{
  "markdown": "# Blumira MCP Server\n\n[![Build Status](https://github.com/WYRE-AI/blumira-mcp/actions/workflows/release.yml/badge.svg)](https://github.com/WYRE-AI/blumira-mcp/actions/workflows/release.yml)\n[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)\n[![Node.js](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg)](https://nodejs.org/)\n\nA [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server that provides AI assistants with structured access to [Blumira](https://blumira.com) SIEM platform data and operations.\n\n> **Note:** This project is maintained by [Wyre Technology](https://github.com/WYRE-AI).\n\n## Quick Start\n\n**Claude Desktop** — download, open, done:\n\n1. Download `blumira-mcp.mcpb` from the [latest release](https://github.com/WYRE-AI/blumira-mcp/releases/latest)\n2. Open the file (double-click or drag into Claude Desktop)\n3. Enter your Blumira JWT token when prompted\n\nNo terminal, no JSON editing, no Node.js install required.\n\n**Claude Code (CLI):**\n\n```bash\nclaude mcp add blumira-mcp \\\n  -e BLUMIRA_JWT_TOKEN=your-jwt-token \\\n  -- npx -y github:WYRE-AI/blumira-mcp\n```\n\nSee [Installation](#installation) for Docker and from-source methods.\n\n## Features\n\n- **🔌 MCP Protocol Compliance**: Full support for MCP resources and tools\n- **🛡️ Comprehensive SIEM Coverage**: Tools spanning findings, agents/devices, users, resolutions, and MSP account management\n- **🔍 Decision-Tree Navigation**: Start with `blumira_navigate` to explore domains, then dynamically load domain-specific tools\n- **🏢 MSP Multi-Tenant Support**: Full MSP endpoint coverage for managing findings, agents, and users across accounts\n- **🔒 Secure Authentication**: JWT token or API key (`pax8ApiTokenV1`) authentication\n- **🌐 Dual Transport**: Supports both stdio (local) and HTTP Streamable (remote/Docker) transports\n- **📦 MCPB Packaging**: One-click installation via MCP Bundle for desktop clients\n- **🐳 Docker Ready**: Containerized deployment with HTTP transport and health checks\n- **⚡ Rate Limiting**: Built-in rate limiter respects Blumira API limits\n- **🔎 Rich Filtering**: Support for `.eq`, `.in`, `.gt`, `.lt`, `.contains`, `.regex`, and negation operators\n\n## Installation\n\n### Option 1: MCPB Bundle (Claude Desktop)\n\nThe simplest method — no terminal, no JSON editing, no Node.js install required.\n\n1. Download `blumira-mcp.mcpb` from the [latest release](https://github.com/WYRE-AI/blumira-mcp/releases/latest)\n2. Open the file (double-click or drag into Claude Desktop)\n3. Enter your Blumira JWT token when prompted\n\nFor **Claude Code (CLI)**, one command:\n\n```bash\nclaude mcp add blumira-mcp \\\n  -e BLUMIRA_JWT_TOKEN=your-jwt-token \\\n  -- npx -y github:WYRE-AI/blumira-mcp\n```\n\n### Option 2: Docker\n\n```bash\ndocker compose up\n```\n\nOr pull the pre-built image:\n\n```bash\ndocker run -d \\\n  -e BLUMIRA_JWT_TOKEN=your-token \\\n  -p 8080:8080 \\\n  ghcr.io/wyre-ai/blumira-mcp:latest\n```\n\n### Option 3: From Source\n\n```bash\ngit clone https://github.com/WYRE-AI/blumira-mcp.git\ncd blumira-mcp\nnpm ci\nnpm run build\n```\n\n## Configuration\n\n| Variable | Description | Default |\n|----------|-------------|---------|\n| `BLUMIRA_JWT_TOKEN` | JWT token for authentication | — |\n| `MCP_TRANSPORT` | Transport mode (`stdio` or `http`) | `stdio` |\n| `MCP_HTTP_PORT` | HTTP server port | `8080` |\n| `AUTH_MODE` | Auth mode (`env` or `gateway`) | `env` |\n| `LOG_LEVEL` | Log level (`debug`, `info`, `warn`, `error`) | `info` |\n\n## Domains\n\nThe server uses decision-tree navigation. Start with `blumira_navigate` to pick a domain:\n\n| Domain | Tools |\n|--------|-------|\n| **findings** | List findings, get finding, get finding details, resolve finding, assign owners, list/add comments |\n| **agents** | List devices, get device, list agent keys, get agent key |\n| **users** | List users |\n| **resolutions** | List available resolutions |\n| **msp** | List/get accounts, list/get/resolve findings, assign owners, comments, list devices/keys, list users |\n\n## Filtering\n\nBlumira supports rich query filtering on list endpoints:\n\n```\nstatus.eq=10              # Exact match\nseverity.in=HIGH,CRITICAL # Multiple values\ncreated_at.gt=2026-01-01  # Greater than\nname.contains=malware     # Substring match\n!status.eq=30             # Negation\n```\n\nPass filters as tool input parameters — the server handles query string construction.\n\n## Docker Deployment\n\nCopy `.env.example` to `.env` and fill in your credentials:\n\n```bash\ncp .env.example .env\n# Edit .env with your Blumira JWT token\ndocker compose up -d\n```\n\n## Development\n\n```bash\nnpm ci\nnpm run build       # Build the project\nnpm run dev         # Watch mode\nnpm run test        # Run tests\nnpm run lint        # Type-check\nnpm run clean       # Remove dist/\n```\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n\n## License\n\nApache 2.0 — Copyright WYRE Technology\n",
  "bytes": 4911,
  "sha": "62c3b871a0f89ffbab8f2e784e42d5609d2c99ff3e18ab34be6a6d285ea3460c",
  "repo_slug": "wyre-technology/blumira-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_wyre_technology_blumira_mcp_fef40990/readme"
}