Fmc Firewall Ops logo

Fmc Firewall Ops

Community
automateyournetwork
fmc-firewall-ops

Cisco Secure Firewall FMC — access policy search, rule inspection, FTD device targeting, multi-FMC profile management. Use when searching firewall rules by IP or FQDN, checking if host A can reach host B through the firewall, auditing FMC access policies, or reviewing SGT-based segmentation rules.

Overview

Publisherautomateyournetwork
Repositorynetclaw
Skill namefmc-firewall-ops
Stars
680
Forks
189
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by automateyournetwork on GitHub. Read the source before you install it.

Installation

Install the Fmc Firewall Ops AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/fmc-firewall-ops
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/automateyournetwork/netclaw.git /tmp/netclaw
mkdir -p .claude/skills
cp -r /tmp/netclaw/workspace/skills/fmc-firewall-ops .claude/skills/fmc-firewall-ops
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fmc Firewall Ops in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Fmc Firewall Ops on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Fmc Firewall Ops is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Cisco FMC Firewall Operations

MCP Server

  • Repository: CiscoDevNet/CiscoFMC-MCP-server-community
  • Transport: HTTP (http://<host>:8000/mcp) — requires HTTPS reverse proxy for production
  • Install: git clone + pip install -r requirements.txt + python -m sfw_mcp_fmc.server (or Docker)
  • Requires: FMC_BASE_URL, FMC_USERNAME, FMC_PASSWORD

Available Tools (4)

ToolWhat It Does
list_fmc_profilesDiscover all configured FMC instances (single or multi-FMC mode). Returns profile IDs, display names, and aliases. Use this first to select which FMC to query.
find_rules_by_ip_or_fqdnSearch rules within a specific access policy by IP address or FQDN. Matches source/destination network objects against the given indicator.
find_rules_for_targetResolve FTD devices or HA clusters to their assigned access policies, then search those policies. Use when you know the firewall device name but not the policy name.
search_access_rulesFMC-wide rule search with multiple filter types: network indicators (IP, FQDN), identity indicators (SGT tags, realm users/groups), and policy name filters. The most powerful search tool.

Key Concepts

ConceptWhat It Means
FMCFirepower Management Center — centralized management for Cisco Secure Firewalls (FTD)
FTDFirepower Threat Defense — the firewall appliance/virtual managed by FMC
Access PolicyCollection of access rules (ACLs) applied to FTD devices — permit/deny by source/dest/port/app
Access RuleIndividual rule within a policy — source zones, dest zones, source/dest networks, ports, action (allow/block/monitor)
SGTSecurity Group Tag — TrustSec identity-based tag for micro-segmentation
HA ClusterHigh Availability pair of FTD devices sharing the same policy
ProfileFMC connection configuration (URL, credentials) — supports multi-FMC environments

Workflow: Firewall Rule Audit

When a user asks "what firewall rules exist for 10.1.1.0/24?":

  1. Discover FMCs: list_fmc_profiles — identify which FMCs manage this network
  2. Search rules: search_access_rules with network indicator 10.1.1.0/24
  3. For each match: Extract rule name, action (allow/block), source/dest zones, source/dest networks, ports, logging settings
  4. Cross-reference: Check if rules are overly permissive (any/any), redundant, or shadowed
  5. Report: Formatted rule table with security assessment

Workflow: "Can Host A Reach Host B?"

When investigating connectivity through the firewall:

  1. Identify FTD: Which firewall sits between source and destination?
  2. Resolve policy: find_rules_for_target with the FTD device name
  3. Search source IP: find_rules_by_ip_or_fqdn for the source IP in the resolved policy
  4. Search dest IP: Same for destination IP
  5. Analyze: Do the matching rules permit the required port/protocol?
  6. Report: "Traffic from 10.1.1.50 to 10.2.1.100:443 is ALLOWED by rule 'Web-Servers-Inbound' (line 47)" or "BLOCKED by implicit deny"

Workflow: Security Group Tag (SGT) Policy Review

When auditing TrustSec/SGT-based policies:

  1. Search by SGT: search_access_rules with identity indicator for a specific SGT value
  2. List matching rules: Which rules reference this SGT in source or destination?
  3. Check actions: Are SGT-based rules enforcing proper segmentation?
  4. Cross-reference: Use ise-posture-audit to verify SGT assignment policies in ISE
  5. Report: SGT policy coverage analysis

Workflow: Multi-FMC Environment Audit

When managing multiple FMC instances:

  1. List all FMCs: list_fmc_profiles — see all managed FMC instances
  2. For each FMC: search_access_rules with common indicators
  3. Compare policies: Are policies consistent across FMCs?
  4. Identify drift: Rules present in one FMC but not another
  5. Report: Cross-FMC policy consistency analysis

Integration with Other Skills

SkillHow They Work Together
pyats-securityFMC rule audit + device-level ACL verification via pyATS
ise-posture-auditFMC SGT rules + ISE SGT assignment and TrustSec matrix
ise-incident-responseFMC rules for quarantine verification + ISE endpoint investigation
aws-security-auditCross-platform security: FMC on-prem + AWS cloud security posture
gcp-cloud-loggingFMC firewall logs vs GCP firewall logs for hybrid environments
nso-device-opsFMC policies + NSO device config for end-to-end policy view
servicenow-change-workflowServiceNow CR gating before any FMC policy modifications
github-opsCommit FMC rule snapshots to Git for config-as-code tracking

Multi-FMC Configuration

Single FMC mode (set in .env):

FMC_BASE_URL=https://fmc.example.com
FMC_USERNAME=api-user
FMC_PASSWORD=changeme
FMC_VERIFY_SSL=false

Multi-FMC mode (profile directory):

profiles/
  dc-east.env    # FMC for DC East
  dc-west.env    # FMC for DC West
  dmz.env        # FMC for DMZ firewalls

Each profile .env contains:

FMC_PROFILE_ID=dc-east
FMC_PROFILE_DISPLAY_NAME=DC East FMC
FMC_PROFILE_ALIASES=10.1.1.10,fmc-east
FMC_BASE_URL=https://fmc-east.example.com
FMC_USERNAME=api-user
FMC_PASSWORD=changeme
FMC_VERIFY_SSL=false

Important Rules

  • Read-only — all 4 tools are search/query operations; no rule modifications
  • HTTP transport — server runs on port 8000, front with HTTPS proxy for production
  • Multi-FMC — always call list_fmc_profiles first to select the right FMC instance
  • FMC API rate limits — FMC REST API has per-user rate limits; avoid rapid-fire queries
  • Record in GAIT — log all firewall policy investigations for audit trail

Environment Variables

  • FMC_BASE_URL — FMC URL (e.g., https://fmc.example.com)
  • FMC_USERNAME — FMC API username
  • FMC_PASSWORD — FMC API password
  • FMC_VERIFY_SSL — SSL verification (true/false)
  • FMC_PROFILES_DIR — path to multi-FMC profiles directory (optional)
  • FMC_PROFILE_DEFAULT — default profile name (optional)

Failure Behavior

  • On a tool error (timeout, unreachable host, malformed response), report the failure and its error message directly to the user rather than fabricating or guessing at results.
  • For a confirmed read-only call, check connectivity and retry once if appropriate. For any call that changes state or sends a message, a timeout does not prove the action failed: inspect current state or delivery status before retrying, preserve the required approval/change gates, and do not repeat an action whose outcome is unknown.

Frequently asked questions

What does the Fmc Firewall Ops AI skill do?

Cisco Secure Firewall FMC — access policy search, rule inspection, FTD device targeting, multi-FMC profile management. Use when searching firewall rules by IP or FQDN, checking if host A can reach host B through the firewall, auditing FMC access policies, or reviewing SGT-based segmentation rules.

Why use Fmc Firewall Ops on TypingMind?

Because you install it once and use it with any model. Fmc Firewall Ops is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Fmc Firewall Ops in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/automateyournetwork/netclaw/tree/main/workspace/skills/fmc-firewall-ops. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Fmc Firewall Ops?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Fmc Firewall Ops?

As many as you like. As long as a model supports skills, you can use Fmc Firewall Ops with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Fmc Firewall Ops AI skill free?

Yes. It is published on GitHub by automateyournetwork under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇