Splunk-MCP-Server-official

http://splunkbase.splunk.com/app/7931

Splunk MCP Server

Splunkbase App ID: 7931
Built by: Splunk LLC
Latest Version: 1.0.1 (February 7, 2026)
Status: Splunk Supported · Beta
Category: Artificial Intelligence, IT Operations
Rating: ⭐ 5/5 (7 reviews) · #8 in Artificial Intelligence
Downloads: 5,029+

Overview

The Model Context Protocol (MCP) is an open standard and framework that enables seamless, secure, and standardized two-way communication between AI applications (like large language models) and external data sources or tools. It acts as a universal adapter allowing AI systems to access, execute, and integrate functionalities from diverse systems through a common protocol, simplifying data sharing and tool interoperability without custom coding for each integration.

Splunk's MCP server leverages this to provide a standardized, secure, and scalable interface to connect AI assistants, agents, and other intelligent systems with data in the Splunk platform for both Enterprise and Cloud customers (currently in beta).

Compatibility

• Platforms: Splunk Enterprise, Splunk Cloud Platform
• Platform Versions: 8.0, 8.1, 8.2, 9.0, 9.1, 9.2, 9.3, 9.4, 10.0, 10.1, 10.2

Key Features

Universal Connectivity — Seamlessly connects AI agents and tools to Splunk data resources in a secure and efficient manner.

Enterprise-Grade Security — Includes built-in authentication, authorization, and Role-Based Access Control (RBAC). Respects existing Splunk authentication and access controls, preventing unauthorized data exposure. Supports auditing, logging, and input validation to monitor for malicious payloads or command injection attempts.

Rapid Deployment — Offers a plug-and-play solution, eliminating the need for custom integrations.

Core Capabilities

• Explore the Data — Navigate and interact with Splunk data effortlessly.
• Discover Knowledge Objects — Identify and access relevant saved searches, lookups, and other knowledge assets.
• Execute Searches — Run powerful Splunk queries to extract insights and drive intelligent workflows.
• Leverage AI capabilities from Splunk's AI Assistant — SPL search generation from natural language, search optimization, search explanation, retrieve MLTK models and algorithms.

MCP Server Type & Features

Deploy Type

HTTP/SSE — The server is hosted within your Splunk instance and exposed over HTTP. Clients connect via the Splunk management port (default 8089) at the endpoint /services/mcp. It is not a locally-spawned stdio process.

Example initialization response confirming the transport:

curl -k \
  -H "Authorization: Bearer <YOUR_TOKEN>" \
  -H "Content-Type: application/json" \
  -X POST \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"client":"curl","version":"0.1"}}' \
  https://<YOUR_SPLUNK_HOST>:8089/services/mcp

{
  "jsonrpc": "2.0",
  "id": 1,
  "result": {
    "protocolVersion": "2025-03-26",
    "capabilities": { "tools": {} },
    "serverInfo": { "name": "Splunk_MCP_Server", "version": "0.2.2" }
  }
}

Features / Capabilities

Tools only — The server exposes Splunk functionality exclusively as callable MCP Tools. The capabilities field in the initialization response confirms {"tools": {}} with no resources or prompts declared.

Available Tools

Safety guardrails are in place to prevent destructive operations.

Client Configuration Examples

Claude Desktop / Claude Code

Uses mcp-remote as a local proxy to inject the Authorization header:

{
  "mcpServers": {
    "splunk-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://<SPLUNK_HOST>:8089/services/mcp",
        "--header",
        "Authorization: Bearer <YOUR_TOKEN>"
      ],
      "env": {
        "NODE_TLS_REJECT_UNAUTHORIZED": "0"
      }
    }
  }
}

Set NODE_TLS_REJECT_UNAUTHORIZED: "0" if using self-signed certificates.

Cursor IDE

{
  "mcpServers": {
    "splunk-mcp-server": {
      "url": "https://<SPLUNK_HOST>:8089/services/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

Authorization & RBAC

Roles must be configured in authorize.conf to grant users access to MCP tools:

[role_mcp_user]
mcp_tool_admin = enabled
mcp_tool_execute = enabled

• sc_admin role can manage MCP capabilities (added in v1.0.0).
• All AI interactions respect existing Splunk RBAC — users can only access data their Splunk role permits.

SSL Configuration

In mcp.conf, you can configure SSL verification:

[mcp]
ssl_verify = true   # Set to false for self-signed certificates

Sample Use Cases

Security Operations — A SOC analyst queries: "Show me all failed login attempts from external IPs in the last hour." The MCP server executes the SPL search and returns a concise report.

DevOps Efficiency — A DevOps engineer asks: "What's the performance trend of my Kubernetes cluster logs in Splunk?" The server pulls and summarizes the data.

Business Insights — A product manager queries: "What's driving customer churn in Q2?" The server combines Splunk data with external sources for a comprehensive analysis.

Multi-App Insights — Connect a Confluence MCP server (containing Splunk system knowledge) with the Splunk MCP server for richer, more accurate insights.

Version History (Selected)

Resources

• Splunkbase App Page
• Official Configuration Docs
• Splunk Blog: Unlock the Power of Splunk Cloud Platform with the MCP Server
• Splunk Community Discussion
• Licensing: Splunk General Terms

© 2005–2026 Splunk LLC. All rights reserved.