Skip to main content
Glama
deenesjakoruzh
Mzaxd

Umami MCP Server

by Mzaxd
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Umami MCPサーバー

Umamiアナリティクス用の読み取り専用MCPサーバーです。HTTP経由でUmami REST APIと直接通信し、主にセルフホスト環境のUmamiをサポートしますが、Umami CloudのAPIキーでも動作します。

このリポジトリは、上位層のエージェントが毎回Umamiのドキュメントを読み直すことなくアナリティクス情報を取得できるように構築されています。ブラウザ自動化、DOMスクレイピング、書き込み操作は一切行いません。

機能

  • 一般的なUmamiアナリティクスクエリのための読み取り専用MCPツール

  • 2つの認証モード:

    • UMAMI_API_KEY

    • UMAMI_USERNAME + UMAMI_PASSWORD

  • メモリ内でのセルフホスト用ベアラトークンキャッシュ

  • ユーザー名/パスワードモードでの自動再ログインおよび401発生時の1回のリトライ

  • ISO形式の時刻文字列とミリ秒単位のタイムスタンプの両方に対応

  • 統計、ページビュー、内訳、イベントシリーズ全体で共有されるフィルタ処理

  • 小規模で保守性の高いモジュールによる厳格なTypeScript実装

  • 明確な構造化ツール出力と明示的なエラーカテゴリ

Related MCP server: umami-mcp-server

要件

  • Node.js >= 20

  • pnpm >= 10

インストール

npmからインストール:

npm install -g umami-analytics-mcp

またはインストールせずに実行:

npx -y umami-analytics-mcp

このリポジトリでローカル開発を行う場合:

pnpm install

設定

.env.exampleから.envファイルを作成します。

cp .env.example .env

以下の認証オプションのいずれかを入力してください:

  1. APIキーモード

UMAMI_API_URL=https://api.umami.is/v1
UMAMI_API_KEY=your-api-key
UMAMI_DEFAULT_TIMEZONE=Asia/Shanghai

  1. セルフホストのユーザー名/パスワードモード

UMAMI_API_URL=https://umami.example.com/api
UMAMI_USERNAME=admin
UMAMI_PASSWORD=secret
UMAMI_DEFAULT_TIMEZONE=Asia/Shanghai

注意:

  • UMAMI_API_URLは、サイトのオリジンだけでなく、APIのベースURLを指定する必要があります。

  • UMAMI_API_KEYとユーザー名/パスワードの両方が設定されている場合、UMAMI_API_KEYが優先されます。

  • UMAMI_DEFAULT_TIMEZONEは、ツールがタイムゾーンをサポートしており、かつ指定を省略した場合に使用されます。

ローカルでの実行

開発モード:

pnpm dev

ビルドして実行:

pnpm build
pnpm start

サーバーはMCP stdioトランスポートを使用するため、クライアントが切断されるまでstdin/stdoutに接続されたままになります。

npmからインストールした場合、同等のコマンドは以下の通りです:

umami-analytics-mcp

テスト

pnpm test
pnpm build

デフォルトではスキップされる、実際のAPIを使用した統合テストテンプレートもあります:

UMAMI_INTEGRATION_TEST=1 pnpm test:integration

MCP Inspector

最初にビルドします:

pnpm build

次に、ビルドされたサーバーに対して公式のMCP Inspectorを起動します:

npx @modelcontextprotocol/inspector node dist/cli.js

開発中のホットリロードには、以下も有効です:

npx @modelcontextprotocol/inspector pnpm dev

公開されたパッケージパスをテストしたい場合は、以下を使用してください:

npx @modelcontextprotocol/inspector npx -y umami-analytics-mcp

Inspectorプロセスで同じUmami環境変数が利用可能であることを確認してください。

Inspectorでの推奨スモークテスト:

  1. umami_ping

  2. umami_list_websites

  3. umami_get_stats

  4. umami_get_breakdown

ツール

umami_ping

設定と認証を検証します。

例:

{}

umami_list_websites

アクセス可能なウェブサイトを一覧表示します。

例:

{}

umami_find_website

ウェブサイト名またはドメインによるあいまい検索を行います。

例:

{
  "query": "example.com"
}

umami_get_stats

ウェブサイトと期間の統計サマリーを取得します。

例:

{
  "websiteId": "8f2f8ce2-1234-4567-89ab-0123456789ab",
  "startAt": "2026-04-23T00:00:00+08:00",
  "endAt": "2026-04-23T23:59:59+08:00",
  "filters": {
    "path": "/pricing"
  }
}

umami_get_pageviews

時系列のページビューとセッションを取得します。

例:

{
  "websiteId": "8f2f8ce2-1234-4567-89ab-0123456789ab",
  "startAt": "2026-04-17T00:00:00+08:00",
  "endAt": "2026-04-23T23:59:59+08:00",
  "unit": "day",
  "compare": "prev",
  "filters": {
    "path": "/blog"
  }
}

umami_get_breakdown

トップページ、リファラー、国、ブラウザ、デバイスなどの内訳行を取得します。

例:

{
  "websiteId": "8f2f8ce2-1234-4567-89ab-0123456789ab",
  "startAt": "2026-04-17T00:00:00+08:00",
  "endAt": "2026-04-23T23:59:59+08:00",
  "type": "path",
  "limit": 10,
  "expanded": false
}

umami_get_active

現在のアクティブな訪問者数を返します。

例:

{
  "websiteId": "8f2f8ce2-1234-4567-89ab-0123456789ab"
}

umami_get_events_series

カスタムイベントの時系列カウントを返します。

例:

{
  "websiteId": "8f2f8ce2-1234-4567-89ab-0123456789ab",
  "startAt": "2026-04-17T00:00:00+08:00",
  "endAt": "2026-04-23T23:59:59+08:00",
  "unit": "day"
}

共有フィルタ

これらのツールは、同じfiltersオブジェクトをサポートしています:

  • path

  • referrer

  • title

  • query

  • browser

  • os

  • device

  • country

  • region

  • city

  • hostname

エラーハンドリング

ツールのエラーは、以下のカテゴリを持つ構造化されたMCPツール結果として返されます:

  • config_missing

  • auth_failed

  • website_not_found

  • umami_http_error

  • network_timeout

  • network_error

  • invalid_input

任意のStdio MCPクライアントへのマウント

StdioベースのMCPクライアントであれば、以下の設定でこのサーバーを実行できます:

  • command: npx

  • args: ["-y", "umami-analytics-mcp"]

  • env: Umamiの環境変数

mcpServersオブジェクトを使用するクライアント向けのJSONスニペット例:

{
  "mcpServers": {
    "umami": {
      "command": "npx",
      "args": ["-y", "umami-analytics-mcp"],
      "env": {
        "UMAMI_API_URL": "https://umami.example.com/api",
        "UMAMI_USERNAME": "admin",
        "UMAMI_PASSWORD": "secret",
        "UMAMI_DEFAULT_TIMEZONE": "Asia/Shanghai"
      }
    }
  }
}

ローカルの未リリースチェックアウトの場合でも、ビルドされたファイルを直接指定できます:

{
  "mcpServers": {
    "umami": {
      "command": "node",
      "args": ["/absolute/path/to/umami-mcp/dist/cli.js"]
    }
  }
}

npmへの公開

このリポジトリは現在、npm CLIパッケージとして構成されています。

推奨されるリリースフロー:

pnpm test
pnpm build
pnpm pack --dry-run
npm login
pnpm publish

注意:

  • umami-mcpはnpm上で既に使用されているため、パッケージ名はumami-analytics-mcpに設定されています。

  • 現在のlicenseは安全なプレースホルダーとしてUNLICENSEDになっています。寛容なライセンスが必要な場合は、実際の公開オープンソースリリース前に置き換えてください。

  • 後で独自のnpmスコープで公開する場合は、package.jsonのnameフィールドのみを変更してください。

内部ドキュメント

Available Tools

8 tools
umami_find_websiteFind Umami WebsiteA
Read-only

Search Umami websites by name or domain using fuzzy matching. Useful before calling other analytics tools.

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesWebsite name or domain fragment to search for.

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds fuzzy matching behavior beyond the readOnlyHint annotation. However, it does not mention the return format or if there are limits, but for a simple search it is sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with a clear usage hint, no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple tool with one parameter, readOnly annotation, and no output schema, the description provides all essential information: purpose, usage context, and parameter meaning.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the query parameter is already well described in the schema. The description adds minimal extra meaning beyond 'search by name or domain'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool searches for Umami websites by name or domain using fuzzy matching, and the title confirms 'Find Umami Website'. It is distinct from siblings which are get/list operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Useful before calling other analytics tools,' providing clear context for when to use this tool versus the other tools available.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

umami_get_activeGet Umami Active VisitorsA
Read-only

Get the number of active visitors on a website during the last 5 minutes.

ParametersJSON Schema
NameRequiredDescriptionDefault
websiteIdYesUmami website ID. Use umami_list_websites or umami_find_website first if you do not know it.

TDQS

A3.8/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the description carries less burden. It adds the specific time window ('last 5 minutes'), which is a useful behavioral detail beyond the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, concise sentence that contains no filler or redundant information. Every word adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with one parameter and no output schema, the description is fairly complete. It specifies the metric and time window, and the parameter description provides guidance on how to find the websiteId. However, it does not explicitly state the return type (e.g., integer).

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 100% description coverage, so the baseline is 3. The tool description adds no additional meaning about the parameter; the parameter's own description already explains how to obtain the websiteId.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific verb (Get), resource (active visitors), and scope (last 5 minutes), distinguishing it from siblings like umami_get_pageviews or umami_get_stats.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not provide any guidance on when to use this tool versus alternatives, nor does it mention when not to use it. The parameter description hints at prerequisites but the main description lacks usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

umami_get_breakdownGet Umami BreakdownA
Read-only

Get a metric breakdown for a website and time range. Use expanded=true for detailed metrics or expanded=false for x/y breakdown rows.

ParametersJSON Schema
NameRequiredDescriptionDefault
websiteIdYesUmami website ID. Use umami_list_websites or umami_find_website first if you do not know it.
startAtYesAn ISO 8601 datetime string or a millisecond timestamp. Example: 2026-04-23T00:00:00+08:00 or 1776873600000.
endAtYesAn ISO 8601 datetime string or a millisecond timestamp. Example: 2026-04-23T00:00:00+08:00 or 1776873600000.
typeYesBreakdown dimension. Supported values: path, entry, exit, title, query, referrer, channel, domain, country, region, city, browser, os, device, language, screen, event, hostname, tag, distinctId.
limitNoMaximum number of rows to return. Umami defaults to 500 when omitted.
offsetNoNumber of rows to skip. Defaults to 0 when omitted.
expandedNoSet to true to call /metrics/expanded instead of /metrics.
filtersNoOptional filter object shared by Umami analytics endpoints.

TDQS

A4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare 'readOnlyHint: true', so the description does not need to restate that. The description adds some behavioral context about the two modes (detailed vs x/y breakdown rows), but it does not disclose other behavioral traits like rate limits, data freshness, or pagination behavior that might be relevant. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise at two sentences, with the purpose front-loaded. Every sentence adds value: the first states the core functionality, and the second provides key usage guidance on the 'expanded' parameter. No unnecessary words or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (8 parameters, nested filters, enum for 'type') and the absence of an output schema, the description is fairly complete. It covers the main purpose and the critical 'expanded' parameter. However, it could be more complete by briefly noting that other parameters (like 'type' and 'filters') are documented in the schema, but the description relies on the schema for those details, which is acceptable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds value beyond the schema by explaining the distinction between 'expanded=true' and 'expanded=false' (detailed metrics vs x/y breakdown rows). This clarifies the parameter's effect on the output format, which is not fully covered in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Get a metric breakdown for a website and time range.' It specifies the resource (metric breakdown), action (get), and scope (website and time range). It also distinguishes between two modes ('expanded=true' vs 'expanded=false'), which differentiates it from siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides guidance on when to use the 'expanded' parameter, but it does not explicitly state when to use this tool versus alternative tools like 'umami_get_stats' or 'umami_get_pageviews'. It lacks exclusions or alternative recommendations, making the usage context clear but incomplete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

umami_get_events_seriesGet Umami Events SeriesB
Read-only

Get custom event counts for a website over time. Returns event name, timestamp, and count rows.

ParametersJSON Schema
NameRequiredDescriptionDefault
websiteIdYesUmami website ID. Use umami_list_websites or umami_find_website first if you do not know it.
startAtYesAn ISO 8601 datetime string or a millisecond timestamp. Example: 2026-04-23T00:00:00+08:00 or 1776873600000.
endAtYesAn ISO 8601 datetime string or a millisecond timestamp. Example: 2026-04-23T00:00:00+08:00 or 1776873600000.
unitYesTime bucket unit. Allowed values: hour, day, month, year.
timezoneNoIANA timezone, for example Asia/Shanghai. Defaults to UMAMI_DEFAULT_TIMEZONE when omitted.
filtersNoOptional filter object shared by Umami analytics endpoints.

TDQS

B3.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true, so the safety profile is clear. The description adds that it returns rows with event name, timestamp, and count, but does not disclose any additional behavioral traits beyond what annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences with no wasted words. It is efficiently structured, though it could benefit from slightly more detail on output structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema, the description partially explains the return values (event name, timestamp, count rows) but lacks detail on the exact data structure (e.g., whether it's an array, how fields are named). For a tool with moderate complexity, this is somewhat incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with detailed parameter descriptions (e.g., websiteId referencing other tools, startAt/endAt examples, unit enum). The description adds minimal extra semantic information, so it is adequate but not exceptional.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it gets custom event counts over time for a website, with a specific resource (custom events) that distinguishes it from sibling tools like umami_get_pageviews (pageviews) and umami_get_breakdown (breakdown data).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like umami_get_pageviews or umami_get_stats. The description only explains what it does without contextualizing when it is the best choice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

umami_get_pageviewsGet Umami Pageviews SeriesA
Read-only

Get pageview and session time series for a website. Supports time bucketing, timezone, period comparison, and shared filters.

ParametersJSON Schema
NameRequiredDescriptionDefault
websiteIdYesUmami website ID. Use umami_list_websites or umami_find_website first if you do not know it.
startAtYesAn ISO 8601 datetime string or a millisecond timestamp. Example: 2026-04-23T00:00:00+08:00 or 1776873600000.
endAtYesAn ISO 8601 datetime string or a millisecond timestamp. Example: 2026-04-23T00:00:00+08:00 or 1776873600000.
unitYesTime bucket unit. Allowed values: hour, day, month, year.
timezoneNoIANA timezone, for example Asia/Shanghai. Defaults to UMAMI_DEFAULT_TIMEZONE when omitted.
compareNoOptional comparison mode. Use prev for previous period or yoy for year-over-year.
filtersNoOptional filter object shared by Umami analytics endpoints.

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, and the description aligns with a read operation. It adds useful context about the type of data returned (time series) and supported features. No behavioral traits are contradicted, and the description provides additional value beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the main purpose. Every sentence adds value without redundancy. Highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 7 parameters (4 required) and no output schema, the description covers the main features. However, it does not mention the output format, which would be helpful since no output schema is provided. Still, it is mostly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description mentions time bucketing, timezone, comparison, and filters, which corresponds to parameters, but does not add new meaning beyond what the schema already provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it retrieves 'pageview and session time series', using a specific verb and resource. It lists supported features (time bucketing, timezone, etc.), distinguishing it from sibling tools like umami_get_stats (aggregates) or umami_get_breakdown (dimension breakdown).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives. While it lists features, it lacks guidance on when not to use it or which sibling to choose instead, leaving the agent to infer from context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

umami_get_statsGet Umami StatsA
Read-only

Get summarized Umami stats for a website and time range. Returns pageviews, visitors, visits, bounces, totaltime, and comparison data.

ParametersJSON Schema
NameRequiredDescriptionDefault
websiteIdYesUmami website ID. Use umami_list_websites or umami_find_website first if you do not know it.
startAtYesAn ISO 8601 datetime string or a millisecond timestamp. Example: 2026-04-23T00:00:00+08:00 or 1776873600000.
endAtYesAn ISO 8601 datetime string or a millisecond timestamp. Example: 2026-04-23T00:00:00+08:00 or 1776873600000.
filtersNoOptional filter object shared by Umami analytics endpoints.

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already indicates the tool is read-only. The description adds no additional behavioral context (e.g., authentication, rate limits, error handling) beyond stating the action, which is consistent with the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description consists of two short sentences that front-load the main purpose and list return values. Every word is necessary and informative, with no redundancy or extraneous details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema, so the description's list of return metrics provides essential context. Combined with the rich input schema descriptions and readOnlyHint, it is largely complete. Minor gap: no indication of the response structure or aggregation details, but it suffices for agent invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with detailed parameter descriptions (e.g., examples for dates, explanations for websiteId). The tool description adds no extra parameter semantics; its mention of returned metrics pertains to output, not input parameters. Baseline 3 applies per guidelines.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get summarized Umami stats' and specifies the resource 'a website and time range', along with listing the returned metrics (pageviews, visitors, visits, bounces, totaltime, comparison data). This effectively distinguishes it from sibling tools like umami_get_pageviews or umami_get_breakdown.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for obtaining aggregate stats over a period, but it does not explicitly state when to prefer this tool over alternatives, nor does it mention when not to use it. No comparison or exclusion criteria are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

umami_list_websitesList Umami WebsitesA
Read-only

List accessible Umami websites. Returns id, name, domain, and createdAt for each website.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A3.8/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint=true; the description adds value by specifying return fields (id, name, domain, createdAt) but does not disclose additional behaviors like pagination or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences front-loaded with the action and result, no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a simple list operation given no parameters, readOnlyHint annotation, and no output schema; could mention if the list includes all websites or is paginated.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0 parameters, baseline is 4. The description adds meaning by detailing the returned fields, surpassing the schema's minimal coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'List' and clearly identifies the resource 'Umami websites', distinguishing it from sibling tools like 'umami_find_website' which implies searching.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives such as 'umami_find_website' for searching specific websites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

umami_pingUmami PingA
Read-only

Validate Umami configuration and authentication. Returns the auth mode, API base URL, instance URL, default timezone, and current user info.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate readOnlyHint=true, and the description confirms it is a read operation by specifying what it returns. It adds operational context about the return values beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence that efficiently conveys the tool's purpose and return values with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no parameters, no output schema, and the simple nature of the tool (validation), the description fully covers what an agent needs to know: what it does and what it returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are no parameters, so the baseline is 4. The description correctly provides no parameter information as none are needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool validates Umami configuration and authentication, listing specific return fields (auth mode, API base URL, instance URL, default timezone, current user info). This distinguishes it from sibling tools that retrieve analytics data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage after configuration to check connectivity, but does not explicitly state when not to use it or suggest alternatives. It is clear enough for basic guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 8 tool updatesv0.1.0
    • First observedumami_find_website
    • First observedumami_get_active
    • First observedumami_get_breakdown
    • First observedumami_get_events_series
    • First observedumami_get_pageviews
    • First observedumami_get_stats
    • First observedumami_list_websites
    • First observedumami_ping
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored across 8 tools

Disambiguation5/5

Each tool serves a distinct purpose: searching, listing, validating, and retrieving various analytics metrics (active visitors, breakdown, events, pageviews, stats). No overlap or ambiguity.

Naming Consistency5/5

All tool names follow a consistent 'umami_verb_noun' pattern (e.g., umami_find_website, umami_get_active). The pattern is uniform and predictable.

Tool Count5/5

With 8 tools, the set is well-scoped for an analytics API. It covers essential query operations without being bloated or sparse.

Completeness5/5

The tool set provides comprehensive read-only access to Umami analytics: website listing/search, active visitors, pageviews, events, breakdowns, stats, and authentication validation. No obvious gaps for querying use cases.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • umami-mcp-server

    frontedu
    A
    license
    Not graded
    quality
    C
    maintenance
    MCP server for Umami Analytics that provides read-only tools to query website stats, events, sessions, reports, and more, enabling natural language analytics queries.
    14 npm
    3
    MIT

  • umami-analytics-mcp

    matious89pl
    A
    license
    A
    quality
    D
    maintenance
    A security-first MCP server for Umami analytics (Cloud and self-hosted v3) enabling analytics, reporting, and administration with least privilege and credential-safe design.
    32
    25 npm
    MIT

  • @byterover/umami-mcp

    campfirein
    A
    license
    A
    quality
    D
    maintenance
    A read-only MCP server for Umami analytics, enabling natural language queries of website stats, traffic trends, events, sessions, and analytics reports.
    13
    14 npm
    1
    Elastic 2.0

Appeared in Searches