mcpField
M
Matomo Analytics

Matomo Analytics

Local
github.comData & Analytics0Updated 10w ago

About Matomo Analytics

Matomo Analytics is an MCP server for Matomo users, providing website analytics through curated read-only tools plus access to the full Reporting API. Its single binary includes real-time reports, response limits, and retries for transient failures.

Key features

  1. 0115 read-only analytics tools
  2. 02Traffic, page, referrer, and e-commerce reports
  3. 03Live visitor counts and visit logs
  4. 04Full API access for other methods
  5. 05Row and response-size limits
  6. 06Automatic retries for transient errors

Use cases

  1. 01Compare website traffic across date ranges
  2. 02Review conversions, goals, and e-commerce data
  3. 03Analyze visitor sources, devices, and locations
  4. 04Check current visitors and visit logs
  5. 05Call Reporting API methods beyond curated tools

MCP support

It exposes Matomo reporting tools to MCP clients over stdio or streamable HTTP. The tools are read-only, with an option to call other Reporting API methods.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository
Packages
cargomatomo-mcp0.1.4
ocighcr.io/liohtml/matomo-mcp:v0.1.4

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README
matomo-mcp logo

matomo-mcp

Talk to your Matomo Analytics. From Claude, Cursor, VS Code, or any MCP client.

CI Crates.io License: MIT Rust MCP

15 curated, read-only analytics tools + a full-API escape hatch. Single binary, instant startup, context-friendly.

Quickstart · Clients · Tools · Configuration · FAQ


You  ▸ How was traffic yesterday, and where did it come from?

Claude ▸ Yesterday you had 14,472 visits (11,416 unique visitors, 66% bounce rate).
         Top acquisition channels:
         1. Organic search — 6,120 visits (Google 92%)
         2. Direct — 4,890 visits
         3. AI assistants — 1,204 visits (↑ 31% vs. last week)
         Want me to break down which landing pages converted best?

Every question your Matomo dashboard can answer, your AI assistant can now answer too — including follow-ups, comparisons, and "why?".

✨ Why matomo-mcp?

🎯 Curated, not generated15 hand-crafted tools modeled on real analytics questions — not 70+ auto-generated API mirrors that flood the model's context and degrade tool selection.
⚡ Instant startupNo introspection round-trips. One static binary, no Node, no Python, no runtime. Starts in milliseconds.
🔒 Safe by defaultRead-only reporting tools. Token sent via POST only (never in URLs/logs), redacted from every error. TLS verification on by default.
🧠 Context-friendlyRow limits on every report and a hard response budget with actionable guidance — one tool call can never blow up the context window.
📡 Real-time includedLive visitor counters and a visit log (matomo_realtime) — see what's happening right now.
🧰 Never a cagematomo_api reaches any Reporting API method (funnels, heatmaps, custom dimensions, …) when the curated tools don't cover it.
🔁 ResilientAutomatic retries with backoff on 429/5xx/network hiccups. Helpful, hint-annotated error messages the model can act on.

🚀 Quickstart

1. Install

Prebuilt binary (Linux, macOS, Windows) — grab it from Releases, or:

# Cargo
cargo install matomo-mcp

# From source
cargo install --git https://github.com/Liohtml/matomo-mcp

# Docker
docker pull ghcr.io/liohtml/matomo-mcp
2. Get a Matomo API token

Matomo → Settings (⚙) → Personal → Security → Auth tokens → Create new token. View-only permissions are all it needs.

3. Verify the connection
matomo-mcp --url https://your-matomo.example.com --token YOUR_TOKEN --check
✓ Connected — Matomo version 5.2.1
✓ Token grants access to 3 site(s):
    #1 My Shop (https://shop.example.com)
    #2 Blog (https://blog.example.com)
    #3 Docs (https://docs.example.com)
4. Connect your client ⬇

🔌 Connect your client

Claude Code
claude mcp add matomo \
  --env MATOMO_URL=https://your-matomo.example.com \
  --env MATOMO_TOKEN=YOUR_TOKEN \
  --env MATOMO_DEFAULT_SITE_ID=1 \
  -- matomo-mcp
Claude Desktop

Add to claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\):

{
  "mcpServers": {
    "matomo": {
      "command": "matomo-mcp",
      "env": {
        "MATOMO_URL": "https://your-matomo.example.com",
        "MATOMO_TOKEN": "YOUR_TOKEN",
        "MATOMO_DEFAULT_SITE_ID": "1"
      }
    }
  }
}
Cursor

.cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{
  "mcpServers": {
    "matomo": {
      "command": "matomo-mcp",
      "env": {
        "MATOMO_URL": "https://your-matomo.example.com",
        "MATOMO_TOKEN": "YOUR_TOKEN",
        "MATOMO_DEFAULT_SITE_ID": "1"
      }
    }
  }
}
VS Code (GitHub Copilot)

.vscode/mcp.json:

{
  "servers": {
    "matomo": {
      "type": "stdio",
      "command": "matomo-mcp",
      "env": {
        "MATOMO_URL": "https://your-matomo.example.com",
        "MATOMO_TOKEN": "${input:matomo-token}",
        "MATOMO_DEFAULT_SITE_ID": "1"
      }
    }
  },
  "inputs": [
    {
      "id": "matomo-token",
      "type": "promptString",
      "description": "Matomo API token",
      "password": true
    }
  ]
}
Windsurf / Zed / other MCP clients

Any client that speaks MCP over stdio works with the generic shape:

{
  "command": "matomo-mcp",
  "args": [],
  "env": {
    "MATOMO_URL": "https://your-matomo.example.com",
    "MATOMO_TOKEN": "YOUR_TOKEN",
    "MATOMO_DEFAULT_SITE_ID": "1"
  }
}
Docker (any client)
{
  "mcpServers": {
    "matomo": {
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MATOMO_URL", "-e", "MATOMO_TOKEN", "-e", "MATOMO_DEFAULT_SITE_ID",
        "ghcr.io/liohtml/matomo-mcp"
      ],
      "env": {
        "MATOMO_URL": "https://your-matomo.example.com",
        "MATOMO_TOKEN": "YOUR_TOKEN",
        "MATOMO_DEFAULT_SITE_ID": "1"
      }
    }
  }
}
Streamable HTTP — host once, connect many clients

Run the server once (on a workstation, LAN box, or container) and point any number of MCP clients at it:

matomo-mcp --url https://your-matomo.example.com --token YOUR_TOKEN --http 127.0.0.1:8080

Clients connect to http://127.0.0.1:8080/mcp with the streamable HTTP transport, e.g.:

claude mcp add --transport http matomo http://127.0.0.1:8080/mcp

Warning

The HTTP endpoint has no built-in authentication. Keep it bound to 127.0.0.1, or put a reverse proxy with auth (or a firewall) in front before exposing it beyond localhost.

Tip

Set MATOMO_DEFAULT_SITE_ID and the model never has to ask which site you mean. No token at hand? Try it against the public demo: --url https://demo.matomo.cloud --default-site-id 1 (no token needed).

🧭 Tools

ToolAnswers questions like
matomo_list_sites"Which sites do we track?"
matomo_visits_summary"How much traffic did we get last week?"
matomo_pages"What are our top pages? Where do people exit?"
matomo_referrers"Where do visitors come from? Which campaigns work? What do AI assistants send us?"
matomo_events"How often was the configurator opened?"
matomo_goals"What's our conversion rate per goal?"
matomo_ecommerce"Revenue this month? Best-selling products?"
matomo_geo"Which countries/cities do visitors come from?"
matomo_devices"Mobile vs. desktop? Which browsers?"
matomo_visit_times"When during the day/week do people visit?"
matomo_site_search"What do people search for on our site — and find nothing?"
matomo_realtime"Who's on the site right now?"
matomo_page_performance"Which pages load slowly?"
matomo_annotations"Which deploys or campaign launches line up with that traffic spike?"
matomo_apiEverything else — funnels, heatmaps, custom dimensions, any Module.action of the Reporting API

All tools accept site_id, period (day/week/month/year/range), date (today, yesterday, 2026-07-01, last30, or start,end ranges), an optional segment (e.g. deviceType==mobile;country==DE), and a row limit.

Prompts to try
  • "Compare this week's traffic with last week — what changed and why?"
  • "Top 10 landing pages by conversions this month, with bounce rates."
  • "Are we getting traffic from ChatGPT or Perplexity? Trend over 3 months."
  • "Which internal searches return no results? Suggest content we should create."
  • "Anything unusual in the visitor log right now?"

⚙️ Configuration

FlagEnvDefaultDescription
--urlMATOMO_URL—Matomo instance URL (sub-directory installs like https://example.com/matomo/ work). Without it the server still starts and tool calls return setup guidance
--tokenMATOMO_TOKEN—API token (token_auth), view access is enough
--default-site-idMATOMO_DEFAULT_SITE_ID—Site used when the model doesn't specify one
--headerMATOMO_EXTRA_HEADERS—Extra HTTP headers (Name:Value, repeatable / comma-separated) — for auth proxies, Zero-Trust, multi-tenant setups
--timeout-secsMATOMO_TIMEOUT_SECS30Per-request timeout
--max-response-charsMATOMO_MAX_RESPONSE_CHARS50000Response budget before truncation
--httpMATOMO_HTTP_BIND—Serve MCP over streamable HTTP on this address instead of stdio (endpoint: http://<addr>/mcp)
--insecureMATOMO_INSECUREfalseAccept self-signed TLS certificates (explicit opt-in)
--check——Verify URL + token + site access, then exit

🆚 How is this different from FGRibreau/mcp-matomo?

mcp-matomo (which inspired this project — thanks! 🙏) introspects your Matomo instance at startup and generates one MCP tool per API method. matomo-mcp takes the opposite approach:

matomo-mcpmcp-matomo
Tool set15 curated tools + escape hatch~70+ generated tools
Model context costSmall, stableLarge, instance-dependent
Parameter typesExact, hand-written enums/defaultsInferred from parameter names
StartupInstant (no network I/O)Introspection round-trips (or cached spec file)
TLS verificationOn by defaultDisabled for introspection
Sub-directory installs✅Path is overwritten
Response size guardRow limits + hard budget—
Retries on transient errors✅—
Real-time (Live) tools✅— (not part of report metadata)

If you want every API method as its own tool, use mcp-matomo. If you want the model to reliably pick the right tool and never flood its context, use matomo-mcp.

🩺 Troubleshooting

"site_id is required"

Either pass --default-site-id 1 (recommended) or let the model call matomo_list_sites first.

401 / "cannot be authenticated"

Run matomo-mcp --url ... --token ... --check. If it fails: regenerate the token (Settings → Personal → Security), make sure it has at least view access to the site.

404 or HTML instead of JSON

MATOMO_URL must point at the Matomo root — the folder containing index.php. For https://example.com/matomo/index.php, use https://example.com/matomo/.

Behind Cloudflare Access / OAuth2 proxy / Zero Trust?

Inject the bypass headers: --header "CF-Access-Client-Id:..." --header "CF-Access-Client-Secret:..." (or via MATOMO_EXTRA_HEADERS).

Responses feel truncated

That's the context guard doing its job. Ask for fewer rows, a shorter date range, or raise --max-response-chars.

🗺️ Roadmap

  • Streamable HTTP transport (--http, host it once, connect many clients)
  • matomo_annotations — read & correlate deploy markers with traffic
  • Multi-instance support (one server, several Matomo installations)
  • Homebrew tap & winget manifest
  • MCP registry listing (official registry via server.json, Glama)

Want one of these sooner? Open an issue — or a PR, see CONTRIBUTING.md.

🛠️ Development

cargo test                                   # 37 tests, fully offline (wiremock)
cargo clippy --all-targets -- -D warnings
cargo run -- --url https://demo.matomo.cloud --default-site-id 1 --check

Architecture and design decisions: docs/ARCHITECTURE.md.

📄 License & Credits

MIT. Not affiliated with or endorsed by Matomo — Matomo is a registered trademark of InnoCraft Ltd.

Built with rmcp, the official Rust MCP SDK. Inspired by FGRibreau/mcp-matomo.

  • MCP Registry name: mcp-name: io.github.Liohtml/matomo-mcp

If matomo-mcp saves you a dashboard visit, a ⭐ helps others find it.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.