What makes MSSQL notable?

1.1K downloads. Trust evidence available

How should MSSQL be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

MSSQL

Execute SQL Server queries and export results as delimiter-separated text. Use when the user asks to fetch, insert, update, or manage data in Microsoft SQL S... Skill: MSSQL Owner: 0xvespertine Summary: Execute SQL Server queries and export results as delimiter-separated text. Use when the user asks to fetch, insert, update, or manage data in Microsoft SQL S... Tags: latest:1.0.2 Version history: v1.0.2 | 2026-04-04T16:57:41.465Z | user v1.0.2 — Declare required env vars in metadata - Added MSSQL_HOST, MSSQL_DB, MSSQL_USER, MSSQL_PASSWORD to requires.env - Fixes manifest/met

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.0.2

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.2release · observed Apr 4, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1741t73nrt7q2vnxcrxcxxtjh83hfew:mssql

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-0xvespertine-mssql/snapshot"

Documentation

CLAWHUB

14,781 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: mssql
version: 1.0.2
description: Execute SQL Server queries and export results as delimiter-separated text. Use when the user asks to fetch, insert, update, or manage data in Microsoft SQL Server, validate BI/reporting numbers, or prepare datasets for charts.
metadata: { "openclaw": { "emoji": "DB", "requires": { "bins": ["sqlcmd"], "env": ["MSSQL_HOST", "MSSQL_DB", "MSSQL_USER", "MSSQL_PASSWORD"] } } }
---

# MSSQL

Run SQL Server queries using `scripts/mssql_query.sh`.

## Quick start

1. Ensure credentials exist at:
   `~/.openclaw/credentials/mssql.env`
2. Run a query:
   `bash skills/mssql/scripts/mssql_query.sh --query "SELECT TOP 20 name FROM sys.tables"`
3. Save to file:
   `bash skills/mssql/scripts/mssql_query.sh --query "SELECT TOP 100 * FROM dbo.MyTable" --out /tmp/mytable.dsv`

## Credentials format

Expected env vars in `~/.openclaw/credentials/mssql.env`:

- `MSSQL_HOST`
- `MSSQL_DB`
- `MSSQL_USER`
- `MSSQL_PASSWORD`
- Optional: `MSSQL_PORT` (default `1433`), `MSSQL_ENCRYPT` (`yes`/`no`, default `yes`), `MSSQL_TRUST_CERT` (`yes`/`no`, default `no`), `SQLCMD_BIN`

The credential file path can be overridden with the `MSSQL_ENV_FILE` environment variable.

## Permissions

Query permissions are controlled entirely at the SQL Server user level. The script does not impose any restrictions on query type — the database user's grants determine what is allowed.

## Database reference map

Place your database map at `references/DB_MAP.md` inside this skill folder. This file tells the agent which databases, schemas, and tables to use and how they relate to each other.

See `references/DB_MAP.example.md` for the expected format.

## Useful patterns

- Run long query from file:
  `bash skills/mssql/scripts/mssql_query.sh --file /path/query.sql --out /tmp/out.dsv`
- Override database:
  `bash skills/mssql/scripts/mssql_query.sh --db OtherDB --query "SELECT TOP 10 * FROM dbo.Users"`
- Change delimiter:
  `bash skills/mssql/scripts/mssql_query.sh --query "SELECT ..." --delim ","`
- Increase timeout:
  `bash skills/mssql/scripts/mssql_query.sh --query "SELECT ..." --timeout 180`

## Output format

Output is **delimiter-separated text**, not RFC 4180 CSV. Fields are not quoted or escaped. This works well for structured numeric and short-text data. If your columns contain embedded delimiters, quotes, or newlines, the output may be malformed — choose a delimiter that does not appear in the data, or post-process the output.

## Best practices

- Prefer explicit columns over `SELECT *`.
- Use `TOP` for exploratory samples.
- Keep queries scoped to the user request.
- Answer in business language by default; provide SQL details when requested.
- Never print or expose credentials in responses.

## Troubleshooting

- `sqlcmd not found` -> install sqlcmd v18+ or set `SQLCMD_BIN`.
- TLS/certificate issues on internal networks -> set `MSSQL_TRUST_CERT=yes` in your credentials file. The default is `no` (certificate validation enabled).

_meta.json

{
  "ownerId": "kn71mmn1vst817r9622exn54vn83fw03",
  "slug": "mssql",
  "version": "1.0.2",
  "publishedAt": 1775321861465
}

references/DB_MAP.example.md

# DB MAP - YOUR_DATABASE_NAME

## Architecture
- Source database: `YOUR_SOURCE_DB` (description of role)
- Working database: `YOUR_WORKING_DB`
- `schema_a.*` = description of schema A
- `schema_b.*` = description of schema B
- `dbo.*` = final business-ready tables for reporting and analysis

## Tables to use
- `dbo.customers`
- `dbo.orders`
- `dbo.products`
- `dbo.invoices`
- `dbo.payments`
- `dbo.stock`

## Usage rules
- For routine business queries, use the final tables listed above first.
- Use other schemas only when debugging or when the final tables do not cover the need.
- Permissions are controlled at the database user level.

skill-card.md

## Description:

Execute SQL Server queries and export results as delimiter-separated text.

This skill is ready for commercial/non-commercial use.

## Publisher:

[0xvespertine](https://clawhub.ai/user/0xvespertine)

### License/Terms of Use:

MIT-0

## Use Case:

Developers, data analysts, and agents use this skill to query Microsoft SQL Server, validate reporting numbers, manage data when authorized, and prepare database result sets for analysis or charts.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill can run unrestricted SQL against the configured SQL Server according to the database user's grants.

Mitigation: Use a least-privilege SQL Server account, preferably read-only unless writes are required, and confirm insert, update, delete, schema, or administrative queries before execution.

Risk: The skill loads credentials and the sqlcmd binary from the local environment.

Mitigation: Install only in a trusted environment, restrict the credential file, trust the selected sqlcmd binary, and never expose credentials in responses.

Risk: Delimiter-separated output is not quoted or escaped, so embedded delimiters, quotes, or newlines can corrupt downstream parsing.

Mitigation: Choose a delimiter that does not appear in the data or post-process the output before using it in automated analysis.

## Reference(s):

- [DB_MAP.example.md](references/DB_MAP.example.md)
- [ClawHub MSSQL skill page](https://clawhub.ai/0xvespertine/skills/mssql)

## Skill Output:

**Output Type(s):** [Text, Files, Shell commands, Configuration]

**Output Format:** [Delimiter-separated text written to stdout or a .dsv file, with Markdown guidance for command usage]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Output is not RFC 4180 CSV; fields are not quoted or escaped.]

## Skill Version(s):

1.0.2 (source: frontmatter and server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.