pulsemcp verified Safe content atomic mcp-remote

SuperAgent

SuperAgent MCP server orchestrates Codex and Gemini CLI agents with parallel execution support, enabling delegation of complex tasks to specialized programming agents. Built by SuperClaude Org, it provides two main tools for running multiple prompts concurrently across different working directories, with Codex offering full system access and comprehensive permissions while Gemini runs in auto-approval YOLO mode. The implementation includes a library of 16 specialized agent personas (backend architect, security engineer, python expert, etc.) that can be invoked to apply domain-specific expertise, making it valuable for complex development workflows, code analysis, system architecture tasks, and scenarios where different types of technical expertise need to be applied simultaneously across multiple projects or contexts.

Cognium trust score
95%
Tier
Verified

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 2026-09-19.

Scan details: Circle-IR · 2026-09-19 · Appeal

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
Last scanned
2026-09-19
Updated
2026-09-19
View source Find related skills

Use via MCP

MCP

Resolve SuperAgent 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