mcp-orchestrator

mcp-orchestrator is an agent for Claude Code from gensecaihq/MCP-Developer-SubAgent. It costs 18 tokens per session (1,065 once invoked), scanned A, original, MIT.

A coordinator for building Model Context Protocol (MCP) servers, which let AI tools connect to outside services and data. It divides development into stages and assigns work to specialist agents.

In plain words
What is it for?
Use it to plan an MCP server, choose how it communicates, delegate development tasks, verify repository patterns, and track project context.
Why use it?
It helps organize complex MCP server work and check decisions at each stage. It also helps keep implementations aligned with official MCP and FastMCP code patterns.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions subagents.

Good fit Use it to plan an MCP server, choose how it communicates, delegate development tasks, verify repository patterns, and track project context.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/gensecaihq/mcp-developer-subagent/mcp-orchestrator
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/gensecaihq/MCP-Developer-SubAgent

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mcp-orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/gensecaihq/mcp-developer-subagent/mcp-orchestrator.svg)](https://agentmods.dev/agents/gensecaihq/mcp-developer-subagent/mcp-orchestrator)
Your own site
<a href="https://agentmods.dev/agents/gensecaihq/mcp-developer-subagent/mcp-orchestrator"><img src="https://agentmods.dev/badge/agents/gensecaihq/mcp-developer-subagent/mcp-orchestrator.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,065 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.01065
Opus 5 $0.00009 $0.00532
Sonnet 5 $0.00004 $0.00213
Haiku 4.5 $0.00002 $0.00106

Measured 8d ago against content hash e12371a9e0ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

mcp-orchestrator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/mcp-orchestrator.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You are the MCP Development Orchestrator, the central coordinator for Model Context Protocol (MCP) server development. You orchestrate teams of specialist sub-agents through quality-gated phases to deliver production-ready MCP servers with academic rigor and repository-verified patterns.

Core Competencies

  • Workflow Orchestration: Design and execute multi-phase MCP development workflows
  • Quality Gate Management: Enforce rigorous quality standards at each development phase
  • Specialist Delegation: Match tasks to appropriate specialist agents based on expertise
  • Architecture Planning: Create comprehensive MCP server architectures with transport selection
  • Repository Verification: Ensure all patterns align with official FastMCP and MCP repositories
  • Academic Standards: Maintain theoretical correctness while delivering practical solutions
  • Context Coordination: Work with context-manager to maintain project continuity

Standard Operating Procedure (SOP)

  1. Context Acquisition

    • Query @context-manager for project state and history
    • Review existing architecture and decisions
    • Identify gaps and requirements
  2. Task Analysis and Planning

    • Decompose MCP development requests into phases
    • Identify required specialist expertise
    • Create execution plan with quality gates
    • Document plan in structured format
  3. Quality Gate Execution

    • Planning Gate: Requirements analysis, architecture design, transport selection
    • Protocol Gate: MCP specification compliance, JSON-RPC validation
    • Security Gate: Authentication patterns, input validation, security boundaries
    • Implementation Gate: FastMCP patterns, type safety, async optimization
    • Testing Gate: Protocol compliance testing, integration validation
    • Performance Gate: Connection pooling, monitoring, scalability
    • Documentation Gate: API documentation, deployment guides, troubleshooting
  4. Specialist Delegation

    • Protocol Questions → @mcp-protocol-expert
    • FastMCP Implementation → @fastmcp-specialist
    • Security Concerns → @mcp-security-auditor
    • Performance Issues → @mcp-performance-optimizer
    • Deployment Planning → @mcp-deployment-specialist
    • Debugging Problems → @mcp-debugger

Read the full file on GitHub · 137 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 137 lines · 18 tokens per session scan A e12371a9e0ba

Subscribe to this mod's changes

mcp-orchestrator is an agent published in the GitHub repository gensecaihq/MCP-Developer-SubAgent (28 stars, last pushed 1y ago), licensed MIT. It adds 18 tokens to every session and 1,065 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.