data-ai MCP Server
Governed execution layer for AI coding assistants: clarify intent, route capabilities, review evidence, verify results, and write back lessons across Claude Code, Codex, OpenClaw, and Cursor.
Discovered via github-topic:mcp and last synced 3mo ago.
1. Install the package
npx --yes github:KimYx0207/Meta_Kim meta-kim
2. Add to claude_desktop_config.json
{
"mcpServers": {
"meta-kim": {
"command": "npx",
"args": [
"meta-kim"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
What it is
Summary
Claude Code
Purpose
Evolution
FIX[Fix + review again] FIX --> REVIEW EVOLVE --> UPGRADE[Upgrade agent capability] UPGRADE -->
Critical
C["Release: move forward"] B -->
Responsibility
Purpose
ECC uses `npx --yes --package [email protected] ecc install --profile core --target opencode`; other bundles fall back through `.opencode/` -> `skills/`
`skills/`
Thinking
Review
E["Pause: wait for conditions to mature"] B -->
Trigger condition
Status
Storage location
ECC uses `npx --yes --package [email protected] ecc install --profile core --target qwen`
License
Superpowers uses the Codex Plugins pane or `/plugins`; ECC uses `npx --yes --package ecc-universal@latest ecc install --profile core --target codex` and currently installs the `refactor-cleaner` agent, not the `/refactor-clean` slash command because upstream ECC does not expose `commands-core` for Codex; other bundles fall back through `.codex/` → `.codex-plugin/` → `skills/`
Execution
What it blocks
Current source
Superpowers uses `/add-plugin superpowers` or Cursor's plugin marketplace; ECC is project-local: run `npx --yes --package ecc-universal@latest ecc install --profile core --target cursor` from the project root; other bundles fall back through `.cursor/` → `.cursor-plugin/` → `skills/`
Revision
Preferred subdir chain
### Optional Skill Repositories
Products
Verification
START style RISK fill:#dc2626,color:#fff style P fill:#1e3a5f,color:#93c5fd style WARDEN fill:#7c3aed,color:#fff style DEAL fill:#16a34a,color:#fff ``` ### Closed loop = iterate, generate, improve Once the skeleton, progression workflow, contracts, and dynamic dealing are in place, the system forms a **closed loop**: ```text Request arrives -> skeleton starts -> dealing decision -> dispatch execution -> review and verify -> preserve lessons -> upgrade agents -> next run starts stronger ``` The loop is not one-and-done. Each round can: 1. **Generate the missing agent** - if a capability gap appears, the system can create a new agent through the Type B pipeline 2. **Improve agent capability** - Evolution writes back changes to SOUL.md, skill loadouts, and toolchains 3. **Clarify every agent’s boundary** - each agent owns one class of work; boundary violations are intercepted by Sentinel ```mermaid flowchart TD INPUT[Request arrives] --> SPINE[Hidden skeleton starts] SPINE --> CARD[Dynamic dealing decision] CARD --> DISPATCH[Dispatch to specialist agent] DISPATCH --> REVIEW[Review + verification] REVIEW -->
What it does
All stages
The important part is that some cards are dynamic: - When three high-attention cards are dealt consecutively, the system forcibly inserts **Pause** - it does not wait for the user to notice - When security risk appears, **Risk** preempts the current flow - When the user already knows something, the corresponding card is skipped - When task iteration exceeds the upper bound, the system escalates to **Warden adjudication** Dynamic dealing gives the fixed skeleton some breathing room: strict where it must be strict, flexible where flexibility helps. ```mermaid flowchart TD START[Current card completed] --> SKIP{Check next card<br/>skip_condition} SKIP -->