Install command
Not provided
Real-time MCP server monitoring statusline showing connected servers, active tools, and performance metrics for Claude Code MCP integration
Open the source and read safety notes before installing.
Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.
Decision playbook
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
0
78
—
No baseline selected
No major trust-signal divergence detected in the current selection.
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Source provenance statusRequired
Marked as source-backed.
Metadata reviewed
Registry metadata indicates a reviewed listing.
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Trust level risk gateRequired
Trust level does not block evaluation.
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Package verification flag
No package verification flag provided.
Checksum metadata
No checksum provided for downloaded artifact.
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
Baseline comparison available
No baseline peer selected yet.
Diverging trust signals identified
No major trust-signal divergence found.
Setup at a glance
Copy-ready — paste the snippet to get started.
Install command
Not provided
Config snippet
Provided
Copy snippet
Provided
Prerequisites
6 to clear
Platforms
1 listed
Difficulty
3/100
Adoption plan
Current risk score 16/100. Use staged verification before broader rollout.
Validate source and review signals before any execution.
Confirm source provenanceRequired
Source URL/provenance metadata is present.
Confirm metadata review state
Listing has review metadata.
Verify install payload
Install/config payload exists and can be inspected.
Confirm safety, privacy, and package integrity signals.
Review safety notesRequired
Safety notes are present.
Review privacy notesRequired
Privacy notes are present.
Verify package integrity metadata
No package verification/checksum metadata.
Adopt in controlled steps based on the selected plan.
Run in isolated sandbox firstRequired
Use a constrained sandbox and observe behavior across multiple tasks.
Roll out graduallyRequired
Roll out to a small cohort before wider usage.
Set monitoring and fallback
Define rollback path and monitor errors after adoption.
Evidence readiness
Required evidence gates are covered (5/6 signals complete).
Source repository/provenance is listed.
Required in this preset
Review metadata is present.
Required in this preset
Safety notes are present.
Required in this preset
Privacy notes are present.
Optional in this preset
Package integrity metadata is missing.
Optional in this preset
Install payload is available.
Required in this preset
Required evidence gates are covered for this preset.
Decision timeline
5/6 steps complete with no blocking gaps for this preset.
triage
Source/provenance metadata is available.
triage
Review metadata is available.
verify
Safety notes are available.
verify
Privacy notes are available.
verify
Package integrity metadata is missing.
rollout
Install payload is available.
No required blockers for this timeline preset.
Prerequisite readiness
6 prerequisites to line up before setup.
Safety & privacy surface
1 safety and 1 privacy notes across 1 risk area. Review closely: credentials & tokens.
#!/usr/bin/env bash
# MCP Server Status Monitor
# Shows connected MCP servers and active tools
read -r input
# Extract MCP server info (if available in Claude Code context)
mcp_servers=$(echo "$input" | jq -r '.mcp.servers // []' 2>/dev/null || echo "[]")
server_count=$(echo "$mcp_servers" | jq 'length' 2>/dev/null || echo "0")
# Count active tools across all servers
active_tools=0
for server in $(echo "$mcp_servers" | jq -r '.[] | @base64'); do
tools=$(echo $server | base64 -d | jq '.tools | length' 2>/dev/null || echo "0")
active_tools=$((active_tools + tools))
done
# Color based on server status
if [ "$server_count" -gt 0 ]; then
color="\033[32m" # Green - servers connected
icon="🔌"
else
color="\033[90m" # Gray - no servers
icon="⚫"
fi
# List server names
server_names=$(echo "$mcp_servers" | jq -r '.[].name' 2>/dev/null | tr '\n' ',' | sed 's/,$//')
# Output
if [ "$server_count" -gt 0 ]; then
echo -e "${icon} MCP ${color}${server_count}${color}\033[0m servers │ ${active_tools} tools │ ${server_names:0:30}"
else
echo -e "${icon} MCP ${color}disconnected${color}\033[0m"
fi{
"statusLine": {
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/statuslines/mcp-server-status-monitor.sh",
"refreshInterval": 2000
}
}{
"statusLine": {
"type": "command",
"command": "$CLAUDE_PROJECT_DIR/.claude/statuslines/mcp-server-status-monitor.sh",
"refreshInterval": 2000
}
}
Extended version checking individual server health and connection status
#!/usr/bin/env bash
# Enhanced MCP Server Status Monitor with Health Checks
input=$(cat)
mcp_servers=$(echo "$input" | jq -r '.mcp.servers // []' 2>/dev/null || echo "[]")
server_count=$(echo "$mcp_servers" | jq 'length' 2>/dev/null || echo "0")
active_tools=0
healthy_servers=0
unhealthy_servers=0
if [ "$server_count" -gt 0 ]; then
for server in $(echo "$mcp_servers" | jq -r '.[] | @base64'); do
decoded=$(echo "$server" | base64 -d 2>/dev/null || echo "{}")
tools=$(echo "$decoded" | jq '.tools | length // 0' 2>/dev/null || echo "0")
status=$(echo "$decoded" | jq -r '.status // "unknown"' 2>/dev/null || echo "unknown")
active_tools=$((active_tools + tools))
if [ "$status" = "connected" ] || [ "$status" = "healthy" ]; then
healthy_servers=$((healthy_servers + 1))
else
unhealthy_servers=$((unhealthy_servers + 1))
fi
done
fi
# Color based on server health
if [ "$unhealthy_servers" -gt 0 ]; then
color="\033[33m" # Yellow - some servers unhealthy
icon="⚠️"
elif [ "$server_count" -gt 0 ]; then
color="\033[32m" # Green - all servers healthy
icon="🔌"
else
color="\033[90m" # Gray - no servers
icon="⚫"
fi
server_names=$(echo "$mcp_servers" | jq -r '.[].name // empty' 2>/dev/null | tr '\n' ',' | sed 's/,$//')
if [ -n "$server_names" ] && [ ${#server_names} -gt 30 ]; then
server_names="${server_names:0:27}..."
fi
RESET="\033[0m"
if [ "$server_count" -gt 0 ]; then
health_info=""
if [ "$unhealthy_servers" -gt 0 ]; then
health_info=" (${unhealthy_servers} unhealthy)"
fi
if [ -n "$server_names" ]; then
echo -e "${icon} MCP ${color}${server_count}${RESET} servers${health_info} │ ${active_tools} tools │ ${server_names}"
else
echo -e "${icon} MCP ${color}${server_count}${RESET} servers${health_info} │ ${active_tools} tools"
fi
else
echo -e "${icon} MCP ${color}disconnected${RESET}"
fi
Version grouping tools by category for better organization
#!/usr/bin/env bash
# MCP Server Status Monitor with Tool Categories
input=$(cat)
mcp_servers=$(echo "$input" | jq -r '.mcp.servers // []' 2>/dev/null || echo "[]")
server_count=$(echo "$mcp_servers" | jq 'length' 2>/dev/null || echo "0")
active_tools=0
declare -A tool_categories
if [ "$server_count" -gt 0 ]; then
for server in $(echo "$mcp_servers" | jq -r '.[] | @base64'); do
decoded=$(echo "$server" | base64 -d 2>/dev/null || echo "{}")
tools=$(echo "$decoded" | jq '.tools | length // 0' 2>/dev/null || echo "0")
server_name=$(echo "$decoded" | jq -r '.name // "unknown"' 2>/dev/null || echo "unknown")
active_tools=$((active_tools + tools))
# Categorize by server name prefix
if [[ "$server_name" == *"filesystem"* ]] || [[ "$server_name" == *"file"* ]]; then
tool_categories["filesystem"]=1
elif [[ "$server_name" == *"git"* ]]; then
tool_categories["git"]=1
elif [[ "$server_name" == *"database"* ]] || [[ "$server_name" == *"db"* ]]; then
tool_categories["database"]=1
fi
done
fi
if [ "$server_count" -gt 0 ]; then
color="\033[32m"
icon="🔌"
else
color="\033[90m"
icon="⚫"
fi
categories_list=""
for category in "${!tool_categories[@]}"; do
if [ -z "$categories_list" ]; then
categories_list="$category"
else
categories_list="$categories_list,$category"
fi
done
server_names=$(echo "$mcp_servers" | jq -r '.[].name // empty' 2>/dev/null | tr '\n' ',' | sed 's/,$//')
if [ -n "$server_names" ] && [ ${#server_names} -gt 30 ]; then
server_names="${server_names:0:27}..."
fi
RESET="\033[0m"
if [ "$server_count" -gt 0 ]; then
if [ -n "$categories_list" ]; then
echo -e "${icon} MCP ${color}${server_count}${RESET} servers │ ${active_tools} tools │ ${categories_list}"
elif [ -n "$server_names" ]; then
echo -e "${icon} MCP ${color}${server_count}${RESET} servers │ ${active_tools} tools │ ${server_names}"
else
echo -e "${icon} MCP ${color}${server_count}${RESET} servers │ ${active_tools} tools"
fi
else
echo -e "${icon} MCP ${color}disconnected${RESET}"
fi
Complete setup script with MCP configuration verification
#!/bin/bash
# Installation script for MCP Server Status Monitor
# Check for jq (required for JSON parsing)
if ! command -v jq &> /dev/null; then
echo "Installing jq for JSON parsing..."
if [[ "$OSTYPE" == "darwin"* ]]; then
brew install jq
elif [[ "$OSTYPE" == "linux-gnu"* ]]; then
sudo apt-get install -y jq || sudo yum install -y jq
else
echo "Please install jq manually: https://stedolan.github.io/jq/"
fi
fi
# Check for base64 (usually available, but verify)
if ! command -v base64 &> /dev/null; then
echo "Warning: base64 command not found. Script may not work correctly."
echo "Install base64: macOS (usually pre-installed), Linux (coreutils package)"
fi
# Check MCP configuration
if [ -f ~/.mcp.json ]; then
echo "MCP configuration found: ~/.mcp.json"
echo "Verifying configuration..."
if jq empty ~/.mcp.json 2>/dev/null; then
echo "MCP configuration is valid JSON"
else
echo "Warning: MCP configuration may be invalid JSON"
fi
else
echo "Note: MCP configuration not found at ~/.mcp.json"
echo "MCP servers can be configured in ~/.mcp.json or via 'claude mcp add' command"
fi
# Test Unicode characters
if echo -e '🔌 ⚫ ⚠️' &> /dev/null; then
echo "Unicode characters supported"
else
echo "Warning: Unicode characters may not be supported in your terminal"
fi
mkdir -p .claude/statuslines
cat > .claude/statuslines/mcp-server-status-monitor.sh << 'SCRIPT_EOF'
#!/usr/bin/env bash
# MCP Server Status Monitor
# Shows connected MCP servers and active tools
read -r input
mcp_servers=$(echo "$input" | jq -r '.mcp.servers // []' 2>/dev/null || echo "[]")
server_count=$(echo "$mcp_servers" | jq 'length' 2>/dev/null || echo "0")
active_tools=0
if [ "$server_count" -gt 0 ]; then
for server in $(echo "$mcp_servers" | jq -r '.[] | @base64'); do
decoded=$(echo "$server" | base64 -d 2>/dev/null || echo "{}")
tools=$(echo "$decoded" | jq '.tools | length // 0' 2>/dev/null || echo "0")
active_tools=$((active_tools + tools))
done
fi
if [ "$server_count" -gt 0 ]; then
color="\033[32m"
icon="🔌"
else
color="\033[90m"
icon="⚫"
fi
server_names=$(echo "$mcp_servers" | jq -r '.[].name // empty' 2>/dev/null | tr '\n' ',' | sed 's/,$//')
if [ -n "$server_names" ] && [ ${#server_names} -gt 30 ]; then
server_names="${server_names:0:27}..."
fi
RESET="\033[0m"
if [ "$server_count" -gt 0 ]; then
if [ -n "$server_names" ]; then
echo -e "${icon} MCP ${color}${server_count}${RESET} servers │ ${active_tools} tools │ ${server_names}"
else
echo -e "${icon} MCP ${color}${server_count}${RESET} servers │ ${active_tools} tools"
fi
else
echo -e "${icon} MCP ${color}disconnected${RESET}"
fi
SCRIPT_EOF
chmod +x .claude/statuslines/mcp-server-status-monitor.sh
# Add to settings.json
if [ ! -f .claude/settings.json ]; then
echo '{"statusLine":{"type":"command","command":"$CLAUDE_PROJECT_DIR/.claude/statuslines/mcp-server-status-monitor.sh","refreshInterval":2000}}' > .claude/settings.json
else
jq '.statusLine = {"type":"command","command":"$CLAUDE_PROJECT_DIR/.claude/statuslines/mcp-server-status-monitor.sh","refreshInterval":2000}' .claude/settings.json > .claude/settings.json.tmp
mv .claude/settings.json.tmp .claude/settings.json
fi
echo "MCP Server Status Monitor installed successfully!"
echo "Note: MCP server status requires Claude Code to expose MCP context in statusline JSON"
echo "Verify MCP servers: claude mcp list"
echo "Add MCP server: claude mcp add --transport stdio server-name command"
Verify servers are actually connected: run 'claude mcp list' to check server status. Ensure servers are properly configured in ~/.mcp.json and restart Claude Code if needed. Check MCP context is available in statusline JSON: echo '$input' | jq .mcp. Verify Claude Code version supports MCP statusline API. Check server startup logs for errors.
Check that MCP context data is accessible. Verify Claude Code version supports MCP statusline API. Run 'claude mcp get [server-name]' to verify individual server status. Check if MCP context is exposed in statusline JSON: echo '$input' | jq .mcp.servers. Ensure servers are registered with Claude Code, not just running externally. Restart Claude Code to refresh MCP connections.
This indicates silent tool registration failure. Run '/mcp' in Claude Code to verify tool registration. Restart connected servers if tools remain unavailable despite connection. Check tool count calculation: for each server, verify tools array exists. Verify base64 decoding works: echo 'test' | base64 | base64 -d. Check jq parsing: echo '$input' | jq '.mcp.servers[0].tools | length'.
Launch with --mcp-debug flag. Check logs: ~/Library/Logs/Claude/mcp.log (macOS) or ~/.local/share/claude/mcp.log (Linux). Verify server.connect() is called and transport listener is active. Check server configuration in ~/.mcp.json. Verify server command is executable: which [server-command]. Test server manually: [server-command] --help.
Server may not support prompts/list or resources/list, or writes non-JSON to stdout. Ensure JSON-RPC 2.0 compliance. Use MCP Inspector for interactive testing. Check server implementation follows MCP protocol. Verify server stdout/stderr separation. Check for error messages in server logs.
Verify server name extraction: echo '$input' | jq '.mcp.servers[].name'. Check server name field exists in MCP context. Verify jq parsing works: echo '$input' | jq '.mcp.servers | length'. Check string truncation logic if names are too long. Verify tr and sed commands work: echo 'test\ntest' | tr '\n' ',' | sed 's/,$//'.
Verify base64 command is available: which base64. Test base64 encoding/decoding: echo 'test' | base64 | base64 -d (should return 'test'). Check base64 -d flag syntax (may vary by OS). Verify jq @base64 encoding works: echo '[{"name":"test"}]' | jq -r '.[] | @base64'. Add error handling for base64 decode failures.
Check JSON input is being read: echo '$input' | jq .. Verify mcp.servers field exists: echo '$input' | jq .mcp.servers. Check jq is installed: which jq. Verify MCP context is available in Claude Code statusline JSON (may require Claude Code version with MCP support). Check refreshInterval in settings.json is set to 2000ms or lower. Restart Claude Code to refresh MCP connections.
Show that MCP Server Status Monitor - Statuslines is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/statuslines/mcp-server-status-monitor)MCP Server Status Monitor - Statuslines side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | Real-time MCP server monitoring statusline showing connected servers, active tools, and performance metrics for Claude Code MCP integration Open dossier | A Claude Code statusline that reads the session JSON on stdin and splits total_duration_ms into API processing time versus network/waiting time (total minus API). Open dossier | Real-time burn rate monitor showing cost per minute, tokens per minute, and projected daily spend to prevent budget overruns during Claude Code sessions. Open dossier | Multi-provider AI performance dashboard with context occupancy tracking, truncation warnings, TTFT latency, tokens/min rate, and model comparison metrics. Open dossier |
|---|---|---|---|---|
| Next steps | ||||
| Trust | ||||
| Review status | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed | ReviewedMaintainer reviewed |
| Package trust | Package not verified | Package not verified | Package not verified | Package not verified |
| Source provenance | Source-backed | Source-backed | Source-backed | Source-backed |
| Submitter | — | — | — | — |
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Brand | — | — | — | — |
| Category | statuslines | statuslines | statuslines | statuslines |
| Source | source-backed | source-backed | source-backed | source-backed |
| Author | JSONbored | JSONbored | JSONbored | JSONbored |
| Added | 2025-10-16 | 2025-10-25 | 2025-10-25 | 2025-10-23 |
| Platforms | Claude Code | Claude Code | Claude Code | Claude Code |
| Source repo | — | — | — | — |
| Safety notes | ✓Runs as a Claude Code statusline command on every refresh and depends on the local shell environment; a failure only affects status rendering, not your session. | ✓Configured as a command-type statusline, so the script runs automatically on every status update. The Examples "Installation" script writes .claude/statuslines/api-latency-breakdown.sh and edits .claude/settings.json, and runs brew/apt-get/yum to install bc. | ✓Runs as a Claude Code statusline command on every refresh and depends on the local shell environment; a failure only affects status rendering, not your session. | ✓Runs as a Claude Code statusline command on every refresh and depends on the local shell environment; a failure only affects status rendering, not your session. |
| Privacy notes | ✓Reads the Claude Code statusline JSON from stdin (model, workspace path, token usage) and renders it in the local terminal; it does not send data off-machine. | ✓The Examples "Enhanced P95" variant appends every measured network time to /tmp/claude_latency_history.txt, leaving session timing data on disk until manually cleared. | ✓Reads the Claude Code statusline JSON from stdin (model, workspace path, token usage) and renders it in the local terminal; it does not send data off-machine. | ✓Reads the Claude Code statusline JSON from stdin (model, token usage, context occupancy) and renders it in the local terminal; it does not send data off-machine. |
| Prerequisites |
|
|
|
|
| Install | — | — | — | — |
| Config | | | | |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Source-backed guides for putting this to work.
Control MCP tool output size with env limits, annotations, and tool search to protect Claude Code context.
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.