// SCAN REPORT

Ansible Know

18 tools. 5 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 3 Jul 2026

5 can modify or destroy data

13 read-only

18 tools total

Community server · catalogue entry verified 03/07/2026

How to control Ansible Know ↓

TOOL MAP

What Ansible Know exposes to your agents

Read (13) Write / Execute (4) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Ansible Know tools

Destructive · Medium clear_cache Clearing caches permanently removes stored data (cached documentation, module info, etc.) that cannot be recovered without re-fetching. Write · Medium generate_collection_skills Based on sibling tools (generate_skill, generate_plugin_skill, generate_role_skill), this tool likely generates/creates skill files or artifacts for an Ansible collection. Write · Medium generate_plugin_skill Based on the naming convention of sibling tools (generate_skill, generate_role_skill, generate_collection_skills), 'generate_plugin_skill' likely creates/generates skill artifacts from plugin documentation, which is a Wr Write · Medium generate_role_skill Based on the naming pattern of sibling tools (generate_skill, generate_plugin_skill, generate_collection_skills), this tool likely generates/creates skill artifacts for Ansible roles.

5 of Ansible Know's 18 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Ansible Know

PolicyLayer is an MCP gateway — it sits between your AI agents and Ansible Know, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "clear_cache": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "generate_collection_skills": {
    "limits": [
      {
        "counter": "generate_collection_skills_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "ensure_collection": {
    "limits": [
      {
        "counter": "ensure_collection_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Ansible Know — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ANSIBLE KNOW →

Instant setup, no code required.

FULL CATALOGUE

All 18 Ansible Know tools

DESTRUCTIVE 1 tools

Destructive clear_cache Clear server caches.

WRITE 4 tools

Write generate_collection_skills generate_collection_skills Write generate_plugin_skill generate_plugin_skill Write generate_role_skill generate_role_skill Write generate_skill generate_skill

READ 13 tools

Read ensure_collection ensure_collection Read fetch_doc Fetch a page from docs.ansible.com as clean Markdown. Read get_collection_docs get_collection_docs Read get_collection_manifest get_collection_manifest Read get_module_doc get_module_doc Read get_plugin_doc get_plugin_doc Read get_role_doc get_role_doc Read get_skill Read a specific skill's SKILL.md content by name. Read list_skills List all available generated skills. Returns name, description, path for each. Read search_collections search_collections Read search_docs search_docs Read search_modules search_modules Read search_plugins search_plugins

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Ansible Know

Can an AI agent delete data through the Ansible Know MCP server? +

Yes. The Ansible Know server exposes 1 destructive tools including clear_cache. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Ansible Know? +

The Ansible Know server has 4 write tools including generate_collection_skills, generate_plugin_skill, generate_role_skill. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Ansible Know.

How many tools does the Ansible Know MCP server expose? +

18 tools across 3 categories: Destructive, Read, Write. 13 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Ansible Know? +

Register the Ansible Know MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Ansible Know tool call.

Deterministic rules across all 18 Ansible Know tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ANSIBLE KNOW →

Instant setup, no code required.

18 Ansible Know tools catalogued and risk-classified — across an index of 43,000+ MCP servers.