Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@ActiveCampaign MCP Server find the contact with email maria@example.com"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Um servidor MCP (Model Context Protocol) para integração com a API do ActiveCampaign, permitindo consultas e análises de contatos e eventos de tracking através de ferramentas AI-friendly.
Busca por email: Encontre contatos usando endereço de email
Busca por ID: Recupere contatos específicos pelo ID
Pesquisa avançada: Busque contatos com filtros e paginação
Dados enriquecidos: Inclui campos customizados, tags e listas
Logs de eventos: Acesse histórico completo de eventos por contato
Filtros avançados: Filtre por tipo de evento, data e outros critérios
Busca por email: Obtenha tracking logs usando apenas o email do contato
Dados estruturados: Eventos formatados com timestamps, descrições e metadata
Email: open, click, sent, bounce, reply, forward
Gerenciamento: subscribe, unsubscribe, update
Vendas: deal_add, deal_update, deal_delete
Produtividade: note_add, task_add
Automação: automation_start, automation_complete
Related MCP server: mautic-mcp
Node.js 18 ou superior
NPM ou PNPM
Conta no ActiveCampaign com acesso à API
Clone o repositório
git clone https://github.com/mmarqueti/activecampaign-mcp-server.git
cd activecampaign-mcp-serverInstale as dependências
# Com npm
npm install
# Com pnpm
pnpm installConfigure as variáveis de ambiente
cp .env.example .envEdite o arquivo .env com suas credenciais:
ACTIVECAMPAIGN_API_URL=https://seuaccount.api-us1.com
ACTIVECAMPAIGN_API_KEY=sua-api-key-aquiCompile o projeto
# Com npm
npm run build
# Com pnpm
pnpm buildAcesse sua conta do ActiveCampaign
Vá para Settings > Developer
Copie sua API URL e API Key
Cole as credenciais no arquivo .env
Variável | Descrição | Exemplo |
| URL base da API |
|
| Chave da API |
|
# Modo desenvolvimento
npm run dev
# Modo produção
npm startPara usar este servidor MCP com o Claude Desktop, você precisa configurá-lo no arquivo de configuração do Claude:
⚠️ Nota: Esta funcionalidade requer Claude Desktop versão 0.7.0 ou superior com suporte a MCP.
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.jsonEdite o arquivo claude_desktop_config.json e adicione:
{
"mcpServers": {
"activecampaign": {
"command": "node",
"args": ["/caminho/para/seu/projeto/dist/index.js"],
"env": {
"ACTIVECAMPAIGN_API_URL": "https://seuaccount.api-us1.com",
"ACTIVECAMPAIGN_API_KEY": "sua-api-key-aqui"
}
}
}
}Exemplo com caminho completo:
{
"mcpServers": {
"activecampaign": {
"command": "node",
"args": ["/Users/seunome/projetos/activecampaign-mcp-server/dist/index.js"],
"env": {
"ACTIVECAMPAIGN_API_URL": "https://seuaccount.api-us1.com",
"ACTIVECAMPAIGN_API_KEY": "abc123def456ghi789"
}
}
}
}Certifique-se de que o projeto está compilado:
# Com npm
npm run build
# Com pnpm (recomendado)
pnpm buildAntes de configurar no Claude Desktop, você pode testar se o servidor está funcionando:
# Teste com inspector MCP
pnpm inspect
# Ou teste direto
node dist/index.jsFeche completamente o Claude Desktop e abra novamente para carregar a nova configuração.
No Claude Desktop, você deve poder usar comandos como:
"Busque o contato com email usuario@exemplo.com"
"Mostre os eventos de tracking do contato ID 123"
"Pesquise contatos com o nome João Silva"
Se as ferramentas não aparecerem:
Verifique o caminho: Certifique-se de que o caminho para dist/index.js está correto
Verifique a compilação: Execute npm run build novamente
Verifique as credenciais: Confirme se a API URL e Key estão corretas
Verifique os logs: Olhe os logs do Claude Desktop para erros
Reinicie completamente: Feche o Claude Desktop pelo Activity Monitor/Task Manager
Configuração alternativa com variáveis de ambiente do sistema:
{
"mcpServers": {
"activecampaign": {
"command": "node",
"args": ["/caminho/para/seu/projeto/dist/index.js"]
}
}
}Neste caso, defina as variáveis no seu sistema:
export ACTIVECAMPAIGN_API_URL="https://seuaccount.api-us1.com"
export ACTIVECAMPAIGN_API_KEY="sua-api-key-aqui"Uma vez configurado, você pode testar as ferramentas diretamente no Claude Desktop:
Exemplo de comandos:
🔍 Buscar contato:
"Busque informações do contato john@exemplo.com no ActiveCampaign"
📊 Análise de engajamento:
"Mostre os eventos de email dos últimos 30 dias para o contato ID 123"
🔍 Pesquisa avançada:
"Pesquise todos os contatos que têm 'CEO' no nome e me mostre suas informações completas"
📈 Relatório de atividade:
"Analise o comportamento de engajamento do contato maria@empresa.com nos últimos 3 meses"{
"name": "get_contact_by_email",
"arguments": {
"email": "usuario@exemplo.com"
}
}{
"name": "get_contact_by_id",
"arguments": {
"contactId": "123"
}
}{
"name": "search_contacts",
"arguments": {
"query": "João Silva",
"limit": 10
}
}{
"name": "get_contact_tracking_logs",
"arguments": {
"contactId": "123",
"limit": 50,
"offset": 0,
"eventType": "open",
"dateRange": {
"start": "2024-01-01",
"end": "2024-12-31"
}
}
}{
"name": "get_contact_tracking_logs_by_email",
"arguments": {
"email": "usuario@exemplo.com",
"limit": 100,
"eventType": "click"
}
}src/
├── index.ts # Servidor MCP principal
├── types/
│ └── index.ts # Interfaces e tipos TypeScript
└── tools/
├── index.ts # Exportações das ferramentas
├── contacts.ts # Ferramentas de contatos
└── tracking.ts # Ferramentas de trackingModular: Cada conjunto de ferramentas está em seu próprio arquivo
Tipada: Interfaces TypeScript para todos os dados
Escalável: Fácil adicionar novas ferramentas
Testável: Classes isoladas para facilitar testes
{
"id": "123",
"email": "usuario@exemplo.com",
"firstName": "João",
"lastName": "Silva",
"phone": "+55 11 99999-9999",
"fieldValues": [
{
"field": "Empresa",
"value": "Exemplo Corp"
}
],
"tags": ["Cliente VIP", "Newsletter"],
"lists": [
{
"list": "Newsletter Mensal",
"status": "active"
}
],
"cdate": "2024-01-15T10:30:00Z",
"udate": "2024-01-20T14:45:00Z"
}{
"summary": {
"total": 25,
"count": 25,
"limit": 100,
"offset": 0,
"eventTypes": {
"open": 15,
"click": 8,
"sent": 2
}
},
"events": [
{
"id": "456",
"type": "open",
"timestamp": "2024-01-15T10:30:00-03:00",
"date": "2024-01-15T13:30:00.000Z",
"contact": "123",
"subscriberId": "123",
"hash": "abc123",
"description": "Email foi aberto",
"campaign": {
"id": "789",
"name": "Newsletter Janeiro"
}
}
]
}Contribuições são muito bem-vindas! Para contribuir:
Fork o projeto
Crie uma branch para sua feature (git checkout -b feature/nova-funcionalidade)
Commit suas mudanças (git commit -m 'Adiciona nova funcionalidade')
Push para a branch (git push origin feature/nova-funcionalidade)
Abra um Pull Request
# Instalar dependências
pnpm install
# Executar em modo desenvolvimento
pnpm dev
# Executar testes
pnpm test
# Verificar linting
pnpm lint
# Build para produção
pnpm buildEste projeto está licenciado sob a licença MIT. Veja o arquivo LICENSE para mais detalhes.
Se você encontrar algum problema ou tiver dúvidas:
Verifique se existe uma issue similar
Crie uma nova issue com detalhes do problema
Entre em contato através das issues do GitHub
Busca um contato no ActiveCampaign pelo email
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | Email do contato a ser buscado |
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 it searches for a contact by email but doesn't describe what happens if no contact is found (e.g., returns null, error), if it's case-sensitive, rate limits, authentication needs, or the return format. For a lookup tool with zero annotation coverage, 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.
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 appropriately sized for a simple lookup tool and front-loaded with the key action and resource, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (1 parameter, 100% schema coverage) but lack of annotations and output schema, the description is incomplete. It doesn't explain what is returned (e.g., contact object, error handling) or behavioral aspects like idempotency. For a tool that interacts with an external service, more context on outcomes and constraints is needed to be fully helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with the single parameter 'email' documented as 'Email do contato a ser buscado'. The description adds no additional meaning beyond this, such as format requirements or examples. With high schema coverage, the baseline is 3, as the schema does the heavy lifting, but the description doesn't compensate with extra context.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Busca' - search) and resource ('contato no ActiveCampaign'), making the purpose understandable. It specifies the search criterion ('pelo email'), which distinguishes it from sibling tools like get_contact_by_id. However, it doesn't explicitly differentiate from search_contacts, which might also support email searches.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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_contact_by_id or search_contacts. It doesn't mention prerequisites, such as requiring an existing contact with that email, or exclusions, like what happens if multiple contacts share the same email. Usage is implied by the name but not explicitly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Busca um contato no ActiveCampaign pelo ID
| Name | Required | Description | Default |
|---|---|---|---|
| contactId | Yes | ID do contato a ser buscado |
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 this is a search operation, implying it's read-only and non-destructive, but doesn't confirm this explicitly. It lacks details on error handling (e.g., what happens if the ID is invalid), rate limits, authentication requirements, or return format. For a tool with zero annotation coverage, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence in Portuguese that directly states the tool's function. It's front-loaded with the core purpose and wastes no words, making it highly concise and well-structured for quick understanding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (single parameter, no output schema, no annotations), the description is minimally adequate. It covers the basic purpose but lacks behavioral details and usage guidance. For a simple lookup tool, this might suffice, but it doesn't provide a complete picture for optimal agent use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds minimal value beyond the input schema. It mentions 'pelo ID' (by ID), which aligns with the schema's 'contactId' parameter, but doesn't provide additional context like ID format or examples. With 100% schema description coverage (the schema fully documents the single parameter), the baseline is 3, 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.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Busca um contato no ActiveCampaign pelo ID' (Search for a contact in ActiveCampaign by ID). It specifies the verb (search), resource (contact), and method (by ID). However, it doesn't explicitly differentiate from sibling tools like get_contact_by_email, which is a similar lookup by different identifier.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. It doesn't mention sibling tools like get_contact_by_email (for email-based lookup) or search_contacts (for broader searches), nor does it specify prerequisites or exclusions. The agent must infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Busca os logs de eventos/tracking de um contato específico
| Name | Required | Description | Default |
|---|---|---|---|
| contactId | Yes | ID do contato para buscar os logs de eventos | |
| dateRange | No | Filtrar por intervalo de datas | |
| eventType | No | Filtrar por tipo de evento específico (opcional) | |
| limit | No | Limite de resultados (padrão: 100, máximo: 100) | |
| offset | No | Offset para paginação (padrão: 0) |
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. While 'busca' (search) implies a read-only operation, the description doesn't clarify if this is safe (non-destructive), whether it requires specific permissions, or if there are rate limits. It also doesn't describe the return format (e.g., list of logs with fields) or pagination behavior beyond what the schema hints at with 'limit' and 'offset'. 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence in Portuguese: 'Busca os logs de eventos/tracking de um contato específico.' It's front-loaded with the core purpose, has zero wasted words, and is appropriately sized for the tool's function. Every part of the sentence earns its place by specifying what is being searched and for what resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (5 parameters, no output schema, no annotations), the description is incomplete. It doesn't address behavioral aspects like safety or permissions, provide usage guidelines relative to siblings, or explain the output (since there's no output schema). For a tool that retrieves logs with filtering and pagination, more context is needed to help an agent use it effectively, especially with sibling tools like 'get_contact_tracking_logs_by_email' present.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, meaning all parameters are documented in the schema itself (e.g., 'contactId' for the contact ID, 'dateRange' for filtering by date, 'eventType' with enum values). The description doesn't add any additional meaning beyond this, such as explaining parameter interactions or usage examples. With high schema coverage, the baseline score is 3, as the description doesn't compensate but also doesn't detract.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Busca os logs de eventos/tracking de um contato específico' (Search the event/tracking logs of a specific contact). It specifies the verb 'busca' (search) and the resource 'logs de eventos/tracking' (event/tracking logs), and distinguishes it from siblings like 'get_contact_by_email' or 'search_contacts' by focusing on logs rather than contact details. However, it doesn't explicitly differentiate from 'get_contact_tracking_logs_by_email', which appears to be a similar tool with a different parameter approach.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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. It doesn't mention siblings like 'get_contact_tracking_logs_by_email' or explain scenarios where this tool is preferred over others (e.g., when you have a contact ID vs. email). There's also no information about prerequisites, such as needing an existing contact, or exclusions for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Busca os logs de eventos/tracking de um contato pelo email
| Name | Required | Description | Default |
|---|---|---|---|
| Yes | Email do contato para buscar os logs de eventos | ||
| eventType | No | Filtrar por tipo de evento específico (opcional) | |
| limit | No | Limite de resultados (padrão: 100) | |
| offset | No | Offset para paginação (padrão: 0) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but offers minimal behavioral information. It mentions searching logs but doesn't disclose important traits like whether this is a read-only operation, what permissions are needed, if there are rate limits, what format the logs return in, or how pagination works (though parameters suggest it).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence in Portuguese that directly states the tool's purpose. It's appropriately sized and front-loaded with the core functionality. There's no wasted verbiage or unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 4 parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what the logs contain, their format, or how results are structured. While the schema covers parameters well, the description fails to provide necessary context about the tool's behavior and output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 thoroughly. The description adds no additional parameter information beyond what's in the schema (email for searching, optional eventType filtering, limit/offset for pagination). Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Busca' - searches) and resource ('logs de eventos/tracking de um contato'), specifying it's done by email. However, it doesn't explicitly differentiate from sibling tools like 'get_contact_tracking_logs' (which likely uses a different identifier) or 'search_contacts' (which might have broader search capabilities).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. The description doesn't mention sibling tools like 'get_contact_tracking_logs' (which might use ID instead of email) or 'search_contacts' (which might search across multiple contacts). There's no context about prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Busca contatos no ActiveCampaign com filtros
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Limite de resultados (padrão: 20) | |
| query | Yes | Termo de busca (nome, email, etc.) |
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 mentions filtering capability ('com filtros') but doesn't describe what the search returns (full contact objects? limited fields?), pagination behavior, rate limits, authentication requirements, or error conditions. For a search tool with zero annotation coverage, this leaves significant behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence in Portuguese that states the core functionality without unnecessary words. It's appropriately sized for a simple search tool and front-loads the essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a search tool with no annotations and no output schema, the description is incomplete. It doesn't explain what the search returns, how results are structured, whether there's pagination beyond the 'limit' parameter, or how the search interacts with the ActiveCampaign platform. The agent lacks sufficient context to understand the tool's full behavior.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with both parameters well-documented in the schema: 'limit' with default value and 'query' with search scope examples. The description adds minimal value beyond the schema, only implying filtering capability without specifying how filters work beyond the 'query' parameter. Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Busca contatos no ActiveCampaign com filtros' (Search contacts in ActiveCampaign with filters). It specifies the verb ('busca' - search), resource ('contatos' - contacts), and platform ('ActiveCampaign'), but doesn't explicitly differentiate from sibling tools like 'get_contact_by_email' or 'get_contact_by_id' which appear to be more specific lookup methods.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
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 the sibling tools. It doesn't mention alternatives, prerequisites, or specific contexts where this search tool is preferable over the more targeted 'get_contact_by_email' or 'get_contact_by_id' tools. The agent must infer usage from the tool name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get_contact_by_emailget_contact_by_idget_contact_tracking_logsget_contact_tracking_logs_by_emailsearch_contactsScored across 5 tools
The tools have some overlap that could cause confusion, particularly between get_contact_by_email and get_contact_by_id which serve similar purposes but use different identifiers, and between get_contact_tracking_logs and get_contact_tracking_logs_by_email which are essentially duplicates with different input methods. However, the descriptions clarify the distinctions, preventing complete ambiguity.
All tool names follow a consistent verb_noun pattern with snake_case, using 'get' or 'search' as verbs and clearly specifying the target (e.g., contact, tracking_logs). This predictability makes it easy for agents to understand and use the toolset without confusion.
With 5 tools, the count is reasonable for a contact management server, but it feels slightly thin as it only covers read operations (get and search) without create, update, or delete functions. This limits the scope but is still within an acceptable range for a focused purpose.
The toolset is severely incomplete for a CRM domain like ActiveCampaign, as it only includes retrieval and search functions for contacts and tracking logs. There are significant gaps in CRUD operations—no create, update, or delete tools—which will likely cause agent failures when trying to perform full contact lifecycle management.
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
API-first CRM for LLMs - contacts, companies, deals and activities over a native MCP server.
Let AI agents query data and act across all your business apps via MCP.
