Claude Code Agent
An agentic MCP configuration server that solves the tool overload problem by dynamically spawning Claude Code subagents with only task-relevant MCP servers installed. Built by Tadas Antanavicius, it analyzes trusted server lists to identify relevant capabilities for specific tasks, then creates isolated Claude Code instances with custom system prompts and selective server configurations. The implementation provides 7 tools for complete subagent lifecycle management including initialization, server discovery and installation, chat delegation, transcript inspection, and cleanup, enabling users to scale to hundreds of trusted MCP servers without context window bloat by using specialized subagents equipped with only the tools needed for each specific task.
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
- ai-ml
- Source
- PulseMCP
- Author type
- human
- Updated
- 2026-04-29
Use via MCP
Resolve Claude Code Agent 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.