MCP server
SpanHound
io.github.abhishekash/spanhound
Checked 25 Oct 2026, 21:11 UTC · Still published on its registry; checked against OSV.dev; never run by us
Capture local agent traces and inspect failures, approvals, and run comparisons.
Runs on your computer
At a glance
- Type
- MCP server
- Publisher
- Not verified
- Status
- Runs on your computer
- Sets up in
- Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code
- Last checked
- 25 Oct 2026, 21:11 UTC
Connect it to your agent
Opens the app, which shows the server and asks you to confirm. It then runs the package on your computer with your permissions. For other apps, copy the setup below.
Claude Code
claude mcp add spanhound -- uvx spanhound@0.6.1
Claude Desktop
{"mcpServers":{"spanhound":{"command":"uvx","args":["spanhound@0.6.1"]}}}
Codex (config.toml)
[mcp_servers.spanhound] command = "uvx" args = ["spanhound@0.6.1"]
Gemini CLI
{"mcpServers":{"spanhound":{"command":"uvx","args":["spanhound@0.6.1"]}}}
Cursor
{"mcpServers":{"spanhound":{"command":"uvx","args":["spanhound@0.6.1"]}}}
VS Code
{"servers":{"spanhound":{"type":"stdio","command":"uvx","args":["spanhound@0.6.1"]}}}
Runs on your computer with your permissions: check the package and its source before installing.
Browse
Related MCP servers
- DocVerdict
PDF, photo, email, and file comparison evidence checks with plain-language reports. - CutGPT Research & Fact-Check
Free fact-checks, papers, source vetting, plus verified AI pricing, comparisons, guides, and tools. - AI SENSE Free Public Tools
66 public tools: semantic search, queues, inboxes, webhooks, approvals, DNS, images, PDF and more. - Snapback
Diagnose why an AI agent failed and get the verified fix instantly. Free, no token. - KANONYR publication checks
Before/after page checks: EUR 2 or USD 2. Free inspection, eligible repairs and audits. - ZeroWidth Caliper
Build datasets and rubrics, then run evals that score your AI in Caliper. - Rapier - Markdown Editor & Art
Markdown editor for writing, notes, editable diagrams, drawing and painting with your AI assistant. - Codemind
Hand routine JS/TS tasks to Codemind from your agent. $0.10 per verified build; failures are free.
Badge for your README
[](https://aptlynx.net/servers/io.github.abhishekash/spanhound)
Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents