shinpr/sub-agents-mcp — Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.

Description and use

shinpr/sub-agents-mcp is an open‑source framework that lets developers describe task‑specific AI sub‑agents using simple Markdown files, which are then automatically translated into executable agents for any MCP‑compatible tool. By separating agent definitions from code, the project streamlines the creation, orchestration, and deployment of specialized AI components across crypto, orchestration, and broader AI/ML workflows.

Problem

shinpr/sub-agents-mcp helps turn isolated prompts and tools into repeatable agent workflows.

Outcome

Medium: useful for prototypes or internal workflows, with dependency and maintenance checks before production.

Workflow

• coordinate multi-agent workflows
• add tool-use pipelines
• standardize agent memory

Evidence

Define task-specific AI sub-agents in Markdown for any MCP-compatible tool.

Source