ansible-mcp-server
MCP server that enables natural language interaction with an Ansible repository, providing tools for inventory inspection, syntax checking, and playbook execution with configurable safety controls.
README
Ansible NLP MCP
Servidor MCP local para permitir que o Codex interaja com este repositório Ansible por linguagem natural, usando ferramentas seguras em vez de expor um shell genérico.
Ferramentas
health: mostra raiz, timeout e se execução mutável está habilitada.list_playbooks: lista playbooks e workflows executáveis.inspect_playbook: resume plays, hosts,vars_files, tasks iniciais e variáveis obrigatórias comuns.suggest_playbooks: ranqueia playbooks a partir de um pedido em linguagem natural.inventory_graph: executaansible-inventory --graph.inventory_summary: resume grupos e hosts do inventário.syntax_check: executaansible-playbook --syntax-check.check_playbook: executaansible-playbook --check.run_playbook: executa playbook real, bloqueado por padrão.ping_hosts: executaansible -m pingouansible.windows.win_ping.list_logsetail_log: consulta logs dentro delogs/.
Instalação
cd /root/ansible
python3 -m venv .venv-mcp
. .venv-mcp/bin/activate
pip install -r ansible_mcp/requirements.txt
Teste local
cd /root/ansible
. .venv-mcp/bin/activate
python -m ansible_mcp.server
Esse comando inicia um servidor MCP por stdio e fica aguardando um cliente MCP.
Configuração no Codex
Exemplo para .codex/config.toml no projeto, ou para ~/.codex/config.toml se quiser habilitar globalmente:
[mcp_servers.ansible]
command = "/root/ansible/.venv-mcp/bin/python"
args = ["/root/ansible/ansible_mcp/server.py"]
cwd = "/root/ansible"
enabled = true
startup_timeout_sec = 10
tool_timeout_sec = 900
env = { ANSIBLE_MCP_ROOT = "/root/ansible", ANSIBLE_MCP_ALLOW_RUN = "0" }
Com ANSIBLE_MCP_ALLOW_RUN = "0", o MCP permite inspeção, inventário, ping, syntax-check e check-mode, mas bloqueia execução real de playbooks.
Para permitir execução mutável:
[mcp_servers.ansible]
command = "/root/ansible/.venv-mcp/bin/python"
args = ["/root/ansible/ansible_mcp/server.py"]
cwd = "/root/ansible"
enabled = true
startup_timeout_sec = 10
tool_timeout_sec = 900
env = { ANSIBLE_MCP_ROOT = "/root/ansible", ANSIBLE_MCP_ALLOW_RUN = "1" }
Mesmo habilitado, run_playbook ainda exige confirm = "RUN" na chamada da ferramenta.
Exemplos de intenção NLP
- "Qual playbook eu uso para atualizar Windows do wuday1?"
- "Faça syntax-check do playbook de Windows Update com
day=wuday1." - "Rode em check mode a atualização Linux só no grupo rocky."
- "Mostre os últimos logs do Citrix Day."
- "Liste os grupos de inventário e quantos hosts existem em cada um."
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.