In-depth architectural comparison of the MCPSpend and MCP Server Health Monitor MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.
At a Glance & Executive Verdict
MCPSpend
Monitoring · Local stdio
Quality: 55/100 (Good) | Auth: API Key required
MCP Server Health Monitor
Monitoring · Local stdio
Quality: 49/100 (Fair) | Auth: No auth required
Verdict Summary: Choose MCPSpend if you need specialized Monitoring tools running via a local process. Choose MCP Server Health Monitor if your workspace requires Monitoring integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.
Which MCP Server Should You Choose?
Choose MCPSpend when:
You need dedicated capabilities in the Monitoring domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: API Key required (Freemium).
Primary tools included: Local stdio observability proxy, Per-tool and per-server usage attribution, MCP-based usage queries.
Real-time cost observability for MCP tool calls. Transparent proxy auto-detects every MCP client (Claude Desktop, Cursor, Windsurf, VS Code, Claude Code, Zed, Continue.dev, Cline, Goose) and attributes spend per tool, per project, per end-customer. npx @mcpspend/proxy add install. Free tier 25K calls/month, no card. MIT proxy on npm. EU-hosted, GDPR-ready.
Health monitoring for all your MCP servers
Category & Scope
Tools & Capabilities Breakdown
MCPSpend Tools (6)
Local stdio observability proxy
Per-tool and per-server usage attribution
MCP-based usage queries
Dashboard with sessions and CSV export
Metadata-only telemetry for tool calls
HTTP and stdio MCP access
MCP Server Health Monitor Tools (8)
health_check_all
probes all configured servers in parallel via `list_tools`, measures latency, and stores results. Accepts an optional `timeout_ms` parameter (default: 5000).
Ready-to-Paste Client Configurations
Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).
MCPSpend is categorized under Monitoring and uses a local stdio subprocess. In contrast, MCP Server Health Monitor belongs to Monitoring using local stdio subprocess. Select MCPSpend when you need capabilities focused on monitoring and MCP Server Health Monitor when you require tools for monitoring.
returns per-server detail including latency, last seen time, 24-hour error count, last error message, and p50/p95 latency percentiles. Requires `server_name`.
list_degraded
filters to servers that are offline or have latency above the threshold. Accepts an optional `latency_threshold` override.
get_history
returns raw health check history for a specific server, ordered most-recent first. Requires `server_name`; accepts optional `limit` (default: 50, max: 500).
configure_server
registers a new MCP server to monitor. Servers added this way are stored in `~/.mcp/extra-servers.json` and merged with auto-discovered servers. Required: `name`, `command`. Optional: `args`, `env`.
remove_server
removes a manually registered server from monitoring. Only affects servers added via `configure_server`; auto-discovered servers are not affected. Requires `name`.
check_updates
detects version drift by hashing tool schemas on each probe and comparing against the last stored hash. Returns `has_changed`, `previous_hash`, `current_hash`, and `changed_at` per server.
export_dashboard
generates a self-contained single-file HTML dashboard with summary cards, per-server status table with p50/p95 latency, and inline SVG uptime sparklines. Accepts an optional `output_path` to write to disk.