en es ko ru zh

Clicky MCP Server

Name: Clicky MCP Server
Author: colintoh

by colintoh

Overview Schema Source Related Servers Discussions Admin

TypeScript

Remote

Servidor MCP de Clicky

Un servidor del Protocolo de Contexto de Modelos (MCP) que expone los análisis web de Clicky como 11 herramientas para asistentes de IA: recuentos de visitantes, páginas principales, fuentes de tráfico, tasa de rebote, términos de búsqueda, visitantes en tiempo real y más. Consulta la Referencia de herramientas para ver la lista completa.

Inicio rápido

Necesitas:

Node.js 20+ instalado (node --version)
Un ID de sitio y una clave de sitio de Clicky: encuéntralos en https://clicky.com/user/preferences/site bajo "Info"

Este repositorio clonado y compilado una vez:

git clone https://github.com/colintoh/clicky-mcp.git
cd clicky-mcp && npm install && npm run build

Luego elige tu host MCP a continuación.

¿Por qué no hay un paso npm start? Los servidores stdio de MCP no se ejecutan como demonios independientes; tu host MCP (Claude Desktop, Claude Code, etc.) inicia el servidor como un subproceso bajo demanda y se comunica con él a través de stdin/stdout. No hay nada que "iniciar" por tu cuenta.

Claude Desktop

Abre el archivo de configuración (créalo si no existe):
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
- Linux: ~/.config/Claude/claude_desktop_config.json
Fusiona esto en el bloque mcpServers del archivo (reemplaza los tres marcadores de posición ALL_CAPS):
```
{
  "mcpServers": {
    "clicky-analytics": {
      "command": "ABSOLUTE_PATH_TO_NODE", // e.g. /Users/.../.nvm/versions/node/v25.2.1/bin/node
      "args": ["ABSOLUTE_PATH_TO_CLICKY_MCP_FOLDER/dist/index.js"], // e.g. /Users/.../clicky-mcp/dist/index.js
      "env": {
        "CLICKY_SITE_ID": "YOUR_SITE_ID",
        "CLICKY_SITE_KEY": "YOUR_SITE_KEY"
      }
    }
  }
}
```
Obtén ABSOLUTE_PATH_TO_NODE ejecutando which node en tu terminal. No pongas simplemente "node": Claude Desktop se inicia a través de launchd con un PATH mínimo que no incluye nvm o homebrew, por lo que un "node" simple fallará silenciosamente. Lo mismo ocurre con la ruta a dist/index.js: debe ser absoluta.
Cierra completamente Claude Desktop (⌘Q en macOS; cerrar la ventana no es suficiente), luego vuelve a abrirlo.
Verifica preguntándole a Claude "list my Clicky MCP tools" (lista mis herramientas MCP de Clicky): deberías ver 11 herramientas.

Si algo sale mal, consulta Solución de problemas.

Claude Code

Un comando:

claude mcp add clicky-analytics \
  -e CLICKY_SITE_ID=YOUR_SITE_ID \
  -e CLICKY_SITE_KEY=YOUR_SITE_KEY \
  -- node /absolute/path/to/clicky-mcp/dist/index.js

Esto escribe en ~/.claude.json por defecto. Añade --scope project para escribir en un .mcp.json local del proyecto en su lugar. Reinicia Claude Code (o ejecuta /mcp para actualizar) y las 11 herramientas estarán disponibles.

Inspector MCP (depuración)

Úsalo cuando quieras llamar a las herramientas directamente sin comprometer el servidor a un host; es útil para inspeccionar esquemas o solucionar problemas de respuestas:

npx @modelcontextprotocol/inspector node dist/index.js

Luego abre la URL impresa, establece CLICKY_SITE_ID y CLICKY_SITE_KEY como variables de entorno en la interfaz de usuario del Inspector (o pasa --site-id … --site-key … como argumentos de CLI después de dist/index.js), y explora.

Related MCP server: Plausible MCP Server

Parámetros de fecha

Cada herramienta que reconoce fechas acepta o bien un rango de fechas explícito o una palabra clave de fecha relativa de Clicky, pero no ambos:

Explícito: start_date + end_date, ambos en formato YYYY-MM-DD, rango ≤ 31 días.
Palabra clave: date_range, uno de today, yesterday, last-7-days, last-30-days, this-week, last-week, this-month, last-month, this-year, last-year.

Ejemplo:

{ "date_range": "last-7-days" }

Referencia de herramientas

Las 11 herramientas, ordenadas alfabéticamente según su caso de uso.

get_total_visitors

Recuentos totales de visitantes para un período.

start_date / end_date o date_range

get_actions

Total de visitas a páginas/acciones para un período.

start_date / end_date o date_range
limit (número, opcional, máx. 1000)

get_bounce_rate

Tasa de rebote y tiempo promedio en el sitio para un período.

start_date / end_date o date_range

get_visitors_online

Recuento de visitantes en tiempo real y segmentación. No requiere parámetros.

get_top_pages

Páginas más populares para un período.

start_date / end_date o date_range
limit (número, opcional, máx. 1000)

get_page_traffic

Datos de tráfico para una URL de página específica.

url (cadena, obligatorio)
start_date / end_date o date_range

get_traffic_sources

Desglose de fuentes de tráfico; opcionalmente filtra por URL de página.

start_date / end_date o date_range
page_url (cadena, opcional): URL completa o ruta

get_referring_domains

Dominios de referencia principales que envían tráfico.

start_date / end_date o date_range
limit (número, opcional, máx. 1000)

get_domain_visitors

Datos de visitantes filtrados por dominio de referencia, con segmentación opcional.

domain (cadena, obligatorio)
start_date / end_date o date_range
segments (matriz, opcional): ["pages", "visitors"]. Por defecto es ["visitors"].
limit (número, opcional, máx. 1000)

get_searches

Términos de búsqueda principales que trajeron visitantes.

start_date / end_date o date_range
limit (número, opcional, máx. 1000)

get_countries

Desglose de visitantes por país.

start_date / end_date o date_range
limit (número, opcional, máx. 1000)

Límites de la API

Impuestos por Clicky, no por este servidor:

Rango de fechas explícito máximo: 31 días
Resultados máximos por solicitud: 1,000 elementos
Una solicitud simultánea por IP por ID de sitio

Solución de problemas

"Claude Desktop no ve el servidor". Revisa el registro de inicio en ~/Library/Logs/Claude/mcp-server-clicky-analytics.log. La causa más común es que node no esté en el PATH de launchd de Claude Desktop; soluciónalo reemplazando "command": "node" con la ruta absoluta obtenida de which node. La segunda causa más común es olvidar cerrar completamente Claude Desktop (⌘Q, no solo cerrar la ventana).

"El rango de fechas no puede exceder los 31 días". Ese es un límite de la API de Clicky, no nuestro. Reduce el rango o usa una palabra clave de date_range como last-30-days.

Desarrollo local

Para trabajar en el servidor, no solo usarlo.

npm install         # install deps
npm run dev         # run with tsx, watching for changes (used for local testing only)
npm run build       # compile TS to dist/
npm test            # 46 unit tests, offline, no credentials needed
npm run test:integration  # live API smoke test (requires .env or env vars)

Para el desarrollo local, las credenciales pueden provenir de un archivo .env en la raíz del proyecto:

CLICKY_SITE_ID=your_site_id
CLICKY_SITE_KEY=your_site_key

.env está ignorado por git. No uses .env para hosts como Claude Desktop; pasa las credenciales a través del bloque env de la configuración del host, como se muestra en Inicio rápido. El servidor solo carga .env cuando las credenciales no están ya en el entorno.

Un hook de git pre-push en .githooks/pre-push ejecuta automáticamente npm test antes de cualquier push que actualice la rama remota main, por lo que una regresión no puede pasar desapercibida. Se instala automáticamente mediante el script prepare de npm después de npm install. Los pushes a ramas de características no están restringidos. Evítalo en caso de emergencia con git push --no-verify.

Estructura del proyecto

clicky-mcp/
├── src/
│   ├── index.ts              # MCP server + tool dispatcher
│   ├── clicky-client.ts      # Clicky HTTP API client
│   ├── date-utils.ts         # Shared date param builder
│   └── tools/                # One file per tool
├── test/                     # node:test unit tests
├── scripts/verify.mjs        # Live API smoke runner
├── .githooks/pre-push        # Auto-installed test gate for main
├── package.json
├── tsconfig.json
└── README.md

Instalación de este MCP a través de un agente de IA

Si deseas que un agente de IA (por ejemplo, Claude Code en otro proyecto) instale este MCP por ti, indícale esta sección. El agente debe:

Clonar y compilar:

git clone https://github.com/colintoh/clicky-mcp.git
cd clicky-mcp && npm install && npm run build

Pedir al usuario su ID de sitio y clave de sitio de Clicky (https://clicky.com/user/preferences/site).
Ejecutar which node y capturar la ruta absoluta.
Localizar la configuración de Claude Desktop del usuario (rutas en Inicio rápido › Claude Desktop) y fusionar el fragmento mcpServers de esa sección, sustituyendo la ruta absoluta de node, la ruta absoluta de dist/index.js y las credenciales del usuario.
Decirle al usuario que reinicie completamente Claude Desktop (⌘Q), luego verificar preguntando a Claude "list my Clicky MCP tools" (lista mis herramientas MCP de Clicky): deberían aparecer 11 herramientas.

Para Claude Code, el comando único claude mcp add en Inicio rápido › Claude Code es más rápido y escribe la configuración en un solo paso.

Licencia

MIT

Available Tools

5 tools

get_domain_visitorsC

Get visitors filtered by domain from Clicky analytics with optional segmentation data

ParametersJSON Schema

Name	Required	Description
`domain`	Yes	Domain name to filter by (e.g., "facebook.com", "google.com")
`start_date`	Yes	Start date in YYYY-MM-DD format
`end_date`	Yes	End date in YYYY-MM-DD format
`segments`	No	Optional array of segments to include (pages, visitors). Defaults to visitors only. "visitors" gets the total number of visitors from the domain. "pages" get the list of pages and its visited count from the domain.
`limit`	No	Optional limit for results (max 1000)

TDQS

C2.9/5.0

Behavior2/5

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

With no annotations provided, the description carries full burden but only states it 'gets' data, implying a read-only operation without confirming safety or permissions. It mentions optional segmentation but doesn't disclose behavioral traits like rate limits, authentication needs, or what happens if parameters are invalid. This leaves significant gaps for a tool with 5 parameters.

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, efficient sentence that front-loads the core purpose ('Get visitors filtered by domain') and adds a useful detail ('with optional segmentation data'). There is zero waste, and every word earns its place.

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

Completeness2/5

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

Given no annotations and no output schema, the description is incomplete for a tool with 5 parameters. It doesn't explain return values, error conditions, or behavioral constraints like rate limits or authentication requirements. For a data retrieval tool in analytics, more context is needed to use it effectively.

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 the schema fully documents all 5 parameters. The description adds minimal value beyond the schema by mentioning 'optional segmentation data', which loosely relates to the 'segments' parameter but doesn't provide additional meaning or context. Baseline 3 is appropriate as the schema does the heavy lifting.

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

Purpose4/5

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

The description clearly states the verb ('Get') and resource ('visitors filtered by domain from Clicky analytics'), specifying the filtering mechanism. It distinguishes from siblings like 'get_total_visitors' by mentioning domain filtering, but doesn't explicitly contrast with 'get_traffic_sources' or 'get_page_traffic' which might also involve visitor 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 'get_total_visitors' or 'get_traffic_sources' is provided. The description mentions optional segmentation data but doesn't clarify when segmentation is beneficial or when other tools might be more appropriate.

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

get_page_trafficC

Get traffic data for a specific page by filtering with its URL

ParametersJSON Schema

Name	Required	Description
`url`	Yes	Full URL or path of the page to get traffic for (e.g., https://example.com/path or /path)
`start_date`	Yes	Start date in YYYY-MM-DD format
`end_date`	Yes	End date in YYYY-MM-DD format

TDQS

C2.9/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool retrieves traffic data but doesn't mention any behavioral traits such as rate limits, authentication requirements, data freshness, or what the output format looks like (e.g., metrics like pageviews, sessions). This is a significant gap for a tool with no annotation coverage.

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, efficient sentence that directly states the tool's purpose without unnecessary words. It's front-loaded and every part earns its place, making it easy to parse quickly.

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

Completeness2/5

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

Given the complexity of a traffic data tool with no annotations and no output schema, the description is incomplete. It lacks details on what traffic data is returned (e.g., metrics, format), behavioral aspects like permissions or limits, and differentiation from sibling tools, leaving the agent with insufficient context for effective use.

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 description adds minimal value beyond the input schema, which has 100% coverage with clear descriptions for all three parameters (url, start_date, end_date). It implies URL-based filtering but doesn't provide additional context like URL format constraints or date range implications. Baseline 3 is appropriate as the schema does the heavy lifting.

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

Purpose4/5

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

The description clearly states the tool's purpose with a specific verb ('Get') and resource ('traffic data for a specific page'), and it specifies the filtering mechanism ('by filtering with its URL'). However, it doesn't explicitly differentiate this tool from its siblings like 'get_top_pages' or 'get_total_visitors', which likely provide different scopes or aggregations of traffic 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?

The description provides no guidance on when to use this tool versus its siblings (e.g., 'get_domain_visitors', 'get_top_pages', 'get_total_visitors', 'get_traffic_sources'). It mentions filtering by URL but doesn't explain alternative scenarios or exclusions, leaving the agent to infer usage from tool names alone.

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

get_top_pagesC

Get top pages for a date range from Clicky analytics

ParametersJSON Schema

Name	Required	Description
`start_date`	Yes	Start date in YYYY-MM-DD format
`end_date`	Yes	End date in YYYY-MM-DD format
`limit`	No	Maximum number of pages to return (default: API default, max: 1000)

TDQS

C2.9/5.0

Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions retrieving 'top pages' but doesn't specify what 'top' means (e.g., by views, visits, or other metrics), how results are ordered, if there's pagination, rate limits, authentication needs, or error handling. This leaves significant gaps in understanding the tool's behavior beyond basic functionality.

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, efficient sentence that directly states the tool's purpose without unnecessary words or fluff. It's front-loaded with the core action and resource, making it easy to parse quickly, which is ideal for conciseness in tool definitions.

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

Completeness2/5

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

Given the lack of annotations and output schema, and the description's minimal detail, it's incomplete for a tool that likely returns complex analytics data. It doesn't explain what 'top pages' entails, the structure of the output, or behavioral aspects like data freshness or limitations, leaving the agent with insufficient context to use the tool effectively beyond basic parameter input.

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 clear documentation for each parameter (start_date, end_date, limit) including formats, constraints, and defaults. The description adds no additional semantic details beyond implying date-range usage, so it meets the baseline of 3 where the schema handles most of the parameter explanation without extra value from the description.

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

Purpose4/5

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

The description clearly states the action ('Get') and resource ('top pages') with the source ('from Clicky analytics') and scope ('for a date range'), making the purpose specific and understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_page_traffic' or 'get_total_visitors', which might also involve date ranges or page-related data, leaving some ambiguity about uniqueness.

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 provides no guidance on when to use this tool versus alternatives like 'get_page_traffic' or 'get_traffic_sources', nor does it mention any prerequisites, exclusions, or specific contexts. It only states what the tool does, without indicating appropriate scenarios or comparisons with siblings.

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

get_total_visitorsC

Get total visitors for a date range from Clicky analytics

ParametersJSON Schema

Name	Required	Description	Default
`start_date`	Yes	Start date in YYYY-MM-DD format
`end_date`	Yes	End date in YYYY-MM-DD format

TDQS

C2.9/5.0

Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It states what the tool does but doesn't describe how it behaves: no information about authentication requirements, rate limits, error handling, or what the return value looks like (e.g., is it a single number, a structured object?). For a data retrieval tool with zero annotation coverage, this leaves significant gaps in understanding operational behavior.

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, efficient sentence that communicates the core purpose without unnecessary words. It's appropriately sized for a simple retrieval tool and front-loads the essential information ('Get total visitors'). Every word earns its place.

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

Completeness2/5

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

Given the lack of annotations and output schema, the description is incomplete for effective tool use. While the purpose is clear, it doesn't address key contextual elements: what format the result returns, whether authentication is needed, any rate limits, or how it differs from sibling tools. For a data retrieval tool in an analytics context, more operational context would be helpful.

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 the input schema fully documents both parameters (start_date and end_date) with format patterns. The description adds no additional parameter semantics beyond implying date-range filtering. This meets the baseline expectation when schema does the heavy lifting, but doesn't provide extra context like date range constraints or timezone handling.

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

Purpose4/5

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

The description clearly states the verb ('Get') and resource ('total visitors'), and specifies the data source ('from Clicky analytics'). It distinguishes itself from siblings by focusing on total visitor counts rather than domain-specific, page-level, or source-level metrics. However, it doesn't explicitly contrast with sibling tools like 'get_domain_visitors' which might also provide visitor counts.

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 provides no guidance on when to use this tool versus alternatives like 'get_domain_visitors' or 'get_traffic_sources'. It doesn't mention prerequisites, limitations, or specific use cases. The agent must infer usage from the tool name alone, which is insufficient for optimal tool selection.

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

get_traffic_sourcesB

Get traffic sources breakdown from Clicky analytics. Optionally filter by specific page URL.

ParametersJSON Schema

Name	Required	Description
`start_date`	Yes	Start date in YYYY-MM-DD format
`end_date`	Yes	End date in YYYY-MM-DD format
`page_url`	No	Optional: Full URL or path of the page to get traffic sources for (e.g., https://example.com/path or /path)

TDQS

B3.3/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions an optional filter but does not describe the return format, pagination, rate limits, authentication needs, or whether this is a read-only operation. For a tool with no annotations, this leaves significant gaps in understanding its behavior.

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, efficient sentence that front-loads the main purpose and includes the optional filter. There is no wasted language, and it is appropriately sized for the tool's complexity.

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 no annotations and no output schema, the description is incomplete for a tool with three parameters. It covers the basic purpose and optional filtering but lacks details on return values, error handling, or behavioral traits. This is adequate as a minimum but has clear gaps in providing a full context for the agent.

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 the schema already documents all parameters (start_date, end_date, page_url) with descriptions and formats. The description adds marginal value by mentioning the optional filter by page URL, but does not provide additional semantics beyond what the schema specifies, such as examples or constraints.

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

Purpose4/5

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

The description clearly states the verb ('Get') and resource ('traffic sources breakdown from Clicky analytics'), making the purpose evident. It distinguishes from siblings by focusing on traffic sources rather than visitors, page traffic, or top pages. However, it doesn't explicitly contrast with sibling tools like 'get_domain_visitors' or 'get_page_traffic' beyond the resource type.

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 usage through the optional filter by page URL, suggesting it can be used for overall traffic sources or per-page analysis. However, it lacks explicit guidance on when to use this tool versus alternatives like 'get_page_traffic' or 'get_domain_visitors', and does not mention prerequisites or exclusions.

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.

5 tool updatesSep 24, 2025
- First observedget_domain_visitors
- First observedget_page_traffic
- First observedget_top_pages
- First observedget_total_visitors
- First observedget_traffic_sources

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

A3.5/5.0

Scored 2026-04-18 08:50 across 5 tools

Disambiguation5/5

Each tool has a clearly distinct purpose targeting different analytics dimensions: domain visitors, page traffic, top pages, total visitors, and traffic sources. There is no overlap in functionality, making it easy for an agent to select the correct tool without confusion.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with 'get_' prefix and descriptive nouns (e.g., get_domain_visitors, get_page_traffic). This uniformity enhances readability and predictability across the toolset.

Tool Count5/5

With 5 tools, the server is well-scoped for analytics retrieval, covering key metrics like visitors, pages, and traffic sources. Each tool earns its place without being overly sparse or bloated, fitting typical use cases effectively.

Completeness4/5

The toolset provides comprehensive read-only coverage for analytics data, including filtering and segmentation options. A minor gap exists in lacking write or configuration tools (e.g., setting up analytics), but this is reasonable for a data retrieval-focused server, and agents can work around this limitation.

Maintenance

ActivityInactive

ResponsivenessSlow

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

analytics
com.zenovay
Real-time web analytics for AI agents: query traffic, funnels, revenue, and manage your sites.
Monitoring Observability
2
Hitsteps Analytics and OperationsOAuth
com.hitsteps
AI access to Hitsteps analytics, live visitors, uptime, goals, alerts, and chats.
Monitoring Observability
2
Measure.events Analytics A
io.github.meetclawdius
Privacy-first web analytics. Query pageviews, referrers, trends, and AI insights.
Monitoring Search Data Platforms
622
Betterlytics
io.betterlytics
Query your Betterlytics web analytics from AI agents: traffic, funnels, journeys, errors, uptime.
Monitoring Observability
1170

Related MCP Servers

Umami Analytics MCP Server
Monitoring Web Scraping Search
jakeyShakey
A
license
Not graded
quality
D
maintenance
Enhances Claude's capabilities by providing access to website analytics data from Umami, enabling analysis of user behavior, website performance tracking, and data-driven insights generation.
Updated 2 years ago (2025-03-06 11:37 UTC)
9
MIT
Plausible MCP Server
Monitoring Search
AVIMBU
F
license
B
quality
D
maintenance
Allows AI models to query and retrieve analytics data from Plausible Analytics through the Plausible API, enabling natural language interactions with website statistics.
Updated 2 years ago (2025-03-19 12:51 UTC)
1
8
-
Umami MCP Server
Monitoring Search Web Scraping
lukasschmit
A
license
A
quality
F
maintenance
Enables AI assistants to interact with Umami Analytics for both Cloud and self-hosted instances. It provides tools to retrieve website statistics, visitor metrics, pageview trends, and real-time active user counts.
Updated 8 months ago (2026-02-21 03:32 UTC)
5
1
MIT
plausible-mcp
Monitoring Observability
alexanderop
F
license
Not graded
quality
D
maintenance
Enables querying Plausible Analytics data for website statistics, traffic, engagement, and conversions through natural language, with support for filters, dimensions, and time-series.
Updated 8 months ago (2026-02-09 04:01 UTC)
6
-

Appeared in Searches

Search results for 'Clarik'