librenms-mcp
The LibreNMS MCP Server provides comprehensive, programmable access to LibreNMS for querying and managing network monitoring data and resources.
Device & Inventory Management: List, add, update, delete, and rename devices; trigger rediscovery; check availability and outages; set maintenance mode; get device VLANs, links, ports, and inventory.
Port & Port Group Operations: List, search, and get port details (by ID, MAC, or field); update port descriptions; create and manage port groups; assign or remove ports.
Alerting & Logging: List, acknowledge, and unmute alerts; manage alert rules and templates; retrieve event logs, syslogs, alert logs, and auth logs; add custom event/syslog entries.
Device Groups & Locations: Create, update, and delete device groups and locations; add/remove devices from groups; set maintenance mode for groups or all devices at a location.
Networking & Routing: Search ARP/FDB entries; manage BGP sessions; list OSPF instances and ports; list VLANs, links, VRFs, and IP addresses.
Billing: List, create/update, and delete bills; retrieve bill graphs, history, and graph data.
Services: List, add, edit, and delete monitored services per device.
Oxidized (Config Backup): List Oxidized-tracked devices; retrieve and search stored device configurations.
Health & Sensors: List health graphs and sensors; get sensor data by type or ID across all devices.
System: Get LibreNMS system info, ping/health-check the API, and retrieve poller group details.
Search: Search devices by hostname, OS, location, status, or MAC/IP; search ports by alias, description, name, type, or MAC.
Security & Configuration: Supports STDIO, HTTP SSE, and HTTP Streamable transports; optional bearer token auth; read-only mode to disable writes; tag-based tool filtering; rate limiting; SSL/TLS support; optional Sentry integration; pagination for large datasets.
Allows error tracking and performance monitoring via Sentry, with configurable DSN and options.
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., "@librenms-mcp list all devices with status 'down'"
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.
LibreNMS MCP Server
Let AI agents query and manage LibreNMS network monitoring through the Model Context Protocol
Installation · Tools · Configuration · Security
LibreNMS MCP Server is a Python-based Model Context Protocol (MCP) server designed to provide advanced, programmable access to LibreNMS network monitoring data and management features. It exposes a modern API for querying, automating, and integrating LibreNMS resources such as devices, ports, alerts, inventory, locations, logs, and more. The server supports both read and write operations, robust security features, and is suitable for integration with automation tools, dashboards, and custom network management workflows.
✨ Features
Core Features
Query LibreNMS devices, ports, inventory, locations, logs, and alerts with flexible filtering
Retrieve network topology, device status, and performance metrics
Access and analyze alert history, event logs, and system health
Monitor interface statistics, port status, and traffic data
Track endpoints and connected devices by MAC or IP address
Retrieve and manage device groups, port groups, and poller groups
Get detailed information about network services and routing
Management Operations
Create, update, and delete devices, ports, and groups (if enabled)
Manage alert rules, notifications, and device metadata
Configure read-only mode to restrict all write operations for safe monitoring
Support for bulk operations on devices and ports
Advanced Capabilities
Rate limiting and API security features
Real-time network monitoring and health tracking
Comprehensive logging and audit trails
SSL/TLS support and configurable timeouts
Optional tool-search transform for large tool catalogs
Extensible with custom middlewares and utilities
Related MCP server: Unofficial FortiMonitor MCP Server
🚀 Installation
Prerequisites
Python 3.11 to 3.15
Access to a LibreNMS
Valid LibreNMS token with appropriate permissions
Quick Install from PyPI
The easiest way to get started is to install from PyPI:
# Using UV (recommended)
uvx librenms-mcp
# Or using pip
pip install librenms-mcpRemember to configure the environment variables for your LibreNMS instance before running the server:
# Create environment configuration
export LIBRENMS_URL=https://domain.tld:8443
export LIBRENMS_TOKEN=your-librenms-tokenFor more details, visit: https://pypi.org/project/librenms-mcp/
Install from Source
Clone the repository:
git clone https://github.com/mhajder/librenms-mcp.git
cd librenms-mcpInstall dependencies:
# Using UV (recommended)
uv sync
# Or using pip
pip install -e .Configure environment variables:
cp .env.example .env
# Edit .env with your LibreNMS url and tokenRun the server:
# Using UV (recommended)
uv run librenms-mcp
# Or using the installed command directly
librenms-mcpUsing Docker
A Docker image is available on GitHub Packages for easy deployment. It runs the
HTTP Streamable transport on port 8000 (/mcp).
docker pull ghcr.io/mhajder/librenms-mcp:latestOpen WebUI
Open WebUI 0.6.31 and later connect to the image directly; the separate MCPO
image (ghcr.io/mhajder/librenms-mcpo) is no longer published. In Open WebUI,
go to Admin Settings > Integrations > External Tool Servers, add a connection
of type MCP (Streamable HTTP) with the URL http://<host>:8000/mcp, and set
Bearer authentication to your MCP_HTTP_BEARER_TOKEN.
Development Setup
For development with additional tools:
# Clone and install with development dependencies
git clone https://github.com/mhajder/librenms-mcp.git
cd librenms-mcp
uv sync --group dev
# Run tests
uv run pytest
# Run with coverage
uv run pytest --cov=src/
# Run linting and formatting
uv run ruff check .
uv run ruff format .
# Run type checking
uv run ty check .
# Setup pre-commit hooks
uv run prek install🔧 Configuration
Environment Variables
Boolean settings accept true/false, 1/0, yes/no and on/off
(case-insensitive). Any other value stops the server at startup, so a typo
cannot silently turn read-only mode or TLS verification off. The exception is
SENTRY_SEND_DEFAULT_PII and SENTRY_ENABLE_LOGS: when SENTRY_DSN is set, an
invalid value there logs an error and leaves Sentry off, and the server keeps
running.
# LibreNMS Connection Details
LIBRENMS_URL=https://domain.tld:8443
LIBRENMS_TOKEN=your-librenms-token
# SSL Configuration
LIBRENMS_VERIFY_SSL=true
LIBRENMS_TIMEOUT=30
# Read-Only Mode
# Set READ_ONLY_MODE true to disable all write operations (put, post, delete)
READ_ONLY_MODE=false
# SNMP Credential Redaction
# Replaces SNMP community and SNMPv3 credentials in API responses with <redacted>;
# set REDACT_SNMP_CREDENTIALS false to return them as LibreNMS sends them
REDACT_SNMP_CREDENTIALS=true
# Disabled Tags
# Comma-separated list of tags to disable tools for (empty by default)
# Example: DISABLED_TAGS=alert,alert-rules,alert-templates,bills
DISABLED_TAGS=
# Logging Configuration
LOG_LEVEL=INFO
# Rate Limiting (requests per minute)
# Set RATE_LIMIT_ENABLED true to enable rate limiting
RATE_LIMIT_ENABLED=false
RATE_LIMIT_MAX_REQUESTS=100
RATE_LIMIT_WINDOW_MINUTES=1
# Tool Search Transform (Optional)
# Set TOOL_SEARCH_ENABLED true to replace full tool listings with search_tools + call_tool
TOOL_SEARCH_ENABLED=false
# Search strategy: bm25 (natural language) or regex (pattern match)
TOOL_SEARCH_STRATEGY=bm25
# Maximum number of tools returned by search_tools
TOOL_SEARCH_MAX_RESULTS=5
# Short Device Names (Optional)
# Set RESOLVE_SHORT_HOSTNAMES true to accept a device's short name ("rtr1") where
# a hostname is expected, resolving it to the one device whose hostname, up to the
# first dot, or whose sysName equals it (ignoring case)
RESOLVE_SHORT_HOSTNAMES=false
# Sentry Error Tracking (Optional)
# Set SENTRY_DSN to enable error tracking and performance monitoring
# SENTRY_DSN=https://your-key@o12345.ingest.us.sentry.io/6789
# Optional Sentry configuration
# SENTRY_TRACES_SAMPLE_RATE=1.0
# SENTRY_SEND_DEFAULT_PII=false
# SENTRY_ENVIRONMENT=production
# SENTRY_RELEASE=1.2.3
# SENTRY_PROFILE_SESSION_SAMPLE_RATE=1.0
# SENTRY_PROFILE_LIFECYCLE=trace
# SENTRY_ENABLE_LOGS=true
# MCP Transport Configuration
# Transport type: 'stdio' (default), 'sse' (Server-Sent Events), or 'http' (HTTP Streamable).
# 'streamable-http' is accepted as an alias for 'http'. Any other value stops the server at startup.
MCP_TRANSPORT=stdio
# HTTP Transport Settings (used when MCP_TRANSPORT=sse or MCP_TRANSPORT=http)
# Host to bind the HTTP server (default: 127.0.0.1)
# MCP_HTTP_HOST=127.0.0.1
# Port to bind the HTTP server (default: 8000)
# MCP_HTTP_PORT=8000
# Optional bearer token for authentication (leave empty for no auth)
# MCP_HTTP_BEARER_TOKEN=🧰 Available Tools
Device & Inventory Tools
devices_list: List all devices (with optional filters)device_get: Get details for a specific devicedevice_add: Add a new devicedevice_update: Update device metadatadevice_delete: Remove a devicedevice_ports: List all ports for a devicedevice_ports_get: Get details for a specific port on a devicedevice_fdb: List the forwarding database (learned MACs) for a devicedevice_nac: List network access control (802.1X / MAB) sessions on a devicedevice_availability: Get device availabilitydevice_outages: Get device outagesdevice_set_maintenance: Set device maintenance modedevice_discover: Discover or add a device using provided credentialsdevice_rename: Rename an existing devicedevice_maintenance_status: Get the maintenance status for a devicedevice_vlans: List VLANs for a devicedevice_links: List links for a devicedevice_wireless_sensors: List wireless sensors (frequency, clients, rssi, ...) with current valuesdevice_parents_set: Set the dependency parents of a device (replaces the current set)device_parents_clear: Remove dependency parents from a devicedevice_eventlog_add: Add an event log entry for a deviceinventory_device: Get inventory for a deviceinventory_device_flat: Get flat inventory for a devicedevicegroups_list: List device groupsdevicegroup_add: Add a device groupdevicegroup_update: Update a device groupdevicegroup_delete: Delete a device groupdevicegroup_devices: List devices in a device groupdevicegroup_set_maintenance: Set maintenance for a device groupdevicegroup_add_devices: Add devices to a device groupdevicegroup_remove_devices: Remove devices from a device grouplocations_list: List all locationslocation_add: Add a locationlocation_edit: Edit a locationlocation_delete: Delete a locationlocation_get: Get details for a locationlocation_set_maintenance: Set maintenance for a location
Port & Port Group Tools
ports_list: List all ports (with optional filters)ports_search: Search ports (general search)ports_search_field: Search ports by a specific fieldports_search_mac: Search ports by MAC addressport_get: Get details for a specific portport_fdb: List MAC addresses learned on a portport_ip_info: Get IP address information for a portport_transceiver: Get transceiver information for a portport_description_get: Get a port descriptionport_description_update: Update a port descriptionport_groups_list: List port groupsport_group_add: Add a port groupport_group_list_ports: List ports in a port groupport_group_assign: Assign ports to a port groupport_group_remove: Remove ports from a port group
Port Security Tools
port_security_list: List port security configuration across all devicesport_security_device: Get port security configuration for a deviceport_security_port: Get port security configuration for a single port
Graph Tools
Graphs are returned as MCP images. The tools ask LibreNMS for PNG, which MCP
clients such as Claude can display (SVG, LibreNMS's default webui.graph_type,
often is not). A LibreNMS release that ignores the request renders in its
webui.graph_type format instead; the MIME type is taken from the response.
device_graphs_list: List the graph types available for a devicedevice_graph: Render a device-level graph (e.g.device_icmp_perf)port_graph: Render a per-port graph by interface name (bits,upkts,nupkts,errors,etherlike; the LibreNMS names such asport_bitsare accepted too)port_group_graph: Render a traffic graph for one or more ports by port ID
Interface names containing a slash (Te2/7) are sent percent-encoded, and some
reverse proxies reject or decode the encoded slash. When that happens,
port_graph (for bits) and device_ports_get retry by port ID instead, so
they still work behind such a proxy. Authentication errors are never retried,
and LibreNMS's own "not found" answers are reported as is for names without a
slash (a name with a slash is always retried, since a decoding proxy can turn it
into a LibreNMS "not found" for the wrong path).
Other tools that put a slash-bearing value in the path (ports_search,
ports_search_field, oxidized_config_search with a prefix such as
0.0.0.0/0, location names) have no such fallback. If LibreNMS sits
behind Apache, allow encoded slashes so every tool works:
AllowEncodedSlashes NoDecodeA 400 or 404 for a path with an encoded slash that did not come from LibreNMS includes this hint in the tool's error message.
Alerting & Logging Tools
alerts_get: List current and historical alertsalert_get_by_id: Get details for a specific alertalert_acknowledge: Acknowledge an alertalert_unmute: Unmute an alertalert_rules_list: List alert rulesalert_rule_get: Get details for a specific alert rulealert_rule_add: Add an alert rulealert_rule_edit: Edit an alert rulealert_rule_delete: Delete an alert rulealert_templates_list: List all alert templatesalert_template_get: Get a specific alert templatealert_template_create: Create a new alert templatealert_template_edit: Edit an alert templatelogs_eventlog: Get event log for a device, or for all devices when no hostname is givenlogs_syslog: Get syslog for a device, or for all devices when no hostname is givenlogs_alertlog: Get alert log for a device, or for all devices when no hostname is givenlogs_authlog: Get the server-wide authentication loglogs_syslogsink: Add a syslog sink
Billing Tools
bills_list: List billsbill_get: Get details for a billbill_graph: Render a bill graph as an imagebill_graph_data: Get bill graph databill_history: Get bill historybill_history_graph: Render a bill history graph as an imagebill_history_graph_data: Get bill history graph databill_create_or_update: Create or update a billbill_delete: Delete a bill
Oxidized Tools
oxidized_list: List devices tracked by Oxidized for config backupoxidized_config_get: Get the stored configuration for a specific deviceoxidized_config_search: Search all stored device configurations for a string
Network & Monitoring Tools
arp_search: Search ARP entriespoller_group_get: Get poller group(s)routing_ip_addresses: List all IP addresses from LibreNMS.services_list: List all services from LibreNMS.services_for_device: Get services for a device from LibreNMS.service_add: Add a service to LibreNMSservice_edit: Edit an existing serviceservice_delete: Delete a servicebgp_sessions: List BGP sessionsbgp_session_get: Get details for a specific BGP sessionbgp_session_edit: Edit a BGP sessionfdb_lookup: Lookup forwarding database (FDB) entriesnac_list: List network access control (802.1X / MAB) sessions across all devicesospf_list: List OSPF instancesospf_ports: List OSPF portsvrf_list: List VRFsping: Ping the LibreNMS systemhealth_list: List health sensorshealth_by_type: List health sensors by typehealth_sensor_get: Get details for a health sensorsensors_list: List sensorsswitching_vlans: List all VLANs from LibreNMS.switching_links: List all links from LibreNMS.system_info: Get system info from LibreNMS.Flexible filtering and search for all major resources (devices, ports, alerts, logs, inventory, etc.)
📄 Pagination & Limit Support
To prevent overloading LLM contexts when querying large LibreNMS production instances, all list, search, and log tools support pagination.
Key Features
Sensible Defaults: All list tools default to returning 100 results per page.
Unified Parameters:
limit: The maximum number of results to return (defaults to100, minimum1).offset(orstartfor log tools): The number of results to skip.
Pagination Metadata: Every paginated response includes metadata fields:
limit: The active limit.offset(orstart): The active offset.count: The number of items returned in the current page.total: The total number of items available (for log tools, this is provided if returned by the LibreNMS API).
🚨 Error Responses
Every tool that returns JSON reports a failure in LibreNMS's own error shape, whether the error came from LibreNMS, from a check in this server, or from an exception such as a timeout:
{"status": "error", "message": "Device typo does not exist"}Check status == "error". Up to 1.11.3, exceptions were returned as
{"error": "..."}; clients that looked for an error key need updating.
🔒 Security & Safety Features
SNMP Credential Redaction
LibreNMS returns the full device record from its device endpoints (get, list
and search), including the SNMP community and the SNMPv3 username and
passphrases in plain text. No tool needs them, and anything a tool returns
ends up in an AI client's context, chat history and traces, so the server
replaces them with <redacted> as soon as a response is decoded:
the
community,authname,authpassandcryptopassvalues of device records (objects with adevice_idand ahostnameorsnmpver);the community and SNMPv3 username and passphrase arguments (
-C,-U,-A,-Xand their long forms) in theservice_paramofsnmp(check_snmp) services;the same device values in raw response text quoted in an error message.
Unset values stay as they are, so you can still see whether a credential is
configured; the SNMP version and algorithms are left visible for
troubleshooting. A community field outside a device record (a BGP
community, for instance) is not a credential and is left as is. Credentials
in other services' parameters (such as a check_mysql password) are not
redacted, and credentials sent with device_add are unaffected.
Redaction is on by default. A deployment whose clients need the credentials, such as a trusted automation, can turn it off:
REDACT_SNMP_CREDENTIALS=falseRead-Only Mode
The server supports a read-only mode that disables all write operations for safe monitoring:
READ_ONLY_MODE=trueTag-Based Tool Filtering
You can disable specific categories of tools by setting disabled tags:
DISABLED_TAGS=alert,alert-rules,alert-templates,billsA tool is hidden when any of its tags is disabled, and some tools carry more
than one category tag: for example, port_graph is tagged graphs and ports,
and ospf_list is tagged routing and ospf, so DISABLED_TAGS=ports also
hides port_graph. Alerting is split into three tags: alert (current alerts:
list, acknowledge, unmute), alert-rules and alert-templates; disable all
three to hide every alerting tool.
Besides the categories, read-only marks the tools that stay available in
read-only mode. The admin and global-read tags follow the permission groups
older LibreNMS releases used for their API routes (can:admin,
can:global-read). Current LibreNMS checks permissions per object instead, so
treat these two as broad categories rather than an exact match of what your
LibreNMS user may do.
Tool Search for Large Toolsets
FastMCP tool search can reduce prompt size for servers with many tools.
When enabled, list_tools returns two synthetic tools:
search_tools: Finds matching tools and returns their full schemascall_tool: Executes any discovered tool by name
Enable it with:
TOOL_SEARCH_ENABLED=true
TOOL_SEARCH_STRATEGY=bm25 # bm25 or regex
TOOL_SEARCH_MAX_RESULTS=5 # optional, default is 5bm25 supports natural language queries, while regex uses a regex pattern input for deterministic matching.
Tool search respects existing visibility controls (read-only mode and disabled tags).
Short Device Names
LibreNMS matches devices by their full hostname or ID, so a call naming a
device by its short name (rtr1 for rtr1.dc1.example.net) answers
"Device rtr1 does not exist". With
RESOLVE_SHORT_HOSTNAMES=truea bare short name in a tool's hostname or device argument is replaced by
the stored hostname of the one device whose hostname, up to the first dot, or
whose sysName equals it (ignoring case), so a device added by IP is found by
its sysName. A device whose stored hostname is the name itself always wins,
so calls that already worked keep working. Surrounding whitespace is ignored.
This costs two devices searches (hostname and sysName) per call that uses a
short name. Names containing a dot or a colon (FQDNs, IP addresses) and
device IDs are sent as given, a name that matches no device is left for the
tool to report, and a name that matches several devices is refused with a
tool error listing the candidates.
Rate Limiting
The server supports rate limiting to control API usage and prevent abuse. If enabled, requests are limited per client using a sliding window algorithm.
Enable rate limiting by setting the following environment variables in your .env file:
RATE_LIMIT_ENABLED=true
RATE_LIMIT_MAX_REQUESTS=100 # Maximum requests allowed per window
RATE_LIMIT_WINDOW_MINUTES=1 # Window size in minutesIf RATE_LIMIT_ENABLED is set to true, the server will apply rate limiting middleware. Adjust RATE_LIMIT_MAX_REQUESTS and RATE_LIMIT_WINDOW_MINUTES as needed for your environment.
Sentry Error Tracking & Monitoring (Optional)
The server optionally supports Sentry for error tracking, performance monitoring, and debugging. Sentry integration is completely optional and only initialized if configured.
Installation
To enable Sentry monitoring, install the optional dependency:
# Using UV (recommended)
uv sync --extra sentryConfiguration
Enable Sentry by setting the SENTRY_DSN environment variable in your .env file:
# Required: Sentry DSN for your project
SENTRY_DSN=https://your-key@o12345.ingest.us.sentry.io/6789
# Optional: Performance monitoring sample rate (0.0-1.0, default: 1.0)
SENTRY_TRACES_SAMPLE_RATE=1.0
# Optional: Include personally identifiable information (default: false).
# When true, tool inputs and outputs (device configs, SNMP credentials) are sent to Sentry.
SENTRY_SEND_DEFAULT_PII=false
# Optional: Environment name (e.g., "production", "staging")
SENTRY_ENVIRONMENT=production
# Optional: Release version (auto-detected from package if not set)
SENTRY_RELEASE=1.2.2
# Optional: Profiling - continuous profiling sample rate (0.0-1.0, default: 1.0)
SENTRY_PROFILE_SESSION_SAMPLE_RATE=1.0
# Optional: Profiling - lifecycle mode for profiling (default: "trace")
# Options: "all", "continuation", "trace"
SENTRY_PROFILE_LIFECYCLE=trace
# Optional: Enable log capture as breadcrumbs and events (default: true)
SENTRY_ENABLE_LOGS=trueFeatures
When enabled, Sentry automatically captures:
Exceptions & Errors: All unhandled exceptions with full context
Performance Metrics: Request/response times and traces
MCP Integration: Detailed MCP server activity and interactions
Logs & Breadcrumbs: Application logs and event trails for debugging
Context Data: Environment, client info, and request parameters
Getting a Sentry DSN
Create a free account at sentry.io
Create a new Python project
Copy your DSN from the project settings
Set it in your
.envfile
Disabling Sentry
Sentry is completely optional. If you don't set SENTRY_DSN, the server will run normally without any Sentry integration, and no monitoring data will be collected.
SSL/TLS Configuration
The server supports SSL certificate verification and custom timeout settings:
LIBRENMS_VERIFY_SSL=true # Enable SSL certificate verification
LIBRENMS_TIMEOUT=30 # Connection timeout in secondsTransport Configuration
The server supports multiple transport mechanisms for the MCP protocol. MCP_TRANSPORT is case-insensitive, streamable-http is accepted as an alias for http, and any other value stops the server at startup with an error rather than silently falling back to STDIO:
STDIO Transport (Default)
The default transport uses standard input/output for communication. This is ideal for local usage and integration with tools that communicate via stdin/stdout:
MCP_TRANSPORT=stdioHTTP SSE Transport (Server-Sent Events)
For network-based deployments, you can use HTTP with Server-Sent Events. This allows the MCP server to be accessed over HTTP with real-time streaming:
MCP_TRANSPORT=sse
MCP_HTTP_HOST=127.0.0.1 # Localhost
MCP_HTTP_PORT=8000 # Port to listen on
MCP_HTTP_BEARER_TOKEN=your-secret-token # Optional authentication tokenWhen using SSE transport with a bearer token, clients must include the token in their requests:
curl -H "Authorization: Bearer your-secret-token" http://localhost:8000/sseHTTP Streamable Transport
The HTTP Streamable transport provides HTTP-based communication with request/response streaming. This is ideal for web integrations and tools that need HTTP endpoints:
MCP_TRANSPORT=http
MCP_HTTP_HOST=127.0.0.1 # Localhost
MCP_HTTP_PORT=8000 # Port to listen on
MCP_HTTP_BEARER_TOKEN=your-secret-token # Optional authentication tokenWhen using streamable transport with a bearer token:
curl -H "Authorization: Bearer your-secret-token" \
-H "Accept: application/json, text/event-stream" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}' \
http://localhost:8000/mcpNote: The HTTP transport requires proper JSON-RPC formatting with jsonrpc and id fields. The server may also require session initialization for some operations.
Health Endpoint
Both HTTP transports (sse and http) serve GET /health, which answers 200 ok
when the server is handling requests. It needs no bearer token and does not
contact LibreNMS, so a LibreNMS outage does not mark the MCP server unhealthy.
The Docker image's HEALTHCHECK uses it:
curl http://localhost:8000/healthFor more information on FastMCP transports, see the FastMCP documentation.
🤝 Contributing
Contributions are welcome. See CONTRIBUTING.md for the dev setup, checks and commit message format, and use the issue templates for bugs and feature requests.
Found a security problem? Please report it privately as described in SECURITY.md.
📜 License
MIT License - see LICENSE for details.
Available Tools
113 toolsalert_acknowledgeAlert AcknowledgeCIdempotent
Acknowledge an alert in LibreNMS by ID.
Inputs: alert_id (required), note, until_clear. Returns: object
alert_get_by_idAlert Get By IdARead-onlyIdempotent
Get a specific alert from LibreNMS by ID.
Inputs: alert_id (required). Returns: object
alert_rule_addAlert Rule AddCDestructive
Add a new alert rule to LibreNMS.
Inputs: payload (required). Returns: object
alert_rule_deleteAlert Rule DeleteADestructiveIdempotent
Delete an alert rule from LibreNMS by ID.
Inputs: rule_id (required). Returns: object
alert_rule_editAlert Rule EditCDestructiveIdempotent
Edit an existing alert rule in LibreNMS.
Inputs: payload (required). Returns: object
alert_rule_getAlert Rule GetBRead-onlyIdempotent
Get details for a specific alert rule by ID.
Inputs: rule_id (required). Returns: object
alert_rules_listAlert Rules ListCRead-onlyIdempotent
List all alert rules from LibreNMS.
Inputs: limit, offset. Returns: object
alerts_getAlerts GetBRead-onlyIdempotent
Get alerts from LibreNMS with optional filters.
Inputs: limit, order, state, offset, +2 more. Returns: object
alert_template_createAlert Template CreateC
Create a new alert template in LibreNMS.
Inputs: payload (required). Returns: object
alert_template_editAlert Template EditCDestructiveIdempotent
Edit an existing alert template in LibreNMS.
Inputs: payload (required). Returns: object
alert_template_getAlert Template GetARead-onlyIdempotent
Get a specific alert template from LibreNMS by ID.
Inputs: template_id (required). Returns: object
alert_templates_listAlert Templates ListCRead-onlyIdempotent
List all alert templates from LibreNMS.
Inputs: limit, offset. Returns: object
alert_unmuteAlert UnmuteAIdempotent
Unmute an alert in LibreNMS by ID.
Inputs: alert_id (required). Returns: object
arp_searchArp SearchCRead-onlyIdempotent
Retrieve ARP entries from LibreNMS by search query.
Inputs: query (required), limit, device, offset. Returns: object
bgp_session_editBgp Session EditBDestructiveIdempotent
Edit BGP session in LibreNMS by ID.
Inputs: bgp_id (required), payload (required). Returns: object
bgp_session_getBgp Session GetBRead-onlyIdempotent
Get BGP session from LibreNMS by ID.
Inputs: bgp_id (required). Returns: object
bgp_sessionsBgp SessionsCRead-onlyIdempotent
List BGP sessions from LibreNMS with optional filters.
Inputs: asn, limit, offset, hostname, +7 more. Returns: object
bill_create_or_updateBill Create Or UpdateCDestructive
Create or update a bill in LibreNMS.
Inputs: payload (required). Returns: object
bill_deleteBill DeleteADestructiveIdempotent
Delete a bill from LibreNMS by ID.
Inputs: bill_id (required). Returns: object
bill_getBill GetARead-onlyIdempotent
Get a specific bill from LibreNMS by ID.
Inputs: bill_id (required), period. Returns: object
bill_graphBill GraphARead-onlyIdempotent
Render a bill graph as an image.
For the underlying numbers rather than a picture, use bill_graph_data.
Inputs: bill_id (required), graph_type (required).
bill_graph_dataBill Graph DataCRead-onlyIdempotent
Get bill graph data from LibreNMS.
Inputs: bill_id (required), graph_type (required). Returns: object
bill_historyBill HistoryCRead-onlyIdempotent
Get bill history from LibreNMS.
Inputs: bill_id (required), limit, offset. Returns: object
bill_history_graphBill History GraphARead-onlyIdempotent
Render a graph for a past billing period as an image.
For the underlying numbers rather than a picture, use bill_history_graph_data.
Inputs: bill_id (required), graph_type (required), history_id (required).
bill_history_graph_dataBill History Graph DataCRead-onlyIdempotent
Get bill history graph data from LibreNMS.
Inputs: bill_id (required), graph_type (required), history_id (required). Returns: object
bills_listBills ListARead-onlyIdempotent
List bills from LibreNMS with optional filters.
Inputs: ref, limit, custid, offset, +1 more. Returns: object
device_addDevice AddCDestructive
Add a new device to LibreNMS.
Inputs: payload (required). Returns: object
device_availabilityDevice AvailabilityBRead-onlyIdempotent
Get device availability from LibreNMS.
Inputs: hostname (required). Returns: object
device_deleteDevice DeleteADestructiveIdempotent
Delete a device from LibreNMS by hostname.
Inputs: hostname (required). Returns: object
device_discoverDevice DiscoverB
Trigger device rediscovery in LibreNMS.
Inputs: hostname (required). Returns: object
device_eventlog_addDevice Eventlog AddC
Add a custom event log entry for a device.
Inputs: payload (required), hostname (required). Returns: object
device_fdbDevice FdbARead-onlyIdempotent
List the forwarding database (learned MAC addresses) for a device.
Each entry carries the port_id it was learned on, so this is the device-wide view of what is plugged into a switch.
Inputs: hostname (required), limit, offset. Returns: object
device_getDevice GetARead-onlyIdempotent
Get device details from LibreNMS by hostname.
Inputs: hostname (required). Returns: object
device_graphDevice GraphARead-onlyIdempotent
Render a device-level graph as an image.
Inputs: hostname (required), graph_type (required), width, height, +3 more.
device_graphs_listDevice Graphs ListARead-onlyIdempotent
List the graph types available for a device.
Use this to discover the values accepted by the graph_type argument of
device_graph, for example 'device_icmp_perf' or 'device_poller_perf'.
Inputs: hostname (required). Returns: object
devicegroup_addDevicegroup AddBDestructive
Add a new device group to LibreNMS.
Inputs: payload (required). Returns: object
devicegroup_add_devicesDevicegroup Add DevicesCDestructive
Add devices to a device group in LibreNMS.
Inputs: name (required), payload (required). Returns: object
devicegroup_deleteDevicegroup DeleteBDestructiveIdempotent
Delete a device group from LibreNMS by name.
Inputs: name (required). Returns: object
devicegroup_devicesDevicegroup DevicesCRead-onlyIdempotent
List devices in a device group from LibreNMS.
Inputs: name (required), full, limit, offset. Returns: object
devicegroup_remove_devicesDevicegroup Remove DevicesCDestructive
Remove devices from a device group in LibreNMS.
Inputs: name (required), payload (required). Returns: object
devicegroup_set_maintenanceDevicegroup Set MaintenanceCDestructiveIdempotent
Set maintenance for a device group in LibreNMS.
Inputs: name (required), payload (required). Returns: object
devicegroups_listDevicegroups ListCRead-onlyIdempotent
List all device groups from LibreNMS.
Inputs: limit, offset. Returns: object
devicegroup_updateDevicegroup UpdateBDestructiveIdempotent
Update a device group in LibreNMS.
Inputs: name (required), payload (required). Returns: object
device_linksDevice LinksBRead-onlyIdempotent
Get network links for a specific device.
Inputs: hostname (required), limit, offset. Returns: object
device_maintenance_statusDevice Maintenance StatusARead-onlyIdempotent
Check if a device is currently in maintenance mode.
Inputs: hostname (required). Returns: object
device_nacDevice NacARead-onlyIdempotent
List network access control (802.1X / MAB) sessions on a device.
Shows authenticated endpoints per port, including the authentication method and the assigned VLAN where the device reports it.
Inputs: hostname (required), limit, offset. Returns: object
device_outagesDevice OutagesBRead-onlyIdempotent
Get device outages from LibreNMS.
Inputs: hostname (required), limit, offset. Returns: object
device_parents_clearDevice Parents ClearCDestructiveIdempotent
Remove dependency parents from a device.
Inputs: hostname (required), parent_ids. Returns: object
device_parents_setDevice Parents SetAIdempotent
Set the dependency parents of a device.
Parents drive alert suppression: a device whose parent is down is not alerted on its own. LibreNMS replaces the device's parents with the given ones (it syncs the set), so pass every parent the device should keep. A device cannot be its own parent.
Inputs: hostname (required), parent_ids (required). Returns: object
device_portsDevice PortsBRead-onlyIdempotent
List ports for a device from LibreNMS.
Inputs: hostname (required), limit, offset, columns. Returns: object
device_ports_getDevice Ports GetARead-onlyIdempotent
Get port info for a device by interface name.
Names like 'Te2/7' can fail by name behind proxies that reject or decode the encoded slash. The port is then looked up by ID instead; that response has the same shape but lacks the computed rate fields (in_rate, out_rate, ...).
Inputs: ifname (required), hostname (required). Returns: object
device_renameDevice RenameBDestructiveIdempotent
Rename a device in LibreNMS.
Inputs: hostname (required), new_hostname (required). Returns: object
device_set_maintenanceDevice Set MaintenanceBIdempotent
Set device maintenance in LibreNMS.
Inputs: payload (required), hostname (required). Returns: object
devices_listDevices ListARead-onlyIdempotent
List devices from LibreNMS with optional filters.
Inputs: limit, query, offset. Returns: object
device_updateDevice UpdateCDestructiveIdempotent
Update device fields in LibreNMS.
Inputs: payload (required), hostname (required). Returns: object
device_vlansDevice VlansBRead-onlyIdempotent
Get VLANs configured on a specific device.
Inputs: hostname (required), limit, offset. Returns: object
device_wireless_sensorsDevice Wireless SensorsARead-onlyIdempotent
List the wireless sensors of a device with their current values.
Wireless readings (frequency, clients, distance, rssi, ccq, rate, noise-floor, power, quality, capacity, utilization) are kept apart from the health sensors in LibreNMS, so they do not appear in health_* or sensors_list; this is the only route that returns them.
Inputs: hostname (required), sensor_class. Returns: object
fdb_lookupFdb LookupBRead-onlyIdempotent
Look up a MAC address in the forwarding database.
Inputs: mac (required). Returns: object
health_by_typeHealth By TypeBRead-onlyIdempotent
Get health data by sensor type for a device.
Inputs: type (required), hostname (required), limit, offset. Returns: object
health_listHealth ListARead-onlyIdempotent
List available health graphs for a device.
Inputs: hostname (required), limit, offset. Returns: object
health_sensor_getHealth Sensor GetARead-onlyIdempotent
Get a specific sensor by ID for a device.
Inputs: type (required), hostname (required), sensor_id (required). Returns: object
inventory_deviceInventory DeviceBRead-onlyIdempotent
Get inventory for a device from LibreNMS.
Inputs: hostname (required), limit, offset, ent_physical_class, +1 more. Returns: object
inventory_device_flatInventory Device FlatARead-onlyIdempotent
Get flattened inventory for a device from LibreNMS.
Inputs: hostname (required), limit, offset. Returns: object
location_addLocation AddADestructive
Add a new location to LibreNMS.
Inputs: payload (required). Returns: object
location_deleteLocation DeleteBDestructiveIdempotent
Delete a location from LibreNMS by ID or name.
Inputs: location (required). Returns: object
location_editLocation EditCDestructiveIdempotent
Edit a location in LibreNMS.
Inputs: payload (required), location (required). Returns: object
location_getLocation GetARead-onlyIdempotent
Get a specific location from LibreNMS by identifier.
Inputs: location (required). Returns: object
location_set_maintenanceLocation Set MaintenanceBIdempotent
Set maintenance mode for all devices in a location.
Inputs: payload (required), location (required). Returns: object
locations_listLocations ListBRead-onlyIdempotent
List locations from LibreNMS.
Inputs: limit, offset. Returns: object
logs_alertlogLogs AlertlogBRead-onlyIdempotent
Get alert logs for a device from LibreNMS.
Inputs: limit, start, to_ts, from_ts, +2 more. Returns: object
logs_authlogLogs AuthlogARead-onlyIdempotent
Get authentication logs from LibreNMS.
Auth logs are server-wide rather than per-device, so this takes no hostname.
Inputs: limit, start, to_ts, from_ts, +1 more. Returns: object
logs_eventlogLogs EventlogCRead-onlyIdempotent
Get event logs for a device from LibreNMS.
Inputs: limit, start, to_ts, from_ts, +2 more. Returns: object
logs_syslogLogs SyslogCRead-onlyIdempotent
Get syslogs for a device from LibreNMS.
Inputs: limit, start, to_ts, from_ts, +2 more. Returns: object
logs_syslogsinkLogs SyslogsinkB
Add a syslog entry to LibreNMS via API sink.
Inputs: payload (required). Returns: object
nac_listNac ListARead-onlyIdempotent
List network access control (802.1X / MAB) sessions across all devices.
Note that LibreNMS answers with a 404 and "Nac entry does not exist" rather than an empty list when nothing matches.
Inputs: mac, limit, offset. Returns: object
ospf_listOspf ListCRead-onlyIdempotent
List all OSPF instances from LibreNMS.
Inputs: limit, offset. Returns: object
ospf_portsOspf PortsBRead-onlyIdempotent
List all OSPF ports/interfaces from LibreNMS.
Inputs: limit, offset. Returns: object
oxidized_config_getOxidized Config GetARead-onlyIdempotent
Get the stored device configuration from Oxidized for a specific device.
Inputs: hostname (required). Returns: object
oxidized_config_searchOxidized Config SearchBRead-onlyIdempotent
Search all Oxidized device configurations for a string.
Inputs: search (required), limit, offset. Returns: object
oxidized_listOxidized ListBRead-onlyIdempotent
List devices tracked by Oxidized for config backup.
Inputs: limit, offset, hostname. Returns: object
pingPingARead-onlyIdempotent
Simple API health check - ping LibreNMS API.
Inputs: no named parameters. Returns: object
poller_group_getPoller Group GetBRead-onlyIdempotent
Get poller group(s) from LibreNMS.
Inputs: poller_group. Returns: object
port_description_getPort Description GetARead-onlyIdempotent
Get port description from LibreNMS by port ID.
Inputs: port_id (required). Returns: object
port_description_updatePort Description UpdateBDestructiveIdempotent
Update port description in LibreNMS by port ID.
Inputs: payload (required), port_id (required). Returns: object
port_fdbPort FdbARead-onlyIdempotent
List the MAC addresses learned on a port, from the forwarding database.
This answers "what is connected to this port". To go the other way and find which port a known MAC sits on, use fdb_lookup instead.
Inputs: port_id (required), limit, offset. Returns: object
port_getPort GetCRead-onlyIdempotent
Get port info from LibreNMS by port ID.
Inputs: port_id (required). Returns: object
port_graphPort GraphARead-onlyIdempotent
Render a per-port graph as an image, for example interface traffic.
Names like 'Te2/7' can fail by name behind proxies that reject or decode the encoded slash. For 'bits' this tool then falls back to the port-group endpoint, which renders the same traffic data by port ID, so callers still get a graph.
Inputs: ifname (required), hostname (required), width, height, +4 more.
port_group_addPort Group AddBDestructive
Add a port group to LibreNMS.
Inputs: payload (required). Returns: object
port_group_assignPort Group AssignB
Assign ports to a port group in LibreNMS.
Inputs: payload (required), port_group_id (required). Returns: object
port_group_graphPort Group GraphARead-onlyIdempotent
Render a traffic graph for one or more ports, by port ID.
Plots every supplied port on the same axes, which makes it useful for comparing members of a LAG. Unlike port_graph this takes numeric port IDs rather than interface names.
Inputs: port_ids (required), width, height, legend, +2 more.
port_group_list_portsPort Group List PortsCRead-onlyIdempotent
List ports in a port group from LibreNMS.
Inputs: name (required), limit, offset. Returns: object
port_group_removePort Group RemoveB
Remove ports from a port group in LibreNMS.
Inputs: payload (required), port_group_id (required). Returns: object
port_groups_listPort Groups ListCRead-onlyIdempotent
List port groups from LibreNMS.
Inputs: limit, offset. Returns: object
port_ip_infoPort Ip InfoARead-onlyIdempotent
Get port IP info from LibreNMS by port ID.
Inputs: port_id (required). Returns: object
port_security_devicePort Security DeviceARead-onlyIdempotent
Get port security configuration for every port on a device.
Inputs: hostname (required), limit, offset. Returns: object
port_security_listPort Security ListARead-onlyIdempotent
List port security configuration across all devices.
Covers switchport port-security state such as the maximum number of learned MAC addresses, violation mode and current status.
Inputs: limit, offset. Returns: object
port_security_portPort Security PortARead-onlyIdempotent
Get port security configuration for a single port.
Inputs: port_id (required). Returns: object
ports_listPorts ListCRead-onlyIdempotent
Get all ports from LibreNMS with optional filters.
Inputs: limit, query, offset. Returns: object
ports_searchPorts SearchBRead-onlyIdempotent
Search ports in LibreNMS by search string.
Inputs: search (required), limit, offset. Returns: object
ports_search_fieldPorts Search FieldCRead-onlyIdempotent
Search ports in LibreNMS by specific field.
Inputs: field (required), search (required), limit, offset. Returns: object
ports_search_macPorts Search MacARead-onlyIdempotent
Find the switch ports where a MAC address was learned (forwarding table).
This searches LibreNMS's FDB data, i.e. where a host's MAC appears on the network, not the ports' own hardware addresses: a port's own MAC is not found unless another device learned it. Results are ordered by how many MACs each port has learned, so the access port the host is plugged into usually comes first.
Inputs: mac (required), limit, offset. Returns: object
port_transceiverPort TransceiverARead-onlyIdempotent
Get port transceiver info from LibreNMS by port ID.
Inputs: port_id (required). Returns: object
routing_ip_addressesRouting Ip AddressesBRead-onlyIdempotent
List all IP addresses from LibreNMS.
Inputs: limit, offset. Returns: object
sensors_listSensors ListARead-onlyIdempotent
List all sensors across all devices.
Inputs: limit, offset. Returns: object
service_addService AddCDestructive
Add a service for a device in LibreNMS.
Inputs: payload (required), hostname (required). Returns: object
service_deleteService DeleteADestructiveIdempotent
Delete a service from LibreNMS by service ID.
Inputs: service_id (required). Returns: object
service_editService EditADestructiveIdempotent
Edit a service in LibreNMS by service ID.
Inputs: payload (required), service_id (required). Returns: object
services_for_deviceServices For DeviceBRead-onlyIdempotent
Get services for a device from LibreNMS.
Inputs: hostname (required), limit, state, offset, +1 more. Returns: object
services_listServices ListARead-onlyIdempotent
List all services from LibreNMS with optional filters.
Inputs: limit, state, offset, service_type. Returns: object
switching_linksSwitching LinksCRead-onlyIdempotent
List all links from LibreNMS.
Inputs: limit, offset. Returns: object
switching_vlansSwitching VlansCRead-onlyIdempotent
List all VLANs from LibreNMS.
Inputs: limit, offset. Returns: object
system_infoSystem InfoCRead-onlyIdempotent
Get system info from LibreNMS.
Inputs: no named parameters. Returns: object
vrf_listVrf ListBRead-onlyIdempotent
List all VRF (Virtual Routing and Forwarding) instances from LibreNMS.
Inputs: limit, offset. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 113 tools
Many tools are distinct, but several overlap: fdb_lookup and ports_search_mac both find ports by MAC, while device_ports, device_ports_get, port_get, ports_list, and ports_search are near-neighbors. Descriptions often clarify boundaries, but the set still requires careful selection among similar lookup/list tools.
The surface is mostly snake_case, but conventions are mixed: noun-first names like logs_eventlog and health_list coexist with verb-first names like alert_rule_add. Singular/plural inconsistency (devicegroup vs devicegroups, port_group_add vs port_groups_list) makes the pattern only partly predictable.
113 tools is far beyond a practical surface for reliable agent selection, even for a broad network-monitoring domain. Many tools are granular list/search/get variants, making this an extreme count mismatch.
Core LibreNMS domains are extensively covered: devices, ports, alerts/rules/templates, billing, health/sensors, logs, groups, locations, routing, switching, NAC, Oxidized, and services. Minor lifecycle gaps remain, such as no alert_template_delete and limited port create/delete or maintenance variants, but most workflows are supported.
Maintenance
Related MCP Connectors
MCP server for Pentest-Tools.com: run scans, manage findings and reports via your preffered LLM.
The Mercado Pago MCP Server implements the Model Context Protocol to provide AI agents and LLMs with access to Mercado Pago's APIs and tools within compatible development environments. It acts as an intermediary that translates Mercado Pago resources into executable functions (tools) that AI applications can invoke to perform actions and automate flows. The server simplifies integration, enables using documentation to implement or improve code, and optimizes operations through natural language interactions without manual implementations.
An MCP server that provides an API to LLMs to manage their JumpCloud resources.
MCP server for Uptrack uptime monitoring. Manage monitors and incidents from AI agents.
Related MCP Servers
- AlicenseCqualityBmaintenanceA Python-based MCP server that enables querying Cisco's Meraki Dashboard API to discover, monitor, and manage Meraki environments.2247MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for the FortiMonitor v2 monitoring API. 241 tools across 33 modules covering server management, outage monitoring, maintenance windows, metrics, notifications, cloud monitoring, SNMP, dashboards, reporting, and more. Unofficial community project, not affiliated with Fortinet. Python, MIT license, Docker and local deployment supported.3MIT
- AlicenseNot gradedqualityDmaintenanceMCP server for interacting with NetBox API, enabling users to query and manage NetBox resources such as devices through natural language.MIT
- AlicenseNot gradedqualityCmaintenanceMCP server for LibreNMS network monitoring — query devices, alerts, sensors, ports, and more through AI assistants like Claude.MIT