What is mcp-server AGENTS.md?

Project instructions for an MCP server template written in TypeScript and built with Bun. They describe its tools, tests, documentation, logging, retries, validated inputs, and standard input/output message handling.

Use them when adding or changing MCP tool handlers, types, logging, retry logic, unit tests, integration tests, or tool documentation.

They explain the project's structure and conventions so changes fit the existing server design.

mcp-server AGENTS.md — Instructions file by berryj85

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 instructions/berryj85/mcp-server/agents-md

Clone the repo

git clone --depth 1 https://github.com/berryj85/mcp-server

Made for: Codex, OpenCode.

Per session 710 This file is loaded in full into every session.

When invoked 710 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5	$0.00710	$0.00710
Opus 5	$0.00355	$0.00355
Sonnet 5	$0.00142	$0.00142
Haiku 4.5	$0.00071	$0.00071

Measured yesterday against content hash 12c9d6cf2340, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mcp-server AGENTS.md 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 yesterday.

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.

AGENTS.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Template

Project Overview

Project Name: mcp-server-template
Language: TypeScript
Build Tool: Bun
Runtime: Bun / Node.js

Technology Stack

Core Framework

Framework: Model Context Protocol (MCP) SDK
Version: 1.0.0
Runtime Version: Bun 1.0+ / Node.js 18+

Architecture & Design Patterns

Overall Pattern

Pattern: Transport-based Server
Description: MCP server using stdio transport for JSON-RPC message handling

Package Structure

mcp-server-template/
 ├─ src/
 │   ├─ server.ts          # Main server entry point
 │   ├─ tools/
 │   │   └─ index.ts       # Tool handlers and definitions
 │   ├─ lib/
 │   │   ├─ logger.ts      # Structured logging (stderr only)
 │   │   └─ retry.ts       # Retry utilities
 │   └─ types/
 │       └─ index.ts       # Zod schemas and types
 │
 ├─ tests/
 │   ├─ unit/              # Unit tests
 │   └─ integration/       # Integration tests
 │
 └─ docs/
     └─ tools/             # Tool documentation

Design Principles

Single Responsibility: Each tool handler in its own function
Dependency Injection: Tools receive validated input
Dependency Rule: No circular imports between modules
Error Handling: All errors caught and returned as structured responses
Testability: Pure functions for tool handlers

Development Standards

Code Style

Style Guide: Biome linter/formatter
Line Length: 100 characters
Indentation: 2 spaces
Naming:
- Classes: PascalCase
- Functions: camelCase
- Constants: UPPER_SNAKE_CASE or camelCase
- Files: snake_case for tools, camelCase otherwise
- Tests: *.test.ts

API Standards

Protocol: JSON-RPC 2.0 (MCP)
Validation: Zod schemas for all tool inputs
Response Format: Structured JSON with isError flag
Logging: stderr only (console.error)

Security Guidelines

No secrets in code or logs
Input validation with Zod before processing
Error messages don't expose internal details
stdin/stdout only for JSON-RPC (no console.log)

Read the full file on GitHub · 100 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.

yesterday First seen · 100 lines · 710 tokens per session scan A 12c9d6cf2340

Subscribe to this mod's changes

mcp-server AGENTS.md is an instructions file published in the GitHub repository berryj85/mcp-server (0 stars, last pushed 4mo ago), licensed MIT. It adds 710 tokens to every session, about $0.0036 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 2026-09-01.

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-server AGENTS.md