LocalFree server, account needed

Spanlens MCP server

spanlens/Spanlens

Query Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.

13 GitHub stars1 forks
Source code

Install Spanlens in Claude Code

Claude Code
claude mcp add spanlens-spanlens -e SPANLENS_API_KEY=... -- npx -y @spanlens/mcp-server
mcp.json (Claude Desktop, Cursor, VS Code, Windsurf)
{
  "mcpServers": {
    "spanlens-spanlens": {
      "command": "npx",
      "args": [
        "-y",
        "@spanlens/mcp-server"
      ],
      "env": {
        "SPANLENS_API_KEY": "..."
      }
    }
  }
}

Replace each ... with your own value.

Frequently asked questions

What does the Spanlens MCP server do?

Query Spanlens LLM observability from Cursor, Claude Desktop, or Continue via MCP.

Is the Spanlens MCP server free?

The server is free, but you will likely need an account. The server itself is free, but it connects to a service that needs an account or API key, which may have paid tiers. Check the provider for current pricing.

Does Spanlens run locally or remotely?

Local. Runs on your machine (stdio). You install it with npx, uvx, Docker or from source.

How do I add Spanlens to Claude Code?

Run: claude mcp add spanlens-spanlens -e SPANLENS_API_KEY=... -- npx -y @spanlens/mcp-server

More monitoring & observability MCP servers

View all

Synology NAS

13

cmeans/mcp-synology

MCP server for Synology NAS — browse files, monitor health, and automate operations

LocalFree

Spanlens

13

spanlens/Spanlens/mcp-server

Read-only access to Spanlens LLM observability: request logs, costs, agent traces, anomalies, model savings and per-user analytics.

LocalAccount neededTypeScript

Talos Linux

4251

Nosmoht/talos-mcp-server

MCP server for Talos Linux — resources, services, logs, health, config, lifecycle via gRPC.

LocalFree

Koru Shield

1385

KoruShield/koru-shield-mcp

Manage Koru Shield DNS filtering: profiles, rules, categories, schedules, and logs.

Local + RemoteAccount needed

LLM Latency Tracker

12

mazamaka/llm-latency-tracker

Measured latency, time to first token and uptime for ~45 AI inference APIs, by region.

RemoteAccount needed

Netassist

2370

Edge-Echo/mcp-netassist

Network and proxy diagnostics: GitHub reachability, system proxy status, local proxy port probing, DNS/TCP/HTTP checks, hosts conflict scan, and a doctor that suggests what to change.

LocalFreeTypeScript