Provides read-only access to Cisco Firepower Management Center (FMC), allowing users to query firewall configurations, search for network objects by IP, and monitor device deployment status.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Cisco FMC MCP Server Find the network object associated with IP 10.1.10.50"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A read-only Model Context Protocol (MCP) server for Cisco Firepower Management Center (FMC) 7.4.x.
This server allows LLMs like Claude to query your firewall configuration, search for network objects, and check deployment status—all through natural language.
Read-Only Access: Safe exploration of FMC configuration without modification risk
Rate Limiting: Built-in token bucket rate limiter (120 req/min, 10 concurrent connections)
Automatic Token Refresh: Handles FMC's 30-minute token expiration and 3-refresh limit
Transparent Pagination: Automatically fetches all pages from large datasets
Resource | Description |
| FMC server version and system information |
| List of all managed firewall devices |
| All network objects (IPs, subnets) |
| Devices with pending changes |
Tool | Description |
| Find network objects containing a specific IP |
| Check if devices are in sync |
Related MCP server: scm-mcp
Python 3.10+
uv (recommended) or pip
Access to a Cisco FMC 7.4.x instance
# Clone the repository
git clone https://github.com/your-org/fmc-mcp.git
cd fmc-mcp
# Install dependencies
uv syncpip install -e .Copy the example configuration:
cp .env.example .envEdit .env with your FMC credentials:
FMC_HOST=fmc.example.com
FMC_USERNAME=api_user
FMC_PASSWORD=your_password_hereVariable | Required | Default | Description |
| Yes | - | FMC hostname or IP |
| Yes | - | API username |
| Yes | - | API password |
| No |
| SSL certificate verification |
| No | auto | Domain UUID (auto-discovered) |
| No |
| Request timeout in seconds |
# Using uv
uv run python -m fmc_mcp
# Or using the CLI entry point
uv run mcp-server-fmcuv run python -c "from fmc_mcp.client import FMCClient; import asyncio; asyncio.run(FMCClient().test_connection())"Add to your Claude Desktop configuration (claude_desktop_config.json):
{
"mcpServers": {
"fmc": {
"command": "uv",
"args": ["run", "--directory", "/path/to/fmc-mcp", "python", "-m", "fmc_mcp"]
}
}
}Then restart Claude Desktop and try:
"What version is my FMC running?"
"List all firewall devices"
"Find the network object for IP 10.10.10.5"
"Are there any pending deployments?"
# Install MCP Inspector
npx @anthropic/mcp-inspector
# Run the server
uv run python -m fmc_mcp# Run all tests
uv run pytest -v
# Run with coverage
uv run pytest --cov=src/fmc_mcp --cov-report=term-missing# Linting
uv run ruff check src/ tests/
# Type checking
uv run mypy src/The FMC API has strict rate limits that this server respects:
Limit | Value | How We Handle It |
Requests per minute | 120 | Token bucket rate limiter |
Concurrent connections | 10 | Connection semaphore |
Token lifetime | 30 min | Auto-refresh on 401 |
Max token refreshes | 3 | Full re-authentication after 3 |
The server logs warnings when approaching rate limits:
WARNING when token bucket drops below 20%
ERROR on 429 (rate limited) responses
Read-Only: This server only performs GET requests
SSL: Disabled by default for lab environments; enable in production
Credentials: Store in .env, never commit to version control
API User: Create a dedicated read-only API user in FMC
Apache 2.0
This server cannot be deployed
The HubSpot MCP Server acts as a bridge that enables AI assistants and Large Language Models to securely interact with HubSpot CRM data through natural conversation, without requiring users to understand complex API structures. It provides read-only access to standard CRM objects (contacts, companies, deals, tickets, products, invoices, and more) and their associations, secured via OAuth 2.0, allowing AI agents to perform tasks like summarizing deals, fetching company updates, and looking up record changes.
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
Query your org's data in natural language — read-only MCP access to SQL, NoSQL, files & warehouses.
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
