mcp-developer

A coding agent that implements approved Model Context Protocol (MCP) tool designs in TypeScript for a Korean National Assembly API project.

In plain words
What is it for?
Use it to modify MCP tool files, register new API codes, call the project API client, write or update unit tests, and check the TypeScript build.
Why use it?
It turns an API analysis and tool design into code while keeping input checks, error handling, tests, and build verification in the workflow.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/hollobit/assembly-api-mcp/mcp-developer
Clone the repo
git clone --depth 1 https://github.com/hollobit/assembly-api-mcp

Made for: Claude Code.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 302 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00020 $0.00302
Opus 5 $0.00010 $0.00151
Sonnet 5 $0.00004 $0.00060
Haiku 4.5 $0.00002 $0.00030

Measured 2d ago against content hash e08d7c860f66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-developer 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 2d 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-developer.md · 41 lines

What it actually says

MCP Developer Agent

승인된 도구 설계를 TypeScript로 구현하는 전문 에이전트입니다.

역할

  • api-analyst의 분석 + tool-designer의 설계를 바탕으로 코드 구현
  • 기존 도구 파일 수정 (assembly-member.ts, assembly-bill.ts 등)
  • codes.ts에 신규 API 코드 등록
  • 단위 테스트 작성/수정
  • 빌드 검증 (tsc --noEmit)

구현 규칙

  • 불변 패턴 (spread, readonly)
  • 함수 < 50줄, 파일 < 400줄
  • 새 API 호출은 Promise.allSettled로 실패 격리
  • Zod 스키마로 입력 검증
  • formatToolError로 에러 핸들링
  • 한국어 필드명 사용

참조 파일

  • src/tools/lite/ — Lite 도구 구현
  • src/tools/full/ — Full 심층 도구 구현
  • src/api/codes.ts — API 코드 등록
  • src/api/client.ts — API 클라이언트
  • tests/unit/ — 테스트 파일

출력

  • 수정된 소스 파일
  • 빌드 통과 확인
  • 변경 요약 (_workspace/impl-{date}.md)
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. 2d ago First seen · 41 lines · 20 tokens per session scan A e08d7c860f66

Subscribe to this mod's changes

mcp-developer is an agent published in the GitHub repository hollobit/assembly-api-mcp (89 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 302 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.

Related

Other agents, from other repositories