SolarWinds Observability Logs

Access and visualize logs from SolarWinds Observability.

A Model Context Protocol (MCP) server for accessing and visualizing SolarWinds Observability logs.

This server is currently incomplete as it does not support structured data search (a limitation of the REST API?). I'm uncertain if it also needs to accept a data center to use in the api endpoint calls. Will address both when time allows (needed it for a real work problem, have to fix that first)

Search SolarWinds Observability logs with optional filtering

- Takes search parameters including filter, time range, and pagination options
- Returns formatted log entries with timestamps, hostnames, and messages
- Supports advanced filtering by group, entity, and more
- Default search range is the last 24 hours

Generate a histogram json response for of log events

- Formatted for Claude and canvas representations
- Configurable time intervals (minute, hour, day)
- Supports UTC or local time zones
- Customizable query filters and time ranges
- Default visualization range is the last 24 hours

- URI Template:solarwinds://{query}/search
- Returns log entries matching the specified query
- Example:solarwinds://error/search

git clone https://github.com/@jakenuts/mcp-solarwinds.git cd mcp-solarwinds npm install npm run build

Add to%APPDATA%/Code - Insiders/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json:

{ "mcpServers": { "solarwinds": { "command": "npx", "args": ["-y", "mcp-solarwinds"], "env": { "SOLARWINDS_API_TOKEN": "your-api-token" }, "autoApprove": ["search_logs", "visualize_logs"] } } }

Windows:%APPDATA%/Claude/claude_desktop_config.jsonMacOS:~/Library/Application Support/Claude/claude_desktop_config.json

{ "mcpServers": { "solarwinds": { "command": "npx", "args": ["-y", "mcp-solarwinds"], "env": { "SOLARWINDS_API_TOKEN": "your-api-token" } } } }

If you encounter the ENOENT spawn npx issue on Windows, use this alternative configuration that specifies the full paths:

{ "mcpServers": { "solarwinds": { "command": "C:\\Users\\[username]\\AppData\\Roaming\\nvm\\[node-version]\\node.exe", "args": [ "C:\\Users\\[username]\\AppData\\Roaming\\npm\\node_modules\\npm\\bin\\npx-cli.js", "-y", "mcp-solarwinds" ], "env": { "SOLARWINDS_API_TOKEN": "your-api-token" } } } }

The SolarWinds Observability MCP server requires an API token to authenticate with the SolarWinds Observability API.

There are multiple ways to provide the API token:
- MCP Settings Configuration (Recommended): Configure the token in your MCP settings file
- Environment Variable: Set theSOLARWINDS_API_TOKENenvironment variable
- Local .env File (For Testing): Create a.envfile in the project root withSOLARWINDS_API_TOKEN=your-token
- Copy.env.exampleto.envand add your token
- Run the example script:node examples/local-test.js

{ "filter": "error" }

Advanced search with time range and pagination:

{ "filter": "error", "entityId": "web-server", "startTime": "2025-03-01T00:00:00Z", "endTime": "2025-03-05T23:59:59Z", "pageSize": 100, "direction": "backward" }

{ "filter": "error", "interval": "hour" }

{ "filter": "error", "entityId": "web-server", "startTime": "2025-03-01T00:00:00Z", "endTime": "2025-03-05T23:59:59Z", "interval": "day", "use_utc": true }

{ "filter": "error", "interval": "hour", "format": "json" }

The JSON format returns data that Claude can visualize as a chart:

{ "timeRanges": ["12:02", "12:03", "12:04", "12:05", "12:06", "12:07", "12:08", "12:09"], "counts": [261, 47, 48, 48, 31, 262, 270, 33], "total": 1000, "queryParams": { "query": "error", "startTime": "2025-03-05T00:00:00.000Z", "endTime": "2025-03-05T23:59:59.000Z" } }

Since MCP servers communicate over stdio, debugging can be challenging. The MCP Inspector provides helpful debugging tools:

This will provide a URL to access the inspector in your browser, where you can:

- View all MCP messages
- Inspect request/response payloads
- Test tools interactively
- Monitor server state

For local testing without the MCP framework:

# Create a .env file with your token cp .env.example .env # Edit .env to add your token # Run the example script node examples/local-test.js

- Built with TypeScript and the MCP SDK
- Uses axios for API communication
- Supports ISO 8601 date formats for time ranges
- Generates ASCII histograms for log visualization
- Default search range: last 24 hours
- Default page size: 50 logs
- Supports multiple authentication methods

Fetch logs, metrics, traces, and events from the Chronosphere observability platform.

The Datadog MCP Server acts as a bridge between your observability data in Datadog and any AI agents that support the Model Context Protocol (MCP).

An MCP server for the Datadog API, allowing you to search logs and traces.

Retrieve logs from the Mezmo observability platform.

Kubernetes observability and diagnostics MCP server for cluster health, workload diagnosis, logs, events, topology, audit findings, and remediation actions.

Seamlessly bring real-time production context—logs, metrics, and traces—into your local environment to auto-fix code faster.

Provides access to OpenTelemetry traces and metrics through Logfire.

A server for querying Loki logs from Grafana.

Incident forensic with log files analyzing

An MCP server for log analysis using the LogAI framework, with optional Grafana and GitHub integrations.