fastmcp

Build MCP servers in Python with FastMCP to expose tools, resources, and prompts to LLMs. Supports storage backends, middleware, OAuth Proxy, OpenAPI integration, and FastMCP Cloud deployment. Prevents 30+ errors. Use when: creating MCP servers, or troubleshooting module-level server, storage, lifespan, middleware, OAuth, background tasks, or FastAPI mount errors.

Install with Tessl CLI

npx tessl i github:jezweb/claude-skills --skill fastmcp

What are skills?

Overall
score

81%

Review — 82%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 12 / 16 Passed

Validation for skill structure

SKILL.md

Review

Evals

Discovery

100%

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

This is an excellent skill description that clearly defines its purpose (building MCP servers with FastMCP in Python), lists specific capabilities and features, and provides explicit trigger guidance for both creation and troubleshooting scenarios. The description uses proper third-person voice and includes highly specific technical terms that users would naturally use.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Build MCP servers', 'expose tools, resources, and prompts', and names specific features like 'storage backends, middleware, OAuth Proxy, OpenAPI integration, FastMCP Cloud deployment'. The 'Prevents 30+ errors' claim is concrete and measurable.	3 / 3
Completeness	Clearly answers both what ('Build MCP servers in Python with FastMCP...') and when with an explicit 'Use when:' clause covering creation scenarios and specific troubleshooting contexts like 'module-level server, storage, lifespan, middleware, OAuth, background tasks, or FastAPI mount errors'.	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'MCP servers', 'Python', 'FastMCP', 'storage', 'middleware', 'OAuth', 'background tasks', 'FastAPI mount errors'. These are specific technical terms users would naturally use when seeking this skill.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with clear niche: 'MCP servers', 'FastMCP', 'Python' combination is very specific. The detailed error categories (module-level server, lifespan, FastAPI mount) further distinguish it from generic Python or server skills.	3 / 3
	Total	12 / 12 Passed

Implementation

64%

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

This is a highly actionable skill with excellent executable code examples and comprehensive error coverage. However, it suffers from being overly long and monolithic - the version changelogs, 30 error catalog, and detailed OAuth patterns would be better served as separate reference files. The skill would benefit from explicit validation checkpoints in multi-step workflows like deployment and OAuth setup.

Suggestions

Move the 30 Common Errors section to a separate ERRORS.md file and reference it from the main skill with a brief summary of the most critical 5-6 errors

Extract version changelogs (v2.14.x, v3.0.0) to a CHANGELOG.md or MIGRATION.md file, keeping only breaking changes warnings inline

Add explicit validation steps to multi-step workflows: e.g., 'After OAuth setup, verify with: curl -X POST http://localhost:8000/oauth/token...' or 'Test deployment with: fastmcp test server.py'

Condense the OAuth section by moving provider-specific configurations to a separate OAUTH_PROVIDERS.md reference file

Dimension	Reasoning	Score
Conciseness	The skill is comprehensive but includes some unnecessary verbosity, particularly in the version changelog sections and the extensive error catalog. While most content is useful, sections like 'What's New in v2.14.x' and 'What's New in v3.0.0' could be condensed or moved to separate reference files.	2 / 3
Actionability	Excellent actionability with fully executable code examples throughout. Every major concept includes copy-paste ready Python code, specific CLI commands, and concrete configuration examples. The error solutions provide direct fixes with before/after code comparisons.	3 / 3
Workflow Clarity	While individual code examples are clear, multi-step workflows lack explicit validation checkpoints. The OAuth setup, deployment process, and ASGI integration sections describe steps but don't include verification commands or feedback loops for error recovery.	2 / 3
Progressive Disclosure	The skill is a monolithic document with all content inline. While it has clear section headers, the 30 errors section, version changelogs, and detailed OAuth patterns could be split into separate reference files. References to external docs exist but internal structure could benefit from splitting.	2 / 3
	Total	9 / 12 Passed

Validation

75%

Warnings & errors only

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

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (897 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata' field is not a dictionary	Warning
license_field	'license' field is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	12 / 16 Passed

Reviewed: about 1 month ago

Table of Contents

Discovery Implementation Validation

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.