claude-code-mcp

Name: claude-code-mcp Review
Item: claude-code-mcp
Rating: 2.8
Author: Aaron Matthews

Connector Development Usable

Works inClaude Code Claude Cowork Claude Chat

Usable Scanned — metadata only

Enables Claude to execute and validate code locally within secure environments, reducing context switching between AI assistance and development tooling whil…

MCP Server connects with claude code local command.

Execute code snippets locally and get real-time results without leaving Claude
Debug Python scripts by running them against test data and examining output
Validate SQL queries directly against your database before deploying to production

34 starsMIT (commercial OK)FreeNo code needed

Usable rating — This tool is functional but has notable gaps. Review the evaluation notes below before deploying.

Why it matters

Enables Claude to execute and validate code locally within secure environments, reducing context switching between AI assistance and development tooling while maintaining control over code execution.

Best for

Development teams using Claude for pair programming who need real-time code execution and testing without leaving the conversation interface.

Works in

Claude Code Claude Cowork Claude Chat

Source

https://github.com/KunihiroS/claude-code-mcp

By KunihiroS

How to Get It

Option 1: Claude Desktop AppOpen the Customize panel in the sidebar → browse connectors → search and add. Works in Claude Code, Claude Cowork, and Claude Chat.

Option 2: Paste into Claude CodeCopy the command below and paste it into a Claude Code conversation. Claude will run it for you.

Command

claude mcp add claude-code-mcp -- npx -y claude-code-mcp

Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.

Auto-generated from the tool's public listing — not hands-on verified. Cross-check against the source repo's README before running.

First thing to try

Once it’s connected, paste this into Claude:

Help me execute code snippets locally and get real-time results without leaving Claude

CostFree

Trust Signals Auto-scanned

Stars34Last updated2026-08-25LicenseMIT (OK for commercial use)Known CVEsNone foundSources: GitHub Advisory Database + OSV.dev · Scanned 2026-08-25 · scanner v1

Data & Access

Data processingPrompts sent to Anthropic API. Enterprise/Team plans exclude training.

Community Pulse New

Claude Code's MCP config can silently orphan Docker containers — Hacker News · 8 pts
Ask HN: What public Claude Code MCPs, Skills do you have installed and use? — Hacker News · 7 pts
Show HN: Persistent Memory for Claude Code (MCP) — Hacker News · 7 pts

3 mentions across 1 sources

Reviewer notes

Auto-scanned review. These are observations, not a security certification.

Scored from trust signals (evidence-eval-v1): 34 GitHub stars; contributors unknown; last commit 0d ago; license MIT.

Things to check

Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.

How to evaluate tools before deploying →

Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.

Evaluation Scores

Evaluation

Ease of Use

3/5

Versatility

2/5

Reliability

3/5

Security

3/5

Overall score2.75 / 5.00 UsableEvaluatedAug 2026

Scored from trust signals (evidence-eval-v1): 34 GitHub stars; contributors unknown; last commit 0d ago; license MIT.

← Back to the Claude Observatory