# Tool Orchestration MCP

> Use to design Jarvis tool registry and local MCP-style tool orchestration with typed schemas, permissions, dry-run modes, audit logs, loopback-only services, and safe tool execution.

- Skill: `brathod1432/tool-orchestration-mcp` (Agent Skill)
- Install (CLI): `npx skillmds@latest add brathod1432/tool-orchestration-mcp`
- Raw SKILL.md: https://api.skillmd.com/api/skills/brathod1432/tool-orchestration-mcp/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: brathod1432 (https://skillmd.com/u/brathod1432)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/brathod1432/tool-orchestration-mcp

---


## Internal Safety Override

- Status: active for local design and scoped local implementation.
- Tools must default to least privilege.
- Network-capable tools must be disabled until explicitly approved.
- Destructive tools require dry-run and confirmation.

# Tool Orchestration MCP

## Tool Registry Fields

```json
{
  "name": "string",
  "description": "string",
  "permission": "read_local|write_local|execute_local|automate_app|network|high_impact",
  "side_effects": false,
  "dry_run": true,
  "input_schema": {},
  "output_schema": {},
  "redaction": "string",
  "approval_required": false
}
```

## Tool Classes

Read local:
- File read, search, metadata, local app state.

Write local:
- Patch file, create note, update memory.

Execute local:
- Tests, formatters, safe scripts.

Automate app:
- Browser, Office, desktop UI.

Network:
- External docs, APIs, cloud.

High impact:
- Send, publish, deploy, delete, buy, account/security changes.

## MCP Server Guidelines

- Bind to loopback only.
- Use explicit schemas.
- Bound output length.
- Redact secrets at source.
- Separate read tools from write tools.
- Add dry-run to risky tools.
- Log tool summaries, not raw sensitive payloads.