coding-tools-mcp
Give any AI agent the ability to code
No outside reports on file
Giving an AI direct code execution is very powerful but risky—a trick in the wrong prompt or a confused AI decision could cause real damage to your system or data.
Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsNo API token requiredLOW
- Package sourceGitHub (xyTom/coding-tools-mcp)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
No npm or PyPI package is listed. Install from source: github.com/xyTom/coding-tools-mcp ↗
About Coding Tools MCP
This tool lets AI agents write and run code on a computer. It appears to give Claude or other AI models the ability to execute code directly, which could mean writing files, running scripts, or testing programs.
Who it’s for
Developers who want AI assistants to help write, test, or debug code as part of an automated workflow. It's designed for people comfortable giving an AI agent access to run code on their system.
Alternatives
- E2B Sandbox: Runs code in an isolated sandbox environment rather than directly on your machine.
- LangChain Code Execution: Provides safer code-running integrations with built-in guardrails.
- Anthropic's Artifacts: Claude writes code for you to review and run yourself instead of auto-executing.
- GitHub Copilot: Suggests code without directly executing it on your system.
Setup
Check these steps against the project’s own instructions before running anything.
Follow the project's README for setup instructions at https://github.com/xyTom/coding-tools-mcp (opens external site)
Why this grade
Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 1.2k
- Listing last refreshed
- 2026-10-28
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Security reports
No reports found for this package in our research (last checked 2026-10-29).
Risks to watch for
- Code execution: The AI can run any code it writes on your computer, including commands that delete files, steal data, or install malware.
- File system access: It can read and write files anywhere the user running it has permission to access.
- Prompt injection: Malicious text in files or web pages could trick the AI into running harmful code instead of helpful code.
- No human review: The AI might execute code without a person checking it first.
- Environment secrets: Code execution could access API keys, passwords, or other sensitive data stored in environment variables or config files.
How to lower the risk
Least-privilege permissions
- Run the AI agent with minimal file and folder access, not as an admin.
- Use a separate OS user account with limited permissions just for this tool.
Network isolation
- Consider running this on an air-gapped machine if handling sensitive work.
- Restrict outbound network access if the code execution doesn't need internet.
Monitoring
- Watch what code the AI tries to run before it executes.
- Log all commands and file changes for review.
Red flags to watch for
- The AI tries to delete, modify, or access files outside the intended scope.
- Code includes commands to fetch or run scripts from the internet.
- The AI executes code without being asked to do so.
Questions
How do I install Coding Tools MCP?
Coding Tools MCP does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/xyTom/coding-tools-mcp.
Are there security reports about Coding Tools MCP?
No reports found for this package in our research (last checked 2026-10-29). Coding Tools MCP currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include code execution, file system access, prompt injection.
Is Coding Tools MCP actively maintained?
Coding Tools MCP has 1.2k GitHub stars. Our directory data was last refreshed on 2026-10-28. Check recent commit activity, release tags, and open issues at github.com/xyTom/coding-tools-mcp before pinning it in production.
What are alternatives to Coding Tools MCP?
Notable alternatives to Coding Tools MCP include E2B Sandbox (Runs code in an isolated sandbox environment rather than directly on your machine), LangChain Code Execution (Provides review code-running integrations with built-in guardrails), Anthropic's Artifacts (Claude writes code for you to review and run yourself instead of auto-executing), GitHub Copilot (Suggests code without directly executing it on your system). You can also compare Coding Tools MCP side by side with other MCP servers in the Related tools section on this page.
README badge and team notes
Maintain or use Coding Tools MCP? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.
GitHub README Markdown:
[](https://agentarmorhq.com/skills/xytom-coding-tools-mcp)HTML embed:
<a href="https://agentarmorhq.com/skills/xytom-coding-tools-mcp"><img src="https://agentarmorhq.com/api/badge/xytom-coding-tools-mcp" alt="AgentArmorHQ Risk Grade for Coding Tools MCP" height="20" /></a>Terminal check:
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "xytom-coding-tools-mcp"Share with your security lead
Need sign-off to use coding-tools-mcp? Copy this note for Slack, a ticket or a pull request.
### AgentArmorHQ Security Review Memo: coding-tools-mcp
- **Listing URL:** https://agentarmorhq.com/skills/xytom-coding-tools-mcp
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 1.2k GitHub stars
#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (xyTom/coding-tools-mcp)
#### Recommended Hardened Setup
- **Source Repo:** https://github.com/xyTom/coding-tools-mcp
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.
_Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee._Key facts
- Type
- App connector
- Publisher
- xyTom
- Source code
- github.com/xyTom/coding-tools-mcp
- Est. context load
- ~1.2k tokens / turn (~7 tool schemas, 0.57% of 200k context)
- Popularity
- 1.2k GitHub stars
- Last updated
- 2026-10-28
- Last graded
- 2026-10-22
Community
Discussions for Coding Tools MCP
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude