CtrlK
BlogDocsLog inGet started
Tessl Logo

build-mcp-server

This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates the user about their use case, determines the right deployment model (remote HTTP, MCPB, local stdio), picks a tool-design pattern, and hands off to specialized skills.

70

Quality

86%

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

78%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-structured orchestration skill that keeps the body as a lean decision guide and pushes scaffolding detail to one-level-deep references. Sequencing and progressive disclosure are strong; the only lever is light trimming of justificatory prose.

Suggestions

Tighten the "Why it wins"/"Why it works" rationale blocks to bullet essentials — the deployment recommendation already speaks for itself.

Consider collapsing the Phase 4 framework table and the "Beyond tools" primitives table where their content overlaps with referenced files to reduce body tokens.

The FastMCP provenance aside ("This is jlowin's package — not the frozen FastMCP 1.0…") is useful but could move to versions.md with the other version-sensitive claims.

DimensionReasoningScore

Conciseness

Mostly efficient: terse tables, bullet decisions, and named packages/URLs with no padding of basic concepts; a few justificatory prose blocks ("Why it wins", "Why it works", the FastMCP provenance aside) could be trimmed but largely earn their place.

4 / 5

Actionability

Provides concrete, executable guidance — specific framework/package names, a named decision matrix, real docs URLs, and per-path reference files to scaffold from; minor gap is that copy-paste code lives in references rather than the body, which is appropriate for an orchestration skill.

4 / 5

Workflow Clarity

Six numbered phases are clearly sequenced with an explicit gate ("Do not start scaffolding until you have answers to the questions in Phase 1") and a Phase 6 checklist; not a 5 because the validate→fix→retry feedback loops of the top anchor are not present (and not really needed for a design/guidance skill).

4 / 5

Progressive Disclosure

Clear overview body with well-signaled, verified one-level-deep references (8 real files in references/), content appropriately split (scaffolding code in references, decisions inline), and a dedicated "Reference files" index plus inline "→" pointers for easy navigation.

5 / 5

Total

17

/

20

Passed

Description

95%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 pairs explicit trigger phrases with a concrete statement of the skill's orchestration role and the deployment/tool options it navigates. It is third-person, complete, and distinct; minor tightening of the action list is the only possible improvement.

DimensionReasoningScore

Specificity

Lists several concrete orchestration actions — "interrogates the user about their use case", "determines the right deployment model (remote HTTP, MCPB, local stdio)", "picks a tool-design pattern", "hands off to specialized skills" — with only minor gaps in coverage of tangible outputs.

4 / 5

Completeness

Explicitly answers both what ("entry point for MCP server development" with the interrogate/determine/pick/handoff loop) and when (concrete quoted trigger phrases), matching the anchor for clearly answering both.

5 / 5

Trigger Term Quality

Comprehensive natural-language triggers users would actually say: "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", plus "building something with the Model Context Protocol" — broad synonym coverage.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche as the MCP-build entry point/router with distinct MCP-specific triggers; positioning as the router that "hands off to specialized skills" keeps conflict risk with sibling skills minimal.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
anthropics/claude-plugins-official
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.