CtrlK
BlogDocsLog inGet started
Tessl Logo

building-mcp-server-on-cloudflare

Builds remote MCP (Model Context Protocol) servers on Cloudflare Workers with tools, OAuth authentication, and production deployment. Generates server code, configures auth providers, and deploys to Workers. Use when: user wants to "build MCP server", "create MCP tools", "remote MCP", "deploy MCP", add "OAuth to MCP", or mentions Model Context Protocol on Cloudflare. Also triggers on "MCP authentication" or "MCP deployment". Biases towards retrieval from Cloudflare docs over pre-trained knowledge.

72

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-built skill body: lean, retrieval-biased, and packed with executable code, commands, and config that cover the common path from scaffold to deployed server. Structure and reference hygiene are excellent; the only gaps are one redundant concept explanation and a deploy step without an explicit post-deploy verification checkpoint.

Suggestions

Delete the 'Tools are functions MCP clients can call.' sentence — Claude already knows what MCP tools are; the code example carries the information.

Add an explicit verification step after 'npx wrangler deploy' (e.g., curl the /mcp endpoint or check 'wrangler deployments list') so validation is embedded in the workflow rather than only in the Common Issues section.

DimensionReasoningScore

Conciseness

The body is efficient and command-dense, but contains minor over-explanations of concepts Claude already knows — e.g., 'Tools are functions MCP clients can call' and spelling out MCP basics — that could be trimmed. This matches anchor 4 ('efficient; minor instances of over-explanation') rather than 5 ('every token earns its place') or 3 ('mostly efficient but some unnecessary explanation'), since the excess is slight and isolated.

4 / 5

Actionability

Guidance is fully executable and copy-paste ready: concrete scaffold commands ('npm create cloudflare@latest -- my-mcp-server --template=...'), complete TypeScript tool definitions with Zod schemas, a full wrangler.toml, 'npx wrangler deploy', and inspector test commands. This matches anchor 5 (specific examples covering common cases) rather than 4, since no significant gaps exist.

5 / 5

Workflow Clarity

The Core Workflow is a clearly sequenced Steps 1–5 with a local-test checkpoint (MCP Inspector) and a troubleshooting section for error recovery, but post-deploy verification is only implicit (the 'wrangler deployments list' check lives in troubleshooting, not the deploy step). This fits anchor 4 ('clear sequence with most checkpoints; minor validation gaps') better than 5, which requires explicit validation steps embedded in the sequence. No destructive/batch operations are involved, so no cap applies.

4 / 5

Progressive Disclosure

The body is a clear overview with three well-signaled, one-level-deep reference files (references/examples.md, references/oauth-setup.md, references/troubleshooting.md), all of which exist in the bundle and contain no nested references. Each is pointed to inline at the right moment and again in a labeled References section, matching anchor 5 (clear overview, well-signaled one-level references, easy navigation).

5 / 5

Total

18

/

20

Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states concrete capabilities in third person and pairs them with an explicit, naturally phrased 'Use when:' trigger clause. Only minor trigger-term gaps keep it from a perfect score.

DimensionReasoningScore

Specificity

The description lists multiple concrete, comprehensive actions — 'Builds remote MCP (Model Context Protocol) servers on Cloudflare Workers with tools, OAuth authentication, and production deployment. Generates server code, configures auth providers, and deploys to Workers' — covering build, generate, configure, and deploy. This matches the top anchor (multiple specific concrete actions, comprehensive coverage); the score-4 anchor ('minor gaps in coverage') fits worse since nothing material is missing for this domain.

5 / 5

Completeness

It explicitly answers both questions: 'what' via 'Builds remote MCP servers... Generates server code, configures auth providers, and deploys to Workers' and 'when' via the explicit 'Use when:' clause with concrete quoted trigger phrases. This is a direct match for the anchor-5 example pattern; score 4 ('when could be more explicit') does not apply since the when-clause is explicit and specific.

5 / 5

Trigger Term Quality

Trigger coverage is good and phrased as natural user utterances ('build MCP server', 'create MCP tools', 'remote MCP', 'deploy MCP', 'add OAuth to MCP', 'MCP authentication', 'MCP deployment'), but a few natural terms are missing — e.g., 'connect MCP to Claude/Codex', 'expose tools', or a bare 'Cloudflare Workers' trigger. It matches anchor 4 ('good keyword coverage; a few natural terms missing') better than 5, which requires comprehensive coverage including synonyms and extensions like file formats.

4 / 5

Distinctiveness Conflict Risk

The niche is clear (remote MCP servers on Cloudflare Workers specifically) and triggers are anchored to that combination, giving minimal conflict risk with generic MCP, OAuth, or deployment skills. Third-person voice is used throughout, so no specificity penalty applies. A clear niche with distinct triggers matches anchor 5.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
openai/plugins
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.