Skills building-mcp-servers

📦

building-mcp-servers

Name: building-mcp-servers
Author: Asmayaseen

Content revision r2 High Risk 🌐 Network access🔑 Env variables⚙️ External commands

Build Secure MCP Servers

MCP server projects often lack consistent tool design, transport choices, and evaluation methods. This skill provides practical Python and TypeScript patterns for implementation and testing.

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 "building-mcp-servers" from https://skillstore.io/skills/asmayaseen-building-mcp-servers.md and its manifest at https://skillstore.io/api/skills/asmayaseen-building-mcp-servers/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/asmayaseen-building-mcp-servers.md Signed manifest GET /api/skills/asmayaseen-building-mcp-servers/manifest Signed lockfile GET /api/skills/asmayaseen-building-mcp-servers/lockfile

Test it

Using "building-mcp-servers". Plan an MCP server for a project management API.

Expected outcome:

A prioritized tool catalog for projects, tasks, users, and status updates.
Validated input and output requirements for every tool.
A transport, authentication, pagination, and error-handling plan.

Using "building-mcp-servers". Review this remote MCP deployment before production.

Expected outcome:

The review identifies authentication gaps, broad network exposure, secret-handling risks, missing rate limits, and focused remediation steps.

Using "building-mcp-servers". Create evaluation coverage for a repository MCP server.

Expected outcome:

Ten read-only tasks cover search, comparison, aggregation, historical analysis, pagination, failure handling, and exact answer verification.

Security Audit

High Risk

v9 • 7/23/2026 Open versioned report

Most static alerts are false positives from Markdown, template strings, placeholders, or documented API examples. Two exposure patterns and three semantic design risks remain confirmed.

Files scanned

3,634

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (3)

High

references/node_mcp_server.md:717-740 references/taskflow_patterns.md:12-18 references/taskflow_patterns.md:54-68

Unauthenticated Remote MCP Endpoints

Remote examples expose MCP handlers without client authentication. Permissive CORS and broad binding can make upstream capabilities reachable by unauthorized clients.

The examples explicitly omit MCP client authentication, allow every CORS origin, and bind the TaskFlow server to all interfaces.

High

references/taskflow_patterns.md:127-145 scripts/evaluation.py:326-333 references/evaluation.md:438-470

Credentials Exposed as Tool and CLI Inputs

The guidance puts access tokens in model-visible tool parameters and accepts secrets through command arguments. Transcripts, logs, or process listings may expose them.

The documented tool schema includes access_token, while evaluation examples place API keys and authorization headers directly on the command line.

High

scripts/evaluation.py:94-103 scripts/evaluation.py:109-145

Untrusted MCP Content Re-enters Agent Loop

The evaluator sends server-defined tools and tool results directly to the model. A malicious server can inject instructions or influence later tool calls.

Tool schemas and returned content cross directly into model requests without server trust checks, content isolation, or confirmation controls.

Capability review items (2)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

High

references/taskflow_patterns.md:67

Hardcoded IP address

host="0.0.0.0",

The example binds an unauthenticated HTTP service to every interface, making accidental network exposure likely when users copy the pattern.

Medium

SKILL.md:161

Hardcoded IP address

"0.0.0.0:*",

Allowing the all-interface address in Host validation broadens remote reachability and weakens the nearby DNS rebinding guidance.

Risk Factors

🌐 Network access (35)

🔑 Env variables (18)

⚙️ External commands (44)

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/asmayaseen-building-mcp-servers/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/asmayaseen-building-mcp-servers.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

Asmayaseen. (2026). building-mcp-servers security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/asmayaseen-building-mcp-servers/audits/9

BibTeX citation

@techreport{asmayaseen-asmayaseen-building-mcp-servers-2026,
  author = {Asmayaseen},
  title = {building-mcp-servers security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/asmayaseen-building-mcp-servers/audits/9},
  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: "building-mcp-servers security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
  - name: "Asmayaseen"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/asmayaseen-building-mcp-servers/audits/9"
identifiers:
  - type: other
    value: "skillstore:asmayaseen-building-mcp-servers:audit:9"
    description: "Skillstore immutable audit report identifier"

Compare variants

2 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

C0ntr0lledCha0s Recommended

c0ntr0lledcha0s-building-mcp-servers

Skillstore Score 74

Evidence Confidence High

Skillstore usage 9

Updated

2026-08-21

Asmayaseen Current

asmayaseen-building-mcp-servers

Skillstore Score 38

Evidence Confidence Medium

Skillstore usage 15

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Create a Service Integration

Design and implement an MCP server that exposes a service API through clear, validated tools.

Prepare a Production Deployment

Choose transports, container settings, authentication boundaries, health checks, and operational safeguards for an MCP service.

Evaluate Agent Tool Use

Create stable read-only tasks and measure whether an agent can use MCP tools to produce verified answers.

Try These Prompts

Plan a Basic MCP Server

Design a Python FastMCP server for [service]. List tools, input schemas, response formats, authentication needs, and a minimal test plan.

Implement a TypeScript Server

Create a TypeScript MCP server design for [API]. Include Zod schemas, pagination, structured responses, error handling, and stdio transport.

Create Evaluation Tasks

Develop ten independent read-only evaluation questions for this MCP server. Make each answer stable, verifiable, realistic, and difficult enough to require tools.

Harden a Remote Deployment

Review this Streamable HTTP MCP design for authentication, authorization, secret handling, prompt injection, origin validation, network exposure, rate limits, and audit logging.

Best Practices

Use narrowly scoped tools with validated schemas, precise descriptions, pagination, and structured outputs.
Keep credentials outside model-visible inputs and enforce authorization for every remote request.
Test valid, invalid, adversarial, and high-volume inputs with stable read-only evaluations.

Avoid

Do not expose remote MCP handlers without client authentication, origin controls, and restricted network binding.
Do not place access tokens, API keys, or sensitive user data in tool schemas or command arguments.
Do not trust tool annotations or server-returned content as security guarantees.