Skills mcp-server
📦

mcp-server

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

Build Reliable MCP Servers

MCP server projects often fail because tools mirror APIs instead of real workflows. This skill guides planning, implementation, testing, and evaluation for agent-friendly MCP servers.

Supports: Claude Codex Code(CC)
📊 67 Adequate

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-server" from https://skillstore.io/skills/cam10001110101-mcp-server.md and its manifest at https://skillstore.io/api/skills/cam10001110101-mcp-server/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

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/cam10001110101-mcp-server.md Signed manifest GET /api/skills/cam10001110101-mcp-server/manifest Signed lockfile GET /api/skills/cam10001110101-mcp-server/lockfile

Test it

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

Expected outcome:

A tool plan with workflow-focused names, input fields, response formats, error handling, and evaluation tasks.

Using "mcp-server". Review my TypeScript MCP tool design.

Expected outcome:

  • A list of schema issues and missing descriptions.
  • Specific recommendations for pagination, validation, and response size limits.
  • A short quality checklist for build and runtime checks.

Using "mcp-server". Create evaluations for a GitHub-style MCP server.

Expected outcome:

A set of stable, read-only questions with exact expected answers and instructions for running the harness.

Security Audit

Medium Risk
v8 • 7/5/2026 Open versioned report

The static findings are overwhelmingly documentation examples, placeholder credentials, or TypeScript string templates, so I marked them false positive. The active scripts do include a legitimate evaluation harness that can launch a user-selected MCP server command, which creates a bounded local execution risk. No evidence found of prompt injection, hidden exfiltration, or malicious secret harvesting in the reviewed files.

10
Files scanned
4,269
Lines analyzed
0
Review items
0
False positives ignored

Confirmed security concerns (1)

Medium
scripts/evaluation.py:327-329scripts/connections.py:76-84
User-Controlled MCP Server Command Execution
The evaluation CLI accepts a command and arguments for stdio transport, then passes them into StdioServerParameters to launch the MCP server. This is intended for local evaluation, but running untrusted commands can execute arbitrary local code.
The command, args, and env values come from CLI arguments and are passed into the MCP stdio client. The surrounding code is an evaluation harness, so the risk depends on running trusted inputs.

Risk Factors

🌐 Network access (32)
reference/evaluation.md:456 reference/evaluation.md:469 reference/node_mcp_server.md:16 reference/node_mcp_server.md:406 reference/node_mcp_server.md:442 reference/node_mcp_server.md:467 reference/node_mcp_server.md:473 reference/node_mcp_server.md:541 reference/node_mcp_server.md:591 reference/node_mcp_server.md:635 reference/node_mcp_server.md:888 reference/node_mcp_server.md:417 reference/node_mcp_server.md:661 reference/node_mcp_server.md:594 reference/python_mcp_server.md:193 reference/python_mcp_server.md:259 reference/python_mcp_server.md:262 reference/python_mcp_server.md:409 reference/python_mcp_server.md:412 reference/python_mcp_server.md:453 reference/python_mcp_server.md:246 reference/python_mcp_server.md:286 reference/python_mcp_server.md:429 reference/python_mcp_server.md:379 scripts/evaluation.py:315 scripts/evaluation.py:318 SKILL.md:60 SKILL.md:71 SKILL.md:75 SKILL.md:294 SKILL.md:304 SKILL.md:305
🔑 Env variables (10)
reference/evaluation.md:567 reference/evaluation.md:398 reference/evaluation.md:444 reference/evaluation.md:557 reference/node_mcp_server.md:700 reference/node_mcp_server.md:700 reference/node_mcp_server.md:700 reference/node_mcp_server.md:701 reference/python_mcp_server.md:538 reference/python_mcp_server.md:544
⚙️ External commands (50)
reference/mcp_best_practices.md:703-713 reference/mcp_best_practices.md:713-718 reference/node_mcp_server.md:171-202 reference/node_mcp_server.md:202-212 reference/node_mcp_server.md:212-213 reference/node_mcp_server.md:213-217 reference/node_mcp_server.md:217-218 reference/node_mcp_server.md:218-220 reference/node_mcp_server.md:220-267 reference/node_mcp_server.md:392-393 reference/node_mcp_server.md:393-399 reference/node_mcp_server.md:419-425 reference/node_mcp_server.md:425-427 reference/node_mcp_server.md:444-458 reference/node_mcp_server.md:467-473 reference/node_mcp_server.md:473-476 reference/node_mcp_server.md:509-515 reference/node_mcp_server.md:515-517 reference/node_mcp_server.md:637-663 reference/node_mcp_server.md:663-669 reference/node_mcp_server.md:669-683 reference/node_mcp_server.md:683-719 reference/node_mcp_server.md:765-772 scripts/evaluation.py:204 scripts/evaluation.py:205 SKILL.md:29 SKILL.md:60 SKILL.md:71 SKILL.md:75 SKILL.md:126 SKILL.md:132 SKILL.md:172 SKILL.md:173 SKILL.md:174 SKILL.md:175 SKILL.md:183 SKILL.md:190 SKILL.md:191 SKILL.md:193 SKILL.md:195 SKILL.md:215 SKILL.md:220 SKILL.md:223 SKILL.md:229 SKILL.md:275-283 SKILL.md:283-294 SKILL.md:294-304 SKILL.md:304-305 SKILL.md:305-311 SKILL.md:311-318
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
Security Assessment

Copy report link

https://skillstore.io/skills/cam10001110101-mcp-server/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/cam10001110101-mcp-server/security.svg)](https://skillstore.io/skills/cam10001110101-mcp-server?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/cam10001110101-mcp-server?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/cam10001110101-mcp-server/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/cam10001110101-mcp-server.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

Cam10001110101. (2026). mcp-server security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/cam10001110101-mcp-server/audits/8

BibTeX citation

@techreport{cam10001110101-cam10001110101-mcp-server-2026, author = {Cam10001110101}, title = {mcp-server security audit report (audit version 8)}, institution = {Skillstore}, year = {2026}, number = {8}, url = {https://skillstore.io/skills/cam10001110101-mcp-server/audits/8}, 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-server security audit report (audit version 8)" version: "unspecified" type: report authors: - name: "Cam10001110101" date-released: "2026-07-05" url: "https://skillstore.io/skills/cam10001110101-mcp-server/audits/8" identifiers: - type: other value: "skillstore:cam10001110101-mcp-server:audit:8" 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
Cam10001110101 Recommended Current

cam10001110101-mcp-server

Skillstore Score 67
Evidence Confidence High
Skillstore usage 11
Updated

2026-08-21

Azeem-2

azeem-2-mcp-server

Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 15
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High
45
Architecture
85
Maintainability
87
Content
71
Community
83
Spec Compliance

What You Can Build

Plan a New MCP Integration

Map service APIs into focused tools with clear schemas, useful errors, and stable response formats.

Implement Python or TypeScript Servers

Follow language-specific patterns for validation, async calls, shared helpers, and MCP tool registration.

Evaluate Tool Quality

Create read-only questions and run the included harness to measure whether agents can complete real tasks.

Try These Prompts

Plan My MCP Server 
Use this skill to plan an MCP server for my service. Identify workflows, tools, inputs, outputs, and evaluation questions.
Design Tool Schemas 
Review my API operations and design MCP tool schemas. Include validation rules, response formats, pagination, and error messages.
Implement Server Structure 
Create an MCP server implementation plan for this API. Use the language guide for shared helpers, tool registration, and tests.
Build Evaluation Suite 
Create a read-only evaluation suite for this MCP server. Include realistic questions, verified answers, and harness run instructions.

Best Practices

  • Design tools around complete tasks that agents need to finish.
  • Use strict input validation and clear, actionable error messages.
  • Keep responses concise, paginated, and easy for models to compare.

Avoid

  • Do not wrap every API endpoint as a separate MCP tool without workflow design.
  • Do not return large raw payloads when filtered summaries would answer the task.
  • Do not run evaluation commands or servers from untrusted sources.

Frequently Asked Questions

Does this skill create a complete MCP server automatically?
No. It provides guidance, examples, and an evaluation harness for building your own server.
Which languages does it cover?
It covers Python with FastMCP and Node or TypeScript with the MCP SDK.
Can it connect to external APIs?
Yes. The guide explains API client patterns, authentication planning, pagination, and error handling.
Does the evaluation harness require credentials?
Yes. Model-based evaluation requires a valid Anthropic API key and any service credentials your MCP server needs.
Is it safe to run any command with the harness?
No. Only run trusted local MCP server commands, because the harness can start a process you specify.
Can I use it with Claude Code or Codex?
Yes. The skill content is suitable for Claude, Claude Code, and Codex workflows.

Developer Details

License

Complete terms in LICENSE.txt

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/Cam10001110101/claude-skills-base/tree/main/mnt/skills/examples/mcp-server

Ref

02f077c174c5335e2f5d02ca15e77b70d9543e58

Maintenance freshness

7/18/2026

Usage

8 downloads · 240 views

File structure

📁 reference/

📄 evaluation.md

📄 mcp_best_practices.md

📄 node_mcp_server.md

📄 python_mcp_server.md

📁 scripts/

📄 connections.py

📄 evaluation.py

📄 example_evaluation.xml

📄 requirements.txt

📄 LICENSE.txt

📄 SKILL.md