mcpspan

mcpspan-mcp

Ask your AI agent about your MCP servers. Claude Code, Cursor or any other MCP client answers from your mcpspan numbers:

• Which tools failed most this week, and why?
• How does 1.4.1 compare with 1.4.0?
• What do agents ask for that my server does not have?
• Does Cursor fail more often than Claude?
• Which tools are agents shown but never call?

It reads with a token that sees what you see in the dashboard and changes nothing. It sends nothing anywhere but your mcpspan.

Try it on the demo

No account needed: the live demo answers any token. In Claude Code:

claude mcp add mcpspan-demo \
  -e MCPSPAN_READ_TOKEN=demo \
  -e MCPSPAN_URL=https://demo-api.mcpspan.com \
  -- npx -y mcpspan-mcp

Then ask about the demo's server, Flights: what went wrong in the last day?

Get a token

In mcpspan, open Settings → Read tokens and make one. It is shown once, already filled into the lines below, ready to copy.

Add it to your agent

mcpspan Cloud

Claude Code:

claude mcp add mcpspan -e MCPSPAN_READ_TOKEN=mcpspan_read_... -- npx -y mcpspan-mcp

Cursor, Claude Desktop, Windsurf and others, in their MCP settings:

{
  "mcpServers": {
    "mcpspan": {
      "command": "npx",
      "args": ["-y", "mcpspan-mcp"],
      "env": { "MCPSPAN_READ_TOKEN": "mcpspan_read_..." }
    }
  }
}

Self-hosted

The same, with the address your MCP servers report to:

claude mcp add mcpspan \
  -e MCPSPAN_READ_TOKEN=mcpspan_read_... \
  -e MCPSPAN_URL=http://localhost:6271 \
  -- npx -y mcpspan-mcp

{
  "mcpServers": {
    "mcpspan": {
      "command": "npx",
      "args": ["-y", "mcpspan-mcp"],
      "env": {
        "MCPSPAN_READ_TOKEN": "mcpspan_read_...",
        "MCPSPAN_URL": "http://localhost:6271"
      }
    }
  }
}

Needs mcpspan 0.9.0 or newer. If the agent reaches your installation over the internet, put HTTPS in front of it: the token travels with every question.

Settings

Variable
MCPSPAN_READ_TOKEN	The read token. Required.
MCPSPAN_URL	Your installation's API, for self-hosted mcpspan. https://api.mcpspan.com when left out.

Needs Node 20 or newer.

Tools

Every tool only reads. Each takes the server by name or id (left out when the account has one) and a window: days back from now (7 when left out), or from and to.

Tool	Answers
list_servers	The servers the account reports on.
get_overview	Calls, failures, error rate, response times and clients.
list_tools	Tools ranked by calls, errors, response time or name.
get_tool	One tool: why it failed, refused arguments, answer sizes, definition changes, repeats, and the call before each failure.
list_errors	The latest failed calls, with the kind of failure and the message.
list_unknown_tools	Tools agents asked for that the server lacks, the closest one it has, and what the agent did next.
list_clients	Each client's calls, error rate and response times.
compare_versions	The server's releases side by side.
get_tool_listing	What agents were shown: tools never used, and what their definitions cost.
list_sessions	Recent sessions, with failures and repeated calls.
get_session	One session's calls, in order.

A token can be revoked at any time under Settings → Read tokens; the agent loses access at once.

Licence

MIT