Bluerock
Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as structured NDJSON. No code changes.
What is Bluerock?
Bluerock is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to runtime visibility for python mcp servers. captures tool calls, session lifecycle, module imports (sha-256), and subprocess execution as structured ndjson. no code changes.
Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as structured NDJSON. No code changes.
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Runtime visibility for Python MCP servers. Captures tool cal
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx bluerockConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Bluerock
Bluerock is a runtime security and observability tool for Python MCP servers that works by wrapping the server process and capturing all MCP protocol events — tool calls, session lifecycle events, module imports with SHA-256 fingerprints, and subprocess executions — as structured NDJSON logs with zero code changes required. Security engineers and platform teams use it to audit what AI agents are actually doing at runtime, detect unexpected module loads, and produce tamper-evident traces of MCP sessions for compliance and incident response.
Prerequisites
- Python 3.10+ installed
- A running Python MCP server to monitor
- pip for installing the bluerock package
- Optionally: jq for parsing NDJSON event logs
Install Bluerock from PyPI
Install the open-source edition of Bluerock using pip with the oss extra to get the OSS sensor components.
pip install bluerock[oss]Create the configuration directory and config file
Bluerock reads its configuration from ~/.bluerock/bluerock-oss.json. Create this file to enable MCP monitoring and module import tracking.
mkdir -p ~/.bluerock
cat > ~/.bluerock/bluerock-oss.json << 'EOF'
{
"enable": true,
"mcp": true,
"imports": {
"enable": true,
"fileslist": true
}
}
EOFWrap your MCP server with Bluerock
Instead of running your MCP server directly, run it through Bluerock using python -m bluerock. Bluerock will intercept and log all MCP events without modifying the server.
python -m bluerock --oss --cfg-dir ~/.bluerock your_mcp_server.pyUpdate your MCP client config to use Bluerock as the wrapper
Modify your MCP client configuration to invoke your server through Bluerock so that all sessions are monitored automatically.
{
"mcpServers": {
"my-server-monitored": {
"command": "python",
"args": ["-m", "bluerock", "--oss", "--cfg-dir", "/Users/you/.bluerock", "/path/to/your_mcp_server.py"]
}
}
}Read and analyze the event logs
Events are written as NDJSON to ~/.bluerock/event-spool/. Use jq to filter and inspect tool call events, session lifecycle events, and module import fingerprints.
cat ~/.bluerock/event-spool/python-*.ndjson | jq .eventBluerock Examples
Client configuration
Claude Desktop configuration that wraps a Python MCP server with Bluerock for runtime monitoring.
{
"mcpServers": {
"monitored-server": {
"command": "python",
"args": [
"-m", "bluerock",
"--oss",
"--cfg-dir", "/Users/you/.bluerock",
"/path/to/your_mcp_server.py"
]
}
}
}Prompts to try
Bluerock is a monitoring wrapper, not an MCP server with its own tools. Use these shell commands to analyze captured events after running an MCP session.
- Filter for MCP tool call events: cat ~/.bluerock/event-spool/python-*.ndjson | jq 'select(.event == "python_mcp_event")'
- List all imported modules and their SHA-256 hashes: cat ~/.bluerock/event-spool/python-*.ndjson | jq 'select(.event == "python_mcp_server_add") | .imports'
- Count sessions created today: cat ~/.bluerock/event-spool/python-*.ndjson | jq 'select(.event == "python_mcp_session_created")' | wc -lTroubleshooting Bluerock
No events appear in the event-spool directory
Check that ~/.bluerock/bluerock-oss.json exists and has "enable": true and "mcp": true. Also verify the event-spool directory exists: ls ~/.bluerock/event-spool/. If missing, create it with mkdir -p ~/.bluerock/event-spool.
The wrapped MCP server fails to start or behaves differently
Run your server directly (without Bluerock) to confirm it starts cleanly. Then add Bluerock back. Check that the path to your server script is absolute and that its dependencies are installed in the same Python environment as Bluerock.
ImportError when running python -m bluerock
Ensure you installed both the base and OSS packages: 'pip install bluerock[oss]'. If installing from wheels, install both the bluerock and bluerock_oss wheels. Verify with: python -c "import bluerock".
Frequently Asked Questions about Bluerock
What is Bluerock?
Bluerock is a Model Context Protocol (MCP) server that runtime visibility for python mcp servers. captures tool calls, session lifecycle, module imports (sha-256), and subprocess execution as structured ndjson. no code changes. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Bluerock?
Follow the installation instructions on the Bluerock GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Bluerock?
Bluerock works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Bluerock free to use?
Yes, Bluerock is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Bluerock Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to Bluerock? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.
Netdata
★ 78.9kReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Kubeshark
★ 11.9keBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Mission Control
★ 4.9kSelf-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Grafana
★ 3.0kThis MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.
Sentrux
★ 2.4kReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
OpenInference
★ 986OpenTelemetry Instrumentation for AI Observability
Browse More Monitoring & Observability MCP Servers
Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Bluerock in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Bluerock?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.