mcp-builder

mcp-builder is a skill for Claude Code from neverinfamous/memory-journal-mcp. It costs 100 tokens per session (741 once invoked), scanned C, original, MIT.

Guidelines for building Model Context Protocol (MCP) servers, which let AI applications call tools and receive structured results.

In plain words
What is it for?
Use them when creating or reviewing MCP server code, including argument validation, structured error responses, logging, secrets, rate limits, and optional Playwright tests.
Why use it?
They help prevent invalid inputs, unhandled failures, exposed secrets, and weak security boundaries in MCP tools.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Good fit Use them when creating or reviewing MCP server code, including argument validation, structured error responses, logging, secrets, rate limits, and optional Playwright tests.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/neverinfamous/memory-journal-mcp/mcp
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.

Any agent
npx skills add neverinfamous/memory-journal-mcp --skill mcp
Clone the repo
git clone --depth 1 https://github.com/neverinfamous/memory-journal-mcp

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-builder

README.md
[![agentmods](https://agentmods.dev/badge/skills/neverinfamous/memory-journal-mcp/mcp/github.svg)](https://agentmods.dev/skills/neverinfamous/memory-journal-mcp/mcp)
Your own site
<a href="https://agentmods.dev/skills/neverinfamous/memory-journal-mcp/mcp"><img src="https://agentmods.dev/badge/skills/neverinfamous/memory-journal-mcp/mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for mcp-builder

Your own site · 80×15
<a href="https://agentmods.dev/skills/neverinfamous/memory-journal-mcp/mcp"><img src="https://agentmods.dev/badge/skills/neverinfamous/memory-journal-mcp/mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 741 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00100 $0.00741
Opus 5.5 $0.00040 $0.00296
Sonnet 5.5 $0.00020 $0.00148
Haiku 4.5 $0.00010 $0.00074

Measured 1mo ago against content hash 3dff783c1261, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

mcp-builder scanned grade C with 1 finding 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 1mo 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Blocklists are Defense-in-Depth**: A blocklist (e.g., forbidding `rm -rf` in a terminal tool) is not a primary security boundary. Your primary security is the sandbox, container, or strict schema validation.
skills/agents-sdk/references/mcp/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Server Builder Guidelines

This skill defines the high-integrity requirements for building MCP servers in this ecosystem.

1. Core Requirements

When building or modifying MCP servers, follow these prioritized rules:

  • Must: Use Zod for all tool argument validation. Do not blindly trust MCP client inputs.
  • Must: Return structured errors ({ isError: true, content: [...] }) from tools rather than throwing raw unhandled exceptions that crash the server.
  • Should: Wrap handlers in try/catch blocks that gracefully surface errors to the LLM context.
  • Should: Centralize error logging using standard prefixes (e.g., [MCP Error]).
  • Optional: Depending on the repository, implement integration testing via Playwright for dual HTTP/SSE verification.

2. Security (Defense-in-Depth)

  • Blocklists are Defense-in-Depth: A blocklist (e.g., forbidding rm -rf in a terminal tool) is not a primary security boundary. Your primary security is the sandbox, container, or strict schema validation.
  • No Secrets in Config: MCP servers must rely on the environment variables for API keys and secrets, never hardcoded files inside the server repository.
  • Rate Limiting & Input Sanitization: Aggressively sanitize path arguments to prevent directory traversal (../../), and apply basic rate-limiting to tools that trigger heavy compute or external API calls.

3. Deep References

For the complete MCP implementation guide, architecture diagrams, and detailed tooling patterns, consult the full reference:

  • MCP Implementation Guide: Contains transport selection (stdio vs. SSE), auth patterns, and multi-tool orchestration diagrams.

4. Scaffold Reference

When you need a minimal, fully compliant MCP server scaffold, use this structure:

import { McpServer } from '@modelcontextprotocol/sdk/server/mcp.js'
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'
import { z } from 'zod'

// Initialize the modern McpServer pattern
const server = new McpServer({ name: 'my-mcp', version: '1.0.0' })

// Define tools using server.tool() which auto-registers schemas and handlers
server.tool(
  'my_tool',
  'Does something using an ID',
  { id: z.string().describe('The user ID to process') },
  async ({ id }) => {
    try {
      // Logic here (input is already validated by Zod)
      return { content: [{ type: 'text', text: `Got ID: ${id}` }] }
    } catch (err) {
      // Graceful error return
      return { isError: true, content: [{ type: 'text', text: `Error: ${err}` }] }
    }
  }
)

// Connect via standard I/O
const transport = new StdioServerTransport()
await server.connect(transport)

Read the full file on GitHub · 66 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 1mo ago First seen · 66 lines · 100 tokens per session scan C 3dff783c1261

Subscribe to this mod's changes

mcp-builder is a skill published in the GitHub repository neverinfamous/memory-journal-mcp (20 stars, last pushed 3mo ago), licensed MIT. It adds 100 tokens to every session and 741 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

skill-creator

Generate a new skill from a plain-language description — decides invocation control, arguments, and context cost, then scaffolds, validates, and tests it.

conorbronsdon/agent-context-os · 33 tokens

context-end

Close a workspace session by reviewing a proposed summary, recording approved outcomes, updating state and decisions, and checking repository safety. Use only when the user explicitly asks to end, close, or hand off the current session.

conorbronsdon/agent-context-os · 46 tokens

context-setup

Build, import, or refresh this workspace's identity, project, reusable-workflow, and weekly-state files through a guided review. Use only when the user explicitly asks to initialize or redo workspace context.

conorbronsdon/agent-context-os · 44 tokens

context-start

Load this workspace's current state, recent decisions, blockers, priorities, and session continuity, then give a concise briefing. Use only when the user explicitly asks to begin or resume a workspace session.

conorbronsdon/agent-context-os · 42 tokens

context-update

Save a brief mid-session checkpoint to this workspace and update current state only when a priority or open thread changed. Use only when the user explicitly asks to checkpoint or save current progress.

conorbronsdon/agent-context-os · 39 tokens

migrate-gemini

Migrate selected Gemini CLI instructions, commands, skills, hooks, and MCP configuration into this workspace with a dry run, review gates, and parity checks.

conorbronsdon/agent-context-os · 37 tokens