Skip to main content

The #1 agentic semantic tool search: 91.6% first-try accuracy on S1 Search Bench • Explore Tool Discovery →

Live 50 Actions

Auvik MCP Server
for AI Agents

Connect your AI agent to StackOne's Auvik MCP server and give it 50 MCP tools out of the box. Auth, tool execution, and security all managed.

Start Free Book Demo Read Docs →
Auvik logo
Auvik MCP Server
Built by StackOne StackOne
DrataGPLocalyzeFlipMindtoolsScreenloop

Coverage

50 Agent Actions

Create, read, update, and delete across Auvik — and extend your agent's capabilities with custom actions.

MCP Actions → Build Actions →

Authentication

Agent Tool Authentication

Per-user OAuth in one call. Your Auvik MCP server gets session-scoped tokens with zero credentials stored on your infra.

Agent Auth →

Security

Agent Protection

Every Auvik tool response scanned for prompt injection in milliseconds — 88.7% accuracy, all running on CPU.

Prompt Injection Defense →

Performance

Max Agent Context. Min Cost.

Free up to 96% of your agent's context window to enhance reasoning and reduce cost, on every Auvik call.

Tools Discovery →

What is the Auvik MCP Server?

A Auvik MCP server lets AI agents read and write Auvik data through the Model Context Protocol — Anthropic's open standard for connecting LLMs to external tools. StackOne's Auvik MCP server ships with 50 pre-built actions, fully extensible via the Connector Builder — plus managed authentication, prompt injection defense, observability, and agent execution runtime. Connect it from MCP clients like Claude Desktop, Claude Code, Cursor, Goose, and VS Code, or from agent frameworks like OpenAI Agents SDK, LangChain, and Vercel AI SDK.

All Auvik MCP Tools

Every action from Auvik's API, ready for your agent. Create, read, update, and delete — scoped to exactly what you need.

Other (50)

  • Read Multiple Devices' Info

    Retrieve a paginated list of monitored devices with their summary inventory info, optionally scoped to specific tenants and filtered by device type, make/model, vendor, online status, last-seen time, and network membership.

  • Read A Single Device's Info

    Retrieve the summary inventory info for a single device by its unique device ID.

  • Read Multiple Devices' Details

    Retrieve a paginated list of devices with their detailed discovery and management attributes, optionally scoped to tenants and filtered by manage status and discovery/protocol status.

  • Read A Single Device's Details

    Retrieve the detailed discovery and management attributes for a single device by its unique device ID.

  • Read Multiple Devices' Extended Details

    Retrieve a paginated list of devices with their extended details for a required device type, optionally scoped to tenants and filtered by modification time, last-seen time, and state-known.

  • Read A Single Device's Extended Details

    Retrieve the extended details for a single device by its unique device ID.

  • Read Multiple Devices' Lifecycle Info

    Retrieve a paginated list of devices with their lifecycle status (sales availability, software/security maintenance, last support), optionally scoped to tenants.

  • Read A Single Device's Lifecycle Info

    Retrieve the lifecycle status (sales availability, software/security maintenance, last support) for a single device by its unique device ID.

  • Read Multiple Devices' Warranty Info

    Retrieve a paginated list of devices with their warranty coverage info, optionally scoped to tenants and filtered by coverage status.

  • Read A Single Device's Warranty Info

    Retrieve the warranty coverage info for a single device by its unique device ID.

  • Read Multiple Networks' Info

    Retrieve a paginated list of discovered networks with their summary info, optionally scoped to tenants and filtered by network type, scan status, and member devices.

  • Read A Single Network's Info

    Retrieve the summary info for a single network by its unique network ID.

  • Read Multiple Networks' Details

    Retrieve a paginated list of networks with their detailed attributes, optionally scoped to tenants and filtered by network type, scan status, member devices, modification time, and scope.

  • Read A Single Network's Details

    Retrieve the detailed attributes for a single network by its unique network ID.

  • Read Multiple Interfaces' Info

    Retrieve a paginated list of device interfaces with their summary info, optionally scoped to tenants and filtered by interface type, operational/admin status, and parent device.

  • Read A Single Interface's Info

    Retrieve the summary info for a single interface by its unique interface ID.

  • Read Multiple Components' Info

    Retrieve a paginated list of hardware components (fans, power supplies, sensors, etc.) with their summary info, optionally scoped to tenants and filtered by parent device and status.

  • Read A Single Component's Info

    Retrieve the summary info for a single hardware component by its unique component ID.

  • Read Multiple Device Configurations

    Retrieve a paginated list of backed-up device configurations, optionally scoped to tenants and filtered by device, backup time range, and running/saved state.

  • Read A Single Device Configuration

    Retrieve a single backed-up device configuration by its unique configuration ID.

  • Read Multiple Entity Audits

    Retrieve a paginated list of entity audit records (remote access sessions and similar activities), optionally scoped to tenants and filtered by user, category, and status.

  • Read A Single Entity Audit

    Retrieve a single entity audit record by its unique audit ID.

  • Read Multiple Entity Notes

    Retrieve a paginated list of notes attached to entities, optionally scoped to tenants and filtered by entity, type, name, and last modifier.

  • Read A Single Entity Note

    Retrieve a single entity note by its unique note ID.

  • Read Multiple Tenants

    Retrieve the list of client tenants accessible to the authenticated API user.

  • Read Multiple Tenant Details

    Retrieve detailed information for the client tenants under a given primary (parent) tenant domain prefix.

  • Read A Single Tenant Detail

    Retrieve detailed information for a single tenant by its unique tenant ID, within a given primary tenant domain prefix.

  • Read Multiple Alerts' Info

    Retrieve a paginated list of alert history records, optionally scoped to tenants and filtered by alert definition, severity, status, affected entity, dismissed/dispatched state, and detection time.

  • Read A Single Alert's Info

    Retrieve a single alert history record by its unique alert ID.

  • Dismiss An Alert

    Dismiss an active alert by its unique alert ID.

  • Read Device Statistics

    Read time-series device performance statistics (bandwidth, CPU, memory, storage utilization, packet counters) for a given statistic type over a time range, optionally scoped to tenants.

  • Read Device Availability Statistics

    Read time-series device availability statistics (availability, outage time, downtime) for a given statistic type over a time range, optionally scoped to tenants.

  • Read Interface Statistics

    Read time-series interface performance statistics (bandwidth, utilization, packet counters) for a given statistic type over a time range, optionally scoped to tenants.

  • Read Component Statistics

    Read time-series component statistics (temperature, fan speed, power status) for a given component type and statistic type over a time range, optionally scoped to tenants.

  • Read OID Statistics

    Read SNMP OID monitor statistics, optionally filtered by device and OID and scoped to tenants.

  • Read Service Statistics

    Read time-series cloud service ping statistics (round-trip time, packet loss, packets transmitted/received) for a given statistic type over a time range, optionally scoped to tenants.

  • Read SNMP Poller Integer Statistics

    Read time-series integer values collected by custom SNMP pollers over a time range, scoped to tenants and optionally filtered by device and poller setting.

  • Read SNMP Poller String Statistics

    Read time-series string values collected by custom SNMP pollers over a time range, scoped to tenants and optionally filtered by device and poller setting.

  • Read Multiple SNMP Poller Settings

    Retrieve a paginated list of custom SNMP poller settings for given tenants, optionally filtered by device, name, OID, type, use, make/model, vendor, and device type.

  • Read A Single SNMP Poller Setting

    Retrieve a single custom SNMP poller setting by its unique poller setting ID.

  • Read Devices For An SNMP Poller Setting

    Retrieve a paginated list of devices that a given SNMP poller setting applies to for given tenants, optionally filtered by online status, last-seen/modification time, device type, make/model, and vendor.

  • Read Client Billing Usage

    Read billable usage for client tenants over a given date range, optionally scoped to specific tenants.

  • Read Device Billing Usage

    Read billable usage for a single device over a given date range.

  • Read Multiple ASM Clients

    Retrieve the list of Auvik SaaS Management (ASM) clients accessible to the authenticated API user.

  • Read Multiple ASM Users

    Retrieve the SaaS users discovered for a given ASM client.

  • Read Multiple ASM Applications

    Retrieve the SaaS applications discovered for a given ASM client, optionally with breach, user, contract, publisher, and access data.

  • Read Multiple ASM Licenses

    Retrieve the SaaS license assignments for a given ASM client and application, with optional under-utilization and last-login filters.

  • Read Multiple ASM Tags

    Retrieve the SaaS application tags for a given ASM client, optionally scoped to a single application.

  • Read Multiple ASM Security Logs

    Retrieve the SaaS security log events for a given ASM client, optionally with related users and applications.

  • Verify API Credentials

    Verify that the configured Auvik API credentials (username and API key) are valid.

Set Up Your Auvik MCP Server in Minutes

One endpoint. Any framework. Your agent is talking to Auvik in under 10 lines of code.

MCP Clients

Claude Desktop setup guide
Claude Code setup guide
Cursor setup guide
Goose setup guide

Agent Frameworks

Claude Desktop
{
  "mcpServers": {
    "stackone": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://api.stackone.com/mcp?x-account-id=<account_id>",
        "--header",
        "Authorization: Basic <YOUR_BASE64_TOKEN>"
      ]
    }
  }
}

Platform Resources

MCP Code Mode: Keeping Tool Responses Out of Agent Context

Anthropic's code_execution processes data already in context. Custom MCP code mode keeps raw tool responses in a sandbox. 14K tokens vs 500.

11 min

Comparing BM25, TF-IDF, and Hybrid Search for MCP Tool Discovery

Benchmarking BM25, TF-IDF, and hybrid search for MCP tool discovery across 916 tools. The 80/20 TF-IDF/BM25 hybrid hits 21% Top-1 accuracy in under 1ms.

10 min

Indirect Prompt Injection Defense for MCP Tools: A Technical Guide

MCP tools that read emails, CRM records, and tickets are indirect prompt injection vectors. Here's how we built a two-tier defense that scans tool results in ~11ms.

12 min

Auvik MCP Server FAQ

Does StackOne have a Auvik MCP server?
Yes. StackOne offers a hosted Auvik MCP server with 50 pre-built actions, and every action is tested and QA'd by StackOne. Connect it to Claude, Cursor, and any other MCP client, or to any agent framework through the AI Action SDK. It ships with managed agent authentication, prompt injection defense, and tool discovery with server-side execution that preserve your agent's context window and keep reasoning performance.
Auvik MCP server vs direct API integration — what's the difference?
A Auvik MCP server and direct API integration serve different use cases. Direct API integration is for software-to-software — backend code calling Auvik. A Auvik MCP server is for AI agents — MCP clients like Claude and Cursor, plus framework agents built with OpenAI, LangChain, or Vercel AI — discovering and calling Auvik at runtime. StackOne provides both.
How does Auvik authentication work for AI agents?
Auvik authentication for AI agents works through a StackOne Connect Session. Create one via the dashboard or the SDK — you get an auth link and ready-to-paste config for Claude Desktop, Cursor, and other MCP clients. Your user authenticates their own Auvik account; StackOne handles token exchange, storage, and refresh. Credentials never reach the LLM, and each user is isolated via origin_owner_id.
Are Auvik MCP tools vulnerable to prompt injection?
Yes — Auvik MCP tools can be vulnerable to indirect prompt injection. Any tool that reads user-written content — documents, messages, tickets, records, or free-text fields — is a potential vector. StackOne Defender scans every tool response before it enters the agent's context — regex patterns in ~1ms, then a MiniLM classifier in ~4ms. 88.7% accuracy, CPU-only.
What is the context bloat of a Auvik agent and how do I avoid it?
Context bloat happens when Auvik tool schemas and API responses eat your Auvik agent's memory, preventing it from reasoning effectively. A single Auvik query can return a massive JSON response, and connecting multiple tools compounds the problem. Tools Discovery and Code Mode reduce context bloat — loading only relevant tools per query and keeping raw responses out of the agent's context.
Can I limit which actions my Auvik agent can access?
Yes — you can limit which actions your Auvik agent can access directly from the StackOne dashboard. Toggle actions on or off, or restrict them to specific accounts, with no code changes to your agent. Session tokens can be scoped to exact actions so if one leaks, exposure stays contained.
Can I create custom agent actions for my Auvik MCP server?
Yes — you can create custom agent actions for your Auvik MCP server using Connector Builder. It's an integration agent your coding assistant (Claude Code, Cursor, or Copilot) can invoke to research Auvik's API, generate production-ready connector YAML, test against the live API, and validate before you ship.
When should I NOT use a Auvik MCP server?
Skip a Auvik MCP server if your integration is purely software-to-software — direct Auvik API integration is simpler when no AI agent is involved. For deterministic, compliance-critical operations (financial transactions, regulatory reporting), direct API gives you predictable behavior without agent-driven decision-making. MCP shines when AI agents need to dynamically discover and call Auvik actions at runtime.
What AI frameworks and AI clients does the StackOne Auvik MCP server support?
The StackOne Auvik MCP server supports both. MCP clients (paste-and-go apps): Claude Desktop, Claude Code, Cursor, VS Code, Goose. Agent frameworks (code SDKs you build with): OpenAI Agents SDK, Anthropic, Vercel AI, Google ADK, CrewAI, Pydantic AI, LangChain, LangGraph, Azure AI Foundry.

Put your AI agents to work

All the tools you need to build and scale AI agent integrations, with best-in-class connectivity, execution, and security.

Start Free Book Demo