pulsemcp Safe content atomic mcp-remote

Claude Code

Claude Code MCP Server provides a streamlined interface for executing Claude Code CLI commands with permissions automatically bypassed. Developed by Peter Steinberger, it exposes a single powerful 'claude_code' tool that enables AI assistants to perform complex coding tasks including file operations, Git commands, web searches, and multi-step workflows without permission interruptions. The server intelligently parses 'Your work folder is...' directives to set the current working directory, handles timeouts gracefully, and supports both Windows and Unix environments. It's particularly valuable for developers who need Claude to execute direct, complex coding operations that standard MCP implementations might struggle with due to permission constraints.

Cognium trust score
50%
Tier
Unverified

Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.

View full trust & usage report →

Metadata

Version
1.0.0
Skill type
atomic
Execution layer
mcp-remote
Category
version-control
Source
PulseMCP
Author type
human
Updated
2026-04-25
View source Find related skills

Use via MCP

MCP

Resolve Claude Code from your agent

Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.

One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.

claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
Swap --scope user for --scope project to commit it to .mcp.json.

Search SkillsRegistry