SkillAgentSearch skills...

agent-safe-tools

Ask your AI coding agent, in natural language, to search production logs or inspect a database — safely. Two drop-in MCP servers (MySQL, SSH logs) keep safety red lines in code: read-only by default, dangerous SQL/shell blocked, production disabled, no stored credentials.

Install / Use

claude mcp add wangke-112 -- npx -y github:wangke-112/agent-safe-tools

If the server publishes to npm under a different name, use that package instead — check the repo README.

About this skill
🔌

MCP Server

Model Context Protocol server

Quality Score

76/100

Category

Security

Supported Platforms

Claude Code
Claude Desktop

Our assessment of agent-safe-tools

agent-safe-tools scores 76/100 on our quality scale, 1023rd of 1,111 Security skills we index.

Its MCP Server is 3.3 KB long, well organised into 10 sections with 3 code examples: a solid amount of guidance for an agent.

It has 3 GitHub stars, so there is little community track record yet; judge it on its content.

Substance
26/30
Structure
18/20
Description
15/15
Adoption
3/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so agent-safe-tools is actively maintained.
  • Our last check on 2026-11-12 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 92/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

agent-safe-tools compared with similar skills

All 4 of these similar skills score higher than agent-safe-tools; compare them before choosing.

SkillScoreStarsUpdatedFormat
agent-safe-tools (this skill)by wangke-11276345d agoMCP Server
claude-memby thedotmack100117.6ktodayCLAUDE.md
Agent-Reachby Panniantong100112.3k9d agoCLAUDE.md
rufloby ruvnet10081.9ktodayCLAUDE.md
headroomby headroomlabs-ai10079.8ktodayCLAUDE.md

Frequently asked questions

How do I install agent-safe-tools?
Run claude mcp add wangke-112 -- npx -y github:wangke-112/agent-safe-tools. The install tabs above show the steps for each supported agent.
Which AI agents does agent-safe-tools work with?
It is written for Claude Code and Claude Desktop, as a MCP Server file. Other agents that read the same format can often use it too.
Is agent-safe-tools safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 92/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is agent-safe-tools still maintained?
The repository was last updated about 2 months ago, so agent-safe-tools is actively maintained.

agent-safe-tools

CI License: MIT Python

Ask your AI coding agent, in natural language, to search production logs or inspect a database — safely. Works with any MCP-capable host (Codex, Claude Code, OpenCode, Cursor, ...).

Core idea: keep the safety red lines in code, not in a prompt. Instead of trusting the model to obey instructions, the limits are enforced by validation and covered by unit tests.

English | 简体中文

Packages

| Package | Description | Install | |---|---|---| | safe-mysql-mcp | Read-only-by-default MySQL MCP server with SQL guardrails | pip install -e ./safe-mysql-mcp | | ssh-logs-mcp | Read-only remote log inspection MCP server with a code-enforced command allowlist | pip install -e ./ssh-logs-mcp |

The two packages are independent and can also be published as separate repositories.

Each package's core is an MCP server; it also ships a skill/ layer that is recommended to install on skill-capable hosts (Codex / Claude Code), so the model knows when and how to call the tools.

Quick start

git clone https://github.com/wangke-112/agent-safe-tools.git
cd agent-safe-tools

# MySQL (read-only)
pip install -e ./safe-mysql-mcp
export MYSQL_HOST=127.0.0.1 MYSQL_USER=readonly_user MYSQL_PASSWORD=****** MYSQL_DATABASE=app
safe-mysql-mcp

# Remote logs (read-only)
pip install -e ./ssh-logs-mcp
export SSH_LOGS_CONFIG=~/.config/ssh-logs-mcp/servers.json
ssh-logs-mcp

Host integration snippets (Codex / Claude Code / OpenCode / Cursor) are in each package README.

Repository layout

agent-safe-tools/
├── safe-mysql-mcp/
│   ├── src/safe_mysql_mcp/     # guard / config / db / server
│   ├── examples/               # profiles and MCP config templates
│   └── tests/                  # SQL guardrail tests (pure functions, no DB)
├── ssh-logs-mcp/
│   ├── src/ssh_logs_mcp/       # policy / config / transport / server
│   ├── examples/               # servers.json template
│   └── tests/                  # command policy tests (no SSH)
└── .github/workflows/ci.yml    # CI across multiple Python versions

Why "safe"

Letting an agent connect straight to production databases or run remote shell commands is risky. Most existing MCP servers only handle "connecting" and leave safety to the model's prompt. This project encodes the limits:

  • Read-only by default, DDL / dangerous statements blocked, LIMIT injected automatically, writes must carry a WHERE clause;
  • Command allowlist, no ; / && / redirects / backticks / $(), no path traversal;
  • Production disabled by default and must be enabled explicitly;
  • Credentials only via environment variables or local config files, never committed.

All of these rules are pure functions with unit tests.

Tests

# Run each package separately (they are independent)
cd safe-mysql-mcp && pip install -e ".[dev]" && pytest
cd ../ssh-logs-mcp && pip install -e ".[dev]" && pytest

License

MIT

Related Skills

View on GitHub
GitHub Stars3
CategorySecurity
Updated1mo ago
Forks0

Languages

Python

Trust signals

92/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 low