Skills mcp-builder

📦

mcp-builder

Name: mcp-builder
Author: ZhanlinCui

Content revision r1 High Risk 🌐 Network access🔑 Env variables⚙️ External commands

Build Reliable MCP Servers

Developers need clear patterns for MCP servers that expose useful tools without confusing agents. This skill provides planning, implementation, testing, and evaluation guidance for Python and TypeScript MCP projects.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "mcp-builder" from https://skillstore.io/skills/zhanlincui-mcp-builder.md and its manifest at https://skillstore.io/api/skills/zhanlincui-mcp-builder/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/zhanlincui-mcp-builder.md Signed manifest GET /api/skills/zhanlincui-mcp-builder/manifest Signed lockfile GET /api/skills/zhanlincui-mcp-builder/lockfile

Test it

Using "mcp-builder". Plan an MCP server for a ticketing API.

Expected outcome:

Recommended tools cover ticket search, ticket details, comments, assignment, and status updates.
Use read-only annotations for search and detail tools, and destructive annotations for mutation tools.
Start with stdio for local testing, then move to streamable HTTP for remote deployment.

Using "mcp-builder". Review my current MCP tool list for usability.

Expected outcome:

The review highlights unclear names, missing pagination, broad response payloads, and error messages that need recovery guidance.

Using "mcp-builder". Create evaluation coverage for a GitHub MCP server.

Expected outcome:

The plan uses stable read-only questions about issues, pull requests, repositories, labels, and dates.
Each question includes one expected answer and a verification path based on tool calls.

Security Audit

High Risk

v4 • 7/8/2026 Open versioned report

Most static findings are false positives caused by Markdown examples, TypeScript template literals, placeholder URLs, and placeholder API keys in reference material. I confirmed the evaluation harness risk where user-supplied environment variables are forwarded to a locally launched MCP server, and added a semantic finding for unrestricted local command execution during stdio evaluation.

Files scanned

3,330

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (4)

High

scripts/connections.py:80

Environment file access

self.env = env

The harness stores user-supplied environment variables that can include secrets before launching a local MCP server. This is intended behavior, but it exposes supplied secrets to any evaluated stdio server.

High

scripts/connections.py:84

Environment file access

StdioServerParameters(command=self.command, args=self.args, env=self.env)

The stdio connection forwards the provided environment dictionary into the launched MCP process. This is a real secret exposure risk when the evaluated server command is untrusted.

High

scripts/evaluation.py:344

Environment file access

env_vars = parse_env_vars(args.env) if args.env else None

The CLI parses user-supplied environment variables and passes them into the evaluation connection. This is expected for testing, but scoped secrets can be exposed to the target server.

High

scripts/evaluation.py:327-329 scripts/evaluation.py:347-351 scripts/connections.py:82-84

Unrestricted Local MCP Process Launch

The evaluation harness accepts a command, arguments, and environment variables, then launches a stdio MCP server from those values. This is intended for testing, but evaluating untrusted servers can execute local code and expose supplied secrets.

The CLI explicitly accepts command, args, and env options and passes them to StdioServerParameters. The risk depends on user choices, but the execution and secret-forwarding boundary is clear.

Risk Factors

🌐 Network access (33)

🔑 Env variables (18)

⚙️ External commands (46)

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/zhanlincui-mcp-builder/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/zhanlincui-mcp-builder/security.svg)](https://skillstore.io/skills/zhanlincui-mcp-builder?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/zhanlincui-mcp-builder?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/zhanlincui-mcp-builder/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/zhanlincui-mcp-builder.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

ZhanlinCui. (2026). mcp-builder security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/zhanlincui-mcp-builder/audits/4

BibTeX citation

@techreport{zhanlincui-zhanlincui-mcp-builder-2026,
  author = {ZhanlinCui},
  title = {mcp-builder security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/zhanlincui-mcp-builder/audits/4},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "mcp-builder security audit report (audit version 4)"
version: "unspecified"
type: report
authors:
  - name: "ZhanlinCui"
date-released: "2026-07-08"
url: "https://skillstore.io/skills/zhanlincui-mcp-builder/audits/4"
identifiers:
  - type: other
    value: "skillstore:zhanlincui-mcp-builder:audit:4"
    description: "Skillstore immutable audit report identifier"

Compare variants

15 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

Doyajin174 Recommended

doyajin174-mcp-builder

Skillstore Score 78

Evidence Confidence High

Skillstore usage 13

Updated

2026-08-21

anthropics

mcp-builder

Skillstore Score 75

Evidence Confidence High

Skillstore usage 15

Updated

2026-08-21

Azeem-2

azeem-2-mcp-builder

Skillstore Score 75

Evidence Confidence High

Skillstore usage 8

Updated

2026-08-21

mcp-use

mcp-use-mcp-builder

Skillstore Score 68

Evidence Confidence High

Skillstore usage 10

Updated

2026-08-21

shubhamsaboo

shubhamsaboo-mcp-builder

Skillstore Score 67

Evidence Confidence Medium

Skillstore usage 5

Updated

2026-08-21

YYH211

yyh211-mcp-builder

Skillstore Score 66

Evidence Confidence High

Skillstore usage 68

Updated

2026-08-21

Cam10001110101

cam10001110101-mcp-builder

Skillstore Score 66

Evidence Confidence High

Skillstore usage 10

Updated

2026-08-21

DYAI2025

dyai2025-mcp-builder

Skillstore Score 66

Evidence Confidence High

Skillstore usage 7

Updated

2026-08-21

ZhanlinCui Current

zhanlincui-mcp-builder

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 22

Updated

2026-08-21

92Bilal26

92bilal26-mcp-builder

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 17

Updated

2026-08-21

sickn33

sickn33-mcp-builder

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 13

Updated

2026-08-21

ArtemisAI

artemisai-mcp-builder

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 10

Updated

2026-08-21

ComposioHQ

composiohq-mcp-builder

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 9

Updated

2026-08-21

AutumnsGrove

autumnsgrove-mcp-builder

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 9

Updated

2026-08-21

davila7

davila7-mcp-builder

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 7

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Plan a New Integration

Map a service API into useful MCP tools, resources, and transport choices before coding.

Standardize Server Design

Apply consistent naming, schemas, pagination, and error handling across a team of MCP servers.

Evaluate Agent Usability

Create read-only evaluation questions that test whether agents can complete realistic tasks.

Try These Prompts

Plan a Basic MCP Server

Use mcp-builder to plan an MCP server for this service: [service name]. Identify core tools, required authentication, transport choice, and first implementation steps.

Design Tool Schemas

Use mcp-builder to design MCP tool names, input schemas, output formats, and annotations for these API operations: [operations]. Prioritize clear agent usage.

Review an MCP Implementation

Use mcp-builder to review this MCP server design or code summary: [details]. Check naming, validation, pagination, error messages, transport, and security concerns.

Create Evaluation Coverage

Use mcp-builder to create an evaluation plan for this MCP server: [tool list and data domain]. Produce ten stable, read-only questions with verification strategy.

Best Practices

Read current MCP protocol and SDK documentation before choosing server patterns.
Keep tool names action oriented, service specific, and easy for agents to discover.
Build evaluations with read-only, stable questions and verified expected answers.

Avoid

Do not expose broad low-level endpoints without practical workflow coverage.
Do not return large unfiltered payloads when pagination or filters are available.
Do not pass production secrets to untrusted MCP servers during evaluation.