# sprocguard (pypi · sprocguard)

Safety net for SQL Server stored procedures: capture their behavior and verify changes.

- Trust score: 82/100 (high trust)
- Change this week: +19
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- pypi · `sprocguard`: 82/100 (this document), [markdown](https://verifymcp.io/servers/jheysonjhordyhuarauyariquelme-sprocguard/sprocguard.md), [page](https://verifymcp.io/servers/jheysonjhordyhuarauyariquelme-sprocguard/sprocguard)

## Channel facts

- Registry: `pypi`
- Package: `sprocguard`
- Version: `0.3.0`
- 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 2026-11-21.

- **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 29 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to JheysonJhordyHuarauyaRiquelme/sprocguard).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 6 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 520 tokens (~86/item across 6 items; 6 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 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 sprocguard MCP server?

sprocguard runs locally as a PyPI package, launched with uvx sprocguard serve. 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 jheysonjhordyhuarauyariquelme-sprocguard -- uvx sprocguard serve
```

### Cursor

```json
{
  "mcpServers": {
    "jheysonjhordyhuarauyariquelme-sprocguard": {
      "command": "uvx",
      "args": [
        "sprocguard",
        "serve"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "jheysonjhordyhuarauyariquelme-sprocguard": {
      "command": "uvx",
      "args": [
        "sprocguard",
        "serve"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add jheysonjhordyhuarauyariquelme-sprocguard -- uvx sprocguard serve
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add jheysonjhordyhuarauyariquelme-sprocguard --command uvx --arg sprocguard --arg serve
```

### Hermes

```yaml
mcp_servers:
  jheysonjhordyhuarauyariquelme-sprocguard:
    command: "uvx"
    args: ["sprocguard", "serve"]
```

### Netclaw

```json
{
  "McpServers": {
    "jheysonjhordyhuarauyariquelme-sprocguard": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "sprocguard",
        "serve"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add jheysonjhordyhuarauyariquelme-sprocguard -t stdio -c uvx -a sprocguard serve
```

### Other

```json
{
  "mcpServers": {
    "jheysonjhordyhuarauyariquelme-sprocguard": {
      "command": "uvx",
      "args": [
        "sprocguard",
        "serve"
      ]
    }
  }
}
```

## 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.

### 2026-11-21 (score 82, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-20 (score 66, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-19 (score 81, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-18 (score 65, −15)

- [security regression] Malware scan: pass → unverified

### 2026-11-17 (score 80, +6)

- [security improvement] Source repository: unverified → pass

### 2026-11-16 (score 74, +10)

- [security regression] Provenance: pass → unverified
- [security improvement] Malware scan: unverified → pass

### 2026-11-15 (score 64, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 63, +1)

- [functional improvement] Stability: unverified → 0.03
- [functional improvement] Security disclosure: fail → pass
- [functional] Package version: 0.1.1 → 0.3.0
- [functional] Package version: 0.1.1 → 0.2.0

## MCP tools (6)

### `inspect_procedure` (~77 tokens)

Describe a stored procedure: parameters, tables it reads and writes, procedures and
triggers involved, and risks (external side effects, dynamic SQL, nondeterminism).
Call this first. `procedure` is a name like 'dbo.usp_PlaceOrder'.

Input parameters:

- `include_definition` (boolean)
- `procedure` (string, required)

### `suggest_cases` (~52 tokens)

Suggest parameter values for test cases: real values found in related tables plus
edge values (0, -1, empty, NULL). Use them to design cases that cover every branch.

Input parameters:

- `procedure` (string, required)

### `capture_baseline` (~153 tokens)

Record what the procedure does TODAY, before you change it.
\`cases` is a list like [{"name": "customer with orders", "params": {"@CustomerId": 1}}].
Each case runs twice inside a rolled-back transaction; result sets, return value, OUTPUT
parameters, errors and table changes are saved to a baseline file. Values that change by
themselves (dates, new IDs) are detected and ignored later. `watch_tables` adds tables to
compare (useful with dynamic SQL). Refuses to replace an existing baseline unless overwrite=true.

Input parameters:

- `cases` (array, required)
- `overwrite` (boolean)
- `procedure` (string, required)
- `watch_tables`

### `verify_procedure` (~63 tokens)

Re-run the baseline cases against the procedure as it is now in the database and list
every difference in behavior. Run it after deploying your change to the development database.
An empty difference list for every case means the behavior is unchanged.

Input parameters:

- `procedure` (string, required)

### `generate_tsqlt_tests` (~51 tokens)

Turn the baseline into tSQLt tests (a .sql file) so the safety net can run in CI.
Version 0.1 supports read-only procedures.

Input parameters:

- `procedure` (string, required)

### `list_baselines` (~18 tokens)

List the procedures that already have a baseline.

Output parameters:

- `result` (array)

## Diagnostics

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

## Score history

- 2026-11-21: 82
- 2026-11-20: 66
- 2026-11-19: 81
- 2026-11-18: 65
- 2026-11-17: 80
- 2026-11-16: 74
- 2026-11-15: 64
- 2026-11-14: 63
- 2026-11-13: 62

## Common questions

### What is the sprocguard MCP server?

sprocguard is an MCP server listed in the public MCP registry as io.github.JheysonJhordyHuarauyaRiquelme/sprocguard. Safety net for SQL Server stored procedures: capture their behavior and verify changes. This page covers its PyPI package (sprocguard).

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

sprocguard scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 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 sprocguard MCP server expose?

sprocguard exposes 6 tools: inspect_procedure, suggest_cases, capture_baseline, verify_procedure, generate_tsqlt_tests, list_baselines. Their descriptions and schemas cost roughly 414 tokens of context every time the server is loaded.

### Is the sprocguard MCP server still maintained?

sprocguard is still listed as active in the MCP registry. We last reached this channel on 21 November 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 sprocguard MCP server under?

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

### What did VerifyMCP test on the sprocguard MCP server?

VerifyMCP ran 16 checks on sprocguard, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/sprocguard/
- Socket report: https://socket.dev/pypi/package/sprocguard
- Repository: https://github.com/JheysonJhordyHuarauyaRiquelme/sprocguard
- Changelog RSS feed: https://verifymcp.io/servers/jheysonjhordyhuarauyariquelme-sprocguard/sprocguard.xml
- Changelog JSON feed: https://verifymcp.io/servers/jheysonjhordyhuarauyariquelme-sprocguard/sprocguard/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/jheysonjhordyhuarauyariquelme-sprocguard/sprocguard.json
- HTML version of this page: https://verifymcp.io/servers/jheysonjhordyhuarauyariquelme-sprocguard/sprocguard
