Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"pcp": {
"args": [
"pcp-mcp"
],
"command": "uvx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
MCP server for Performance Co-Pilot (PCP) metrics.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
uvx 'pcp-mcp' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked pcp-mcp against OSV.dev.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in devops / analytics
MCP server for using the GitLab API
MCP Server for GCP environment for interacting with various Observability APIs.
Enhanced MCP server for GitLab: group projects listing and activity tracking
Yunxiao MCP Server provides AI assistants with the ability to interact with the Yunxiao platform. It provides a set of tools that interact with Yunxiao's API, allowing AI assistants to manage Codeup repository, Project, Pipeline, Packages etc.
MCP Security Weekly
Get CVE alerts and security updates for io.github.major/pcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
MCP server for Performance Co-Pilot (PCP) metrics.
Query system performance metrics via the Model Context Protocol - CPU, memory, disk I/O, network, processes, and more.
📖 Full Documentation | 🚀 Getting Started
Run immediately with uvx — no installation required:
uvx pcp-mcp
Or install as a persistent global tool:
uvx tool install pcp-mcp
pcp-mcp
pip install pcp-mcp
Or with uv:
uv add pcp-mcp
pmcd and pmproxy running
# Fedora/RHEL/CentOS
sudo dnf install pcp
sudo systemctl enable --now pmcd pmproxy
# Ubuntu/Debian
sudo apt install pcp
sudo systemctl enable --now pmcd pmproxy
Configure via environment variables:
| Variable | Description | Default |
|---|---|---|
PCP_HOST | pmproxy host | localhost |
PCP_PORT | pmproxy port | 44322 |
PCP_TARGET_HOST | Target pmcd host to monitor | localhost |
PCP_USE_TLS | Use HTTPS for pmproxy | false |
PCP_TLS_VERIFY | Verify TLS certificates | true |
PCP_TLS_CA_BUNDLE | Path to custom CA bundle | (optional) |
PCP_TIMEOUT | Request timeout (seconds) | 30 |
PCP_USERNAME | HTTP basic auth user | (optional) |
PCP_PASSWORD | HTTP basic auth password | (optional) |
PCP_ALLOWED_HOSTS | Hostspecs allowed via host param | (optional) |
pcp-mcp
PCP_TARGET_HOST=webserver1.example.com pcp-mcp
Or use the CLI flag:
pcp-mcp --target-host webserver1.example.com
PCP_HOST=metrics.example.com pcp-mcp
pcp-mcp --transport sse
Add to ~/.config/claude/claude_desktop_config.json:
{
"mcpServers": {
"pcp": {
"command": "uvx",
"args": ["pcp-mcp"]
}
}
}
For remote monitoring:
{
"mcpServers": {
"pcp": {
"command": "uvx",
"args": ["pcp-mcp", "--target-host", "webserver1.example.com"]
}
}
}
💡 Using
uvxmeans you don't need pcp-mcp installed — it runs directly from PyPI.
get_system_snapshot - Point-in-time system overview (CPU, memory, disk, network, load)get_process_top - Top processes by CPU, memory, or I/O usagequery_metrics - Fetch current values for specific PCP metricssearch_metrics - Discover available metrics by name patterndescribe_metric - Get detailed metadata about a metric"What's the current CPU usage?"
→ Uses get_system_snapshot
"Show me the top 10 processes by memory usage"
→ Uses get_process_top(sort_by="memory", limit=10)
"What metrics are available for network traffic?"
→ Uses search_metrics(pattern="network")
"Get detailed info about kernel.all.load"
→ Uses describe_metric(name="kernel.all.load")
Ask Claude to: