ansible-know-mcp
Module discovery, documentation search, and skill generation for AI agents via the Model Context Protocol.
README
Ansible Know MCP Server
Module discovery, documentation search, and skill generation for AI agents via the Model Context Protocol.
What It Does
Ansible Know is the foundational "learn" layer for AI agents working with Ansible. It provides:
- Module discovery — search and explore Ansible modules across all installed collections
- Module documentation — get structured parameter specs, examples, and metadata
- Documentation search — find conceptual guides from Ansible's AI-friendly docs
- Skill generation — create ready-to-use skill packages that teach agents how to use specific modules
- Collection manifests — get collection-level overviews with per-module summaries
- Resources — browse skills and doc sources as MCP resources
- Prompts — pre-built templates for playbook review, module explanation, and role generation
Together with Ansible Devtools MCP (build) and AAP MCP (deploy), this enables the full autonomous cycle: learn -> build -> deploy.
Agent's MCP servers:
+-----------------------+ +-------------------+ +---------------+
| Ansible Know | | Ansible Devtools | | AAP MCP |
| (this project) | | | | |
| | | | | |
| search_modules | | ansible_lint | | controller.* |
| get_module_doc | | ansible_navigator | | eda.* |
| get_collection_ | | ansible_create_* | | gateway.* |
| manifest | | build_ee | | galaxy.* |
| search_docs | | zen_of_ansible | | |
| generate_skill | | setup_environment | | |
| generate_collection | | environment_info | | |
| list_skills | | | | |
| get_skill | | | | |
| | | | | |
| LEARN | | BUILD | | DEPLOY |
+-----------------------+ +-------------------+ +---------------+
Installation
Using uvx (recommended):
uvx ansible-know-mcp
Using pip:
pip install ansible-know-mcp
Runtime requirement: ansible-core must be installed in the same environment (for ansible-doc).
Usage
With Claude Code
claude mcp add ansible-know -- uvx ansible-know-mcp
To make it available in all projects:
claude mcp add --scope user ansible-know -- uvx ansible-know-mcp
With VS Code / Cursor
Add to .vscode/mcp.json in your workspace:
{
"servers": {
"ansible-know": {
"command": "uvx",
"args": ["ansible-know-mcp"],
"type": "stdio"
}
}
}
With any MCP client
The server runs over stdio by default:
uvx ansible-know-mcp
Full stack configuration
{
"mcpServers": {
"ansible-know": { "command": "uvx", "args": ["ansible-know-mcp"] },
"ansible-devtools": { "command": "ade", "args": ["mcp"] },
"aap": { "command": "aap-mcp-server" }
}
}
Tools
Discovery (read-only)
| Tool | Description |
|---|---|
search_modules(keyword, namespace?) |
Find modules by keyword in name or description. Returns up to 50 matches. |
get_module_doc(module_name) |
Get full structured docs: params, examples, API detection. |
search_docs(query, source?, topic?, audience?, core_only?) |
Search documentation manifests for conceptual guides. Returns up to 20 matches. |
get_collection_manifest(collection_namespace) |
Get collection-level manifest with per-module summaries. |
Skill management
| Tool | Description |
|---|---|
list_skills() |
List all generated skills (read-only). |
get_skill(skill_name) |
Read a skill's SKILL.md content (read-only). |
generate_skill(module_name, install_to?) |
Generate a skill package for one module. Returns SKILL.md inline. |
generate_collection_skills(collection_namespace, install_to?) |
Batch generate skills for an entire collection. |
Resources
| URI | Description |
|---|---|
skills://list |
List all generated skill packages |
skills://{skill_name} |
Read a skill's SKILL.md content by FQCN |
docs://sources |
List configured documentation manifest sources |
Prompts
| Prompt | Description |
|---|---|
review_playbook(playbook_yaml) |
Review a playbook against module docs and best practices |
explain_module(module_name) |
Get a detailed module explanation with usage examples |
generate_role(role_purpose, modules) |
Generate a role skeleton using specified modules |
Development
git clone https://github.com/leogallego/ansible-know-mcp.git
cd ansible-know-mcp
uv venv && source .venv/bin/activate
uv pip install -e ".[dev]"
pytest
Configuration
| Environment Variable | Description | Default |
|---|---|---|
ANSIBLE_KNOWLEDGE_SKILLS_DIR |
Where to write generated skills | ./skills/ |
ANSIBLE_KNOWLEDGE_DOC_SOURCES |
JSON dict of doc manifest sources | Built-in ansible-core source |
License
GPL-3.0-or-later
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
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
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.