CtrlK
BlogDocsLog inGet started
Tessl Logo

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

91

2.21x
Quality

67%

Does it follow best practices?

Impact

93%

2.21x

Average score across 10 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./app/skills/mcp-builder/SKILL.md

The canonical home for this skill is pleaseai/mcp-dev

SKILL.md
Quality
Evals
Security

Quality

Content

56%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.

The body presents a well-sequenced four-phase process with concrete build/test commands, but much of the executable detail is offloaded to reference files that are not actually present in the bundle, and the reference section repeats links already given earlier. Fixing the missing reference files is the highest-impact improvement.

Suggestions

Add the missing ./reference/ files (mcp_best_practices.md, node_mcp_server.md, python_mcp_server.md, evaluation.md) to the bundle, or inline their essential content, so the signaled references resolve.

Consolidate the 'Reference Files' section with the Phase 1.3 links to remove the duplicated reference list and tighten conciseness.

Add a small copy-paste-ready tool scaffolding example (Zod/Pydantic schema + handler) inline so the core implementation is actionable without the missing reference files.

DimensionReasoningScore

Conciseness

Most content is useful process guidance rather than concepts Claude already knows, but the 'Reference Files' section largely duplicates the links already given in Phase 1.3 and the sitemap URL appears multiple times, so it could be tightened; this matches anchor 3 rather than anchor 2 because the padding is redundancy, not concept explanation.

3 / 5

Actionability

Concrete commands (npm run build, npx @modelcontextprotocol/inspector, python -m py_compile) and URLs are present, but the core tool-implementation guidance is high-level lists ('Create shared utilities: API client, error handling helpers') with executable code deferred to reference files, matching anchor 3's 'some concrete guidance but incomplete'.

3 / 5

Workflow Clarity

A clear four-phase sequence (Research/Planning, Implementation, Review/Test, Evaluations) with build and Inspector verification checkpoints in Phase 3 matches anchor 4; it stops short of 5 because error-recovery feedback loops are only implied, and the destructive/batch cap does not apply since server creation is not inherently destructive.

4 / 5

Progressive Disclosure

The structure intent is good—an overview with a dedicated, clearly signaled Reference Files section pointing one level deep to ./reference/*.md—but those referenced files (mcp_best_practices.md, node_mcp_server.md, python_mcp_server.md, evaluation.md) do not exist in the bundle (only scripts/ is present), so navigation is broken, matching anchor 3 over anchor 4.

3 / 5

Total

13

/

20

Passed

Description

78%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.

The description is well-constructed: it states a clear purpose, uses third person, and provides an explicit 'Use when' trigger with concrete, natural keywords. Its main limitation is that the action list stays at the domain level rather than enumerating specific capabilities.

Suggestions

Add one or two more concrete actions (e.g., 'define tool schemas, implement pagination, return structured content') to lift specificity from 3 toward 4-5.

Tighten 'integrate external APIs or services' with a more distinctive qualifier to reduce overlap with general API-integration skills.

DimensionReasoningScore

Specificity

It names the domain (MCP servers) and a couple of concrete actions ('creating high-quality MCP servers', 'integrate external APIs or services') but gives no granular action list, matching anchor 3 rather than anchor 4 which requires several specific actions.

3 / 5

Completeness

It explicitly answers both what ('Guide for creating high-quality MCP servers that enable LLMs to interact with external services through well-designed tools') and when ('Use when building MCP servers to integrate external APIs or services') with concrete trigger phrases, matching anchor 5.

5 / 5

Trigger Term Quality

Natural triggers like 'building MCP servers', 'integrate external APIs or services', and language/SDK terms (FastMCP, Node/TypeScript) give good keyword coverage, though a few common variations are missing so it stops short of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The MCP-server niche is clear with distinct triggers, but 'integrate external APIs or services' is broad enough to risk minor overlap with general API-integration skills, so it sits at anchor 4 rather than 5.

4 / 5

Total

16

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 10 missing

Warning

Total

15

/

16

Passed

Repository
ZHangZHengEric/Sage
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.