SpanHound MCP Server

by abhishekash Your server? Claim it

local only

SpanHound runs on your own machine — the client starts it, so there is no endpoint to ping. 1 654 installs a week from pypi. Last commit 15 Oct 2026.

Capture local agent traces and inspect failures, approvals, and run comparisons.

Installs per day peak 1 076 · avg 55

a month agotoday

1 654

Installs / week

pypi · spanhound

Stars

0 open issues

15 Oct 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check SpanHound every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add spanhound -- uvx spanhound

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "spanhound": {
      "args": [
        "spanhound"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.spanhound]
command = "uvx"
args = ["spanhound"]

.cursor/mcp.json

{
  "mcpServers": {
    "spanhound": {
      "args": [
        "spanhound"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "spanhound": {
      "args": [
        "spanhound"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to SpanHound

same job, measured the same way

mcp-trace-inspector

by abhishekash

Read local agent-run JSONL traces through MCP for failures, approvals, and run comparisons.

1 113 installs/wk local only

The Context Company

by the-context-company

AI agent observability for production traces, natural-language insights, and improvement loops.

answering

Agentmark AI

by agentmark-ai

Inspect AgentMark traces and drive AgentMark Cloud: apps, experiments, metrics, deployments.

34 installs/wk local only

Shield Kya

by the-pixel-boys

Audit trail and traceability for AI agents. MCP gate: evaluate, ingest, request approval.

1 788 installs/wk local only

Marchward

by marchward

Runtime authority for AI agents: credential mediation, spend cap, approval gates, audit log.

38 installs/wk local only

Oldweb Logs

by palthainon

Offline log parsing, CI failures, HTTP capture analysis and bounded JSON configuration validation.

5 tools answering

agentguard

by agentwares

MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.

862 installs/wk local only

Trace Forge

by mdfifty50-boop

Structured execution trace and span logging for AI agents

28 installs/wk local only

SpanHound — questions

Answers built from our own checks of this server.

Why is there no uptime for SpanHound?

SpanHound runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package spanhound was installed 1 654 times last week.

How do I connect SpanHound?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls spanhound straight from pypi; nothing to host, nothing to sign up for.

How many people use SpanHound?

The pypi package spanhound was installed 1 654 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is SpanHound open source?

Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.