# SpanHound (pypi · spanhound)

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

- Trust score: 80/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-23

## Components

- pypi · `spanhound`: 80/100 (this document), [markdown](https://verifymcp.io/servers/abhishekash-spanhound/spanhound.md), [page](https://verifymcp.io/servers/abhishekash-spanhound/spanhound)

## Channel facts

- Registry: `pypi`
- Package: `spanhound`
- Version: `0.6.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-23.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 30 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to abhishekash/spanhound).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 7 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 57/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 570 tokens (~47/item across 12 items; 12 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the SpanHound MCP server?

SpanHound runs locally as a PyPI package, launched with uvx spanhound. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add abhishekash-spanhound -- uvx spanhound
```

### Cursor

```json
{
  "mcpServers": {
    "abhishekash-spanhound": {
      "command": "uvx",
      "args": [
        "spanhound"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "abhishekash-spanhound": {
      "command": "uvx",
      "args": [
        "spanhound"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add abhishekash-spanhound -- uvx spanhound
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "abhishekash-spanhound": {
      "type": "local",
      "command": [
        "uvx",
        "spanhound"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add abhishekash-spanhound --command uvx --arg spanhound
```

### Hermes

```yaml
mcp_servers:
  abhishekash-spanhound:
    command: "uvx"
    args: ["spanhound"]
```

### Netclaw

```json
{
  "McpServers": {
    "abhishekash-spanhound": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "spanhound"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add abhishekash-spanhound -t stdio -c uvx -a spanhound
```

### Other

```json
{
  "mcpServers": {
    "abhishekash-spanhound": {
      "command": "uvx",
      "args": [
        "spanhound"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-23 (score 80, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-22 (score 64, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-21 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-19 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-16 (score 76, +42)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Injection markers: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.07
- [functional improvement] MCP protocol: unverified → pass

### 2026-10-15 (score 34, −41)

- [security regression] Malware scan: pass → unverified
- [security regression] Tool safety: pass → unverified
- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] Package version: 0.6.0 → 0.6.1

### 2026-10-14 (score 75, +26)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Tool coverage: 0
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fair
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 100

## MCP tools (12)

### `list_runs` (~45 tokens)

List recent agent runs: task, model, duration, tool use, human decisions, cost.

Use first to find the trace_id for deeper inspection.

Input parameters:

- `limit` (integer)

Output parameters:

- `result` (string)

### `run_summary` (~28 tokens)

Compact summary of one run (accepts trace_id prefix).

Input parameters:

- `trace_id` (string, required)

Output parameters:

- `result` (string)

### `span_tree` (~34 tokens)

Nested span tree of a run — the shape of what the agent did, with durations.

Input parameters:

- `trace_id` (string, required)

Output parameters:

- `result` (string)

### `slowest_spans` (~48 tokens)

Top-k slowest spans. Use for 'why was this run slow?'. Omit trace_id to search all runs.

Input parameters:

- `k` (integer)
- `trace_id`

Output parameters:

- `result` (string)

### `approval_log` (~54 tokens)

Human-in-the-loop audit: every approval/denial/edit, who decided, and the rationale.

Use when asked 'why did the agent get to do X?' or 'what was denied?'.

Input parameters:

- `trace_id`

Output parameters:

- `result` (string)

### `token_usage` (~29 tokens)

Token and cost totals. Omit trace_id to aggregate across all runs.

Input parameters:

- `trace_id`

Output parameters:

- `result` (string)

### `search_spans` (~46 tokens)

Substring search over span names/attributes, e.g. a tool name, file path, or 'denied'.

Input parameters:

- `needle` (string, required)
- `trace_id`

Output parameters:

- `result` (string)

### `failure_report` (~34 tokens)

Show bounded, redacted tool/provider failures and their actionable diagnostics.

Input parameters:

- `limit` (integer)
- `trace_id`

Output parameters:

- `result` (string)

### `tool_stats` (~45 tokens)

Rank tools by errors, denials, latency, and call volume to find unhealthy integrations.

Input parameters:

- `limit` (integer)
- `tool_name`
- `trace_id`

Output parameters:

- `result` (string)

### `security_audit` (~40 tokens)

Audit caller identity, tenant, server provenance, risk, and approval evidence for tool calls.

Input parameters:

- `limit` (integer)
- `trace_id`

Output parameters:

- `result` (string)

### `recent_activity` (~43 tokens)

Poll newly written spans using a cursor; useful while an agent run is still active.

Input parameters:

- `cursor`
- `limit` (integer)
- `trace_id`

Output parameters:

- `result` (string)

### `compare_runs` (~33 tokens)

Compare selected trace-id prefixes for latency, cost, tokens, tools, and failures.

Input parameters:

- `trace_ids` (array, required)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/abhishekash-spanhound/spanhound#diagnostics

## Score history

- 2026-10-23: 80
- 2026-10-22: 64
- 2026-10-21: 79
- 2026-10-20: 78
- 2026-10-19: 78
- 2026-10-18: 77
- 2026-10-17: 77
- 2026-10-16: 76
- 2026-10-15: 34
- 2026-10-14: 75
- 2026-10-13: 49

## Common questions

### What is the SpanHound MCP server?

SpanHound is an MCP server listed in the public MCP registry as io.github.abhishekash/spanhound. Capture local agent traces and inspect failures, approvals, and run comparisons. This page covers its PyPI package (spanhound).

### Is the SpanHound MCP server safe to use?

SpanHound scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 23 October 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the SpanHound MCP server expose?

SpanHound exposes 12 tools: list_runs, run_summary, span_tree, slowest_spans, approval_log, and 7 more. Their descriptions and schemas cost roughly 479 tokens of context every time the server is loaded.

### Is the SpanHound MCP server still maintained?

SpanHound is still listed as active in the MCP registry. We last reached this channel on 23 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the SpanHound MCP server under?

SpanHound declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/spanhound/
- Socket report: https://socket.dev/pypi/package/spanhound
- Repository: https://github.com/abhishekash/spanhound
- Changelog RSS feed: https://verifymcp.io/servers/abhishekash-spanhound/spanhound.xml
- Changelog JSON feed: https://verifymcp.io/servers/abhishekash-spanhound/spanhound.json
- HTML version of this page: https://verifymcp.io/servers/abhishekash-spanhound/spanhound