Markdown wiki with per-fragment ACL.
Filesystem-based MCP server for Obsidian vaults — read, search, and edit notes, no app required.
MCP server for AI agent read/write access to Obsidian vaults via EVC Team Relay.
Access Obsidian vaults via Local REST API - read, search, and interact with notes
Semantic search and AI context for your Obsidian vault. Surface patterns with catalysts.
Filesystem-direct Obsidian MCP server — search and edit your vault with low context-tax.
Answers built from our own checks of this server.