Claude Code
Wraps Anthropic's Claude Code agent SDK to enable task delegation from MCP clients to Claude Code sessions. Built by egoist using TypeScript and the Claude Agent SDK, it exposes a single task tool that accepts natural language descriptions of coding work, working directory paths, and optional session IDs for continuity. The implementation streams Claude Code execution with automatic edit permissions, restricts tool access to a curated set (WebSearch, WebFetch, Bash, Edit, Glob, Grep, TodoWrite, Write), and returns structured results with session tracking and cost metrics.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/egoist/claude-code-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via 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 --scope user for --scope project to commit it to .mcp.json.