Ansible AWX MCP Server — 51 AI Tools

Ansible AWX MCP ServerAnsible AWX MCP server with 51 ready-to-use AI tools. Connect Ansible AWX to Claude, ChatGPT, Gemini, or any MCP-compatible AI assistant. Cloud MCP connector — no install, no Docker, works from any browser.Category: Developer Tools. 51 tools available. Authentication: API Key.Full Ansible AWX automation — launch jobs, manage hosts, and audit changes from your AI chatWhy Ansible AWX + AI?AWX gives you powerful automation, but managing inventories, creating hosts, launching jobs, and auditing changes requires navigating dozens of UI pages. Tell your AI what to do and it handles everything — from creating hosts and groups to launching playbooks and investigating failures.Example prompts you can send your AI about Ansible AWX

Ask: "Launch the "Deploy to Staging" job template with extra vars for version 2.5"
AI does: AI finds the template, checks the survey spec for required inputs, passes the extra variables, launches the job, and reports back when it completes with the output.

Ask: "What jobs failed in the last 24 hours and why?"
AI does: AI fetches recent failed jobs, retrieves their output logs, and summarizes the failure reasons with the PLAY RECAP.

Ask: "Create a new host "web-03" in the Production inventory and add it to the webservers group"
AI does: AI creates the host with connection variables, then associates it with the webservers group — ready for the next playbook run.

Ask: "Who made changes in AWX this week? Show the audit log."
AI does: AI queries the activity stream filtered by date range and presents a chronological list of who created, updated, or deleted resources.

Ask: "Show me cluster health and job success trends for the last week"
AI does: AI checks cluster node capacity, displays health metrics, and shows the job success/failure time-series graph.

Featured Ansible AWX Tools

awx_launch_job: Launch (execute) a job template — this starts an Ansible playbook run on the configured inventory. Returns the launched job ID and status. After launching, use awx_get_job to monitor progress and awx_get_job_output to see the playbook output when complete. PARAMETER RULES: • extra_vars: JSON or YAML string of variables passed to the playbook. ONLY works if the template has ask_variables_on_launch=true. Format: '{"env": "staging", "version": "2.1.0"}' or YAML: 'env: staging\nversion: 2.1.0' • limit: Ansible host pattern to restrict which hosts the playbook runs on. Examples: "webservers", "host1,host2", "*.prod.example.com" • inventory: Numeric ID of an alternative inventory. ONLY works if ask_inventory_on_launch=true. • job_tags: Run ONLY tasks tagged with these tags. Comma-separated. Example: "deploy,config" • skip_tags: SKIP tasks tagged with these tags. Comma-separated. Example: "slow_tasks,backups" IMPORTANT: Each override parameter ONLY works if the template has the corresponding "ask_*_on_launch" flag enabled. If you pass extra_vars but ask_variables_on_launch=false, they are silently IGNORED. Use awx_get_job_template first to check which overrides are allowed. SUPPORTED OVERRIDES: extra_vars, limit, inventory, job_tags, skip_tags. Other ask_* flags (verbosity, credentials, diff_mode, execution_environment) may appear on templates but cannot be overridden through this tool. COMPLETE EXAMPLES: • Simple launch (no overrides): {"template_id": 15} • Launch with variables: {"template_id": 15, "extra_vars": "{\"env\": \"staging\", \"version\": \"2.1.0\"}"} • Launch on specific hosts: {"template_id": 15, "limit": "webservers"} • Launch with tags: {"template_id": 15, "job_tags": "deploy", "skip_tags": "tests"} WHEN TO USE: "Run the deploy playbook", "Launch template 15", "Execute the backup job", "Run playbook on staging hosts", "Deploy version 2.1.0".

awx_create_host: Create a new host in an AWX inventory. The host will be available for Ansible playbook runs targeting that inventory. REQUIRED: inventory_id (which inventory to add the host to) and name (hostname or IP). OPTIONAL: description, enabled (default true), variables (YAML or JSON string with connection params). COMMON VARIABLES (pass as YAML or JSON string): • ansible_host: IP address or FQDN to connect to (if different from name) • ansible_user: SSH user • ansible_port: SSH port (default 22) • ansible_connection: Connection type (ssh, local, winrm) • ansible_ssh_private_key_file: Path to SSH key EXAMPLES: • Simple host: {"inventory_id": 5, "name": "web-server-01"} • Host with variables: {"inventory_id": 5, "name": "web-server-01", "variables": "ansible_host: 192.168.1.10\nansible_user: deploy"} • Disabled host: {"inventory_id": 5, "name": "web-server-01", "enabled": false} AFTER CREATING: Use awx_add_host_to_group to assign the host to a group. WHEN TO USE: "Add a host to inventory", "Create host web-server-01", "Register a new managed host".

awx_list_activity_stream: View the AWX activity stream (audit log). Shows a chronological record of every create, update, delete, associate, and disassociate operation in AWX — who did what, when, and what changed. Returns: id, timestamp, operation (create/update/delete/associate/disassociate), changes (JSON diff of what changed), object1 and object2 (resource types involved), action_node (cluster node), and summary_fields with the user who performed the action. FILTERING: • By operation type: {"operation": "delete"} — only show deletions • By resource type: {"object_type": "job"} — only job-related events • Combined: {"operation": "create", "object_type": "host"} — only host creation events EXAMPLES: • Recent activity: {} (defaults to most recent first) • Only deletions: {"operation": "delete"} • Only job-related: {"object_type": "job"} • Last 50 events: {"page_size": 50} WHEN TO USE: "Show me the audit log", "What changed recently in AWX?", "Who deleted that inventory?", "Show recent activity", "Audit trail for the last hour".

awx_get_survey_spec: Get the survey form definition for a job template. Surveys define extra input fields that users must fill in before launching a job — like environment name, version number, or deploy target. Returns: name, description, and spec[] array where each item has: question_name, question_description, required flag, type (text/textarea/password/integer/float/multiplechoice/multiselect), variable (the Ansible variable name this answer maps to), min/max (for numeric types), default value, and choices (newline-separated list for choice types). IMPORTANT: Check template.survey_enabled=true before calling this — if surveys are disabled, the spec may be empty. Use awx_get_job_template first. WHEN LAUNCHING WITH SURVEYS: Pass survey answers as extra_vars in awx_launch_job. Each survey question maps to a variable name — use that as the key. Example: survey has variable "target_env" → launch with extra_vars: '{"target_env": "staging"}' EXAMPLES: • Get survey: {"template_id": 15} WHEN TO USE: "What inputs does template 15 need?", "Show me the survey for the deploy template", "What variables do I need to pass to launch this job?", "Does this template have a survey?".

awx_list_hosts: List ALL hosts across ALL inventories in AWX. Unlike awx_get_inventory_hosts which shows hosts in a single inventory, this tool gives a global view of every managed host. Returns: id, name, description, inventory ID, enabled flag, has_active_failures flag, variables (YAML string with ansible_host, ansible_user, etc.), last_job ID, and summary_fields with group memberships. FILTERING: • By name: {"search": "web"} — finds all hosts with "web" in the name • By enabled status: {"enabled": true} — only enabled hosts (or false for disabled) • By inventory: {"inventory": 5} — hosts in a specific inventory EXAMPLES: • All hosts: {} • Disabled hosts: {"enabled": false} • Hosts in inventory 5: {"inventory": 5} • Search for a host: {"search": "db-server"} WHEN TO USE: "Show me all hosts", "List disabled hosts", "Find host db-server", "How many hosts do we manage?", "Which hosts have failures?".

awx_list_instances: List AWX cluster nodes with health and capacity information. Each instance is a server in the AWX cluster that can run jobs. Returns: id, hostname, uuid, node_type (control/execution/hop/hybrid), node_state (ready/unavailable), enabled, capacity, consumed_capacity, percent_capacity_remaining, jobs_running, jobs_total, cpu (core count), memory (bytes), cpu_capacity, mem_capacity, last_seen, last_health_check, errors, ip_address. EXAMPLES: • List all nodes: {} WHEN TO USE: "Show me AWX cluster nodes", "What is the cluster capacity?", "Are all AWX nodes healthy?", "How many jobs are running on each node?", "Cluster health check".

Frequently Asked Questions about Ansible AWXHow do I connect Ansible AWX to Claude or ChatGPT?Create a free LearnToSpeak.ai account, add your Ansible AWX credentials in the dashboard, and paste the generated OAuth URL into Claude.ai's custom connectors or ChatGPT's developer apps. The integration runs fully in the cloud — no desktop app, no CLI, no local install.Does it cost anything to connect Ansible AWX?The Ansible AWX integration is free during the LearnToSpeak.ai public beta. You only need a paid plan from Anthropic or OpenAI (Claude Pro/Max/Team or ChatGPT Plus/Pro/Team) since custom connectors require it on the AI provider side.Which AI assistants support the Ansible AWX connector?Claude.ai (Pro, Max, Team, Enterprise) and ChatGPT (Plus, Pro, Team) both support the Ansible AWX integration via the MCP (Model Context Protocol) standard. The same credentials work across both platforms — add the connector once, use it everywhere.How many Ansible AWX tools does my AI get access to?Your AI gets 51 ready-to-use tools for Ansible AWX, covering the most common read and write operations. Each tool is a discrete action the AI can call on demand — no multi-step prompting, no screen scraping, no workarounds.Is it safe to give an AI access to my Ansible AWX account?Yes. Your Ansible AWX credentials are encrypted at rest with AES-256-GCM and only decrypted in memory when the AI makes a request. LearnToSpeak.ai uses OAuth 2.1 with mandatory PKCE for the AI-to-platform connection, and you can revoke access instantly from the dashboard. We never store or log the actual tool responses returned to the AI.Why use LearnToSpeak.ai instead of running an MCP server locally?Cloud MCP servers work from any browser on any device — no Node.js install, no Docker, no local ports, no maintenance. Configure Ansible AWX once in the dashboard and your AI connects from claude.ai or chat.openai.com directly. That's the entire value proposition: web AI assistants don't read your filesystem, they read our servers.What is the Ansible AWX MCP server?The Ansible AWX MCP server is a cloud-hosted integration that gives AI assistants direct access to Ansible AWX through 51 tools via the Model Context Protocol (MCP) standard. It works with Claude, ChatGPT, Gemini, and any MCP-compatible AI — no local installation or Docker required.How do I connect Ansible AWX to Claude via MCP?Sign up at LearnToSpeak.ai, add your Ansible AWX credentials, and copy the generated MCP URL into Claude.ai's custom connectors (Settings → Developer → Custom Connectors). The cloud MCP server handles the connection — no CLI, no local server, no Docker.How do I connect Ansible AWX to ChatGPT via MCP?Sign up at LearnToSpeak.ai, add your Ansible AWX credentials, and copy the generated MCP URL into ChatGPT's developer apps (Settings → Apps → Advanced → Developer mode). Works with any ChatGPT Plus, Pro, or Team account.What can AI do with Ansible AWX through MCP?Ansible AWX offers 51 MCP tools covering Full Ansible AWX automation: launch jobs, manage inventories/hosts/groups, audit changes, and monitor cluster health. Ask your AI to perform any of these actions in natural language — it calls the right tool automatically.What is MCP (Model Context Protocol)?MCP is an open standard that lets AI assistants like Claude, ChatGPT, and Gemini connect directly to external apps and services. LearnToSpeak.ai hosts cloud MCP servers so you don't need to install anything locally — your AI connects from any browser.Related MCP Servers

GitHub MCP Server — 44 tools

GitLab MCP Server — 90 tools

NetBox MCP Server — 179 tools

Cisco CPNR MCP Server — 36 tools

Grafana MCP Server — 50 tools

Browse all 34 MCP servers