CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mcp-integration

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

Quality

83%

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

70%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 delivers highly actionable, copy-paste-ready MCP configuration guidance with a clear validated workflow and strong troubleshooting coverage. Its weaknesses are redundancy (auth/env-var content repeated across sections and duplicated with the reference files) and a broken examples/ reference, plus one internally inconsistent tool-naming example.

Suggestions

Deduplicate authentication and environment-variable content: the SSE OAuth and stdio env-var configs appear both in 'MCP Server Types'/'Environment Variable Expansion' and again in 'Authentication Patterns' — consolidate each topic once and point to references/authentication.md for depth.

Fix or remove the 'Example Configurations' section: the referenced examples/stdio-server.json, examples/sse-server.json, and examples/http-server.json files do not exist in the bundle, so either add them or drop the pointer.

State the 'document required environment variables in README' guidance once (it currently appears in Environment Variable Expansion, Token-Based auth, the validation checklist, the DO list, and the workflow) and correct the tool-naming example to match the documented format (mcp__plugin_asana_asana__create_task).

DimensionReasoningScore

Conciseness

The body is mostly concrete configuration rather than concept explanation, but it is noticeably loose: "Document required environment variables in README" appears roughly five times, OAuth and stdio env-var configurations are duplicated between the "MCP Server Types"/"Environment Variable Expansion" sections and the "Authentication Patterns" section, and the wildcard pre-allow warning is stated twice. This is more than the minor trimming of anchor 4, matching anchor 3's "could be tightened".

3 / 5

Actionability

Guidance is largely copy-paste ready: complete JSON configs for every server type, inline plugin.json syntax, allowed-tools frontmatter examples, and concrete test commands (/mcp, claude --debug). It misses a 5 due to minor gaps — the tool-naming example "mcp__plugin_asana_asana__asana_create_task" contradicts the stated format "mcp__plugin_<plugin-name>_<server-name>__<tool-name>" (which would yield "...__create_task"), and the referenced "Working examples in examples/" files do not exist in the bundle.

4 / 5

Workflow Clarity

The Implementation Workflow gives a clear 9-step sequence with explicit validation steps ("Test locally with /mcp command", "Test error cases"), backed by a Validation Checklist, a Configuration Checklist, and a Debugging section with per-symptom recovery guidance ("Tools not available: ... Run /mcp ... Restart Claude Code after config changes"). This matches the top anchor's sequence + validation + feedback loops + checklists; this is not a destructive/batch skill so no cap applies.

5 / 5

Progressive Disclosure

The three references/ files are real and clearly signaled with one-line descriptions, but the body also points to an examples/ directory (stdio-server.json, sse-server.json, http-server.json) that is missing from the bundle, and it inlines ~550 lines of server-type, authentication, and env-var detail that duplicates the dedicated reference files. Structure exists and references are signaled, but content that belongs in the reference files is inline and one reference path is broken, fitting anchor 3 better than anchor 4's "minor organization gaps".

3 / 5

Total

15

/

20

Passed

Description

91%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 with an explicit use-when clause, comprehensive natural trigger terms including synonyms and the .mcp.json filename, and a clearly named niche. Its only weaknesses are the mildly padded single-action capability statement ("comprehensive guidance") and one generic trigger phrase ("connect external service") that slightly raises conflict risk.

DimensionReasoningScore

Specificity

The description enumerates several concrete actions ("add MCP server", "configure MCP in plugin", "use .mcp.json", "connect external service") alongside the concrete domain of MCP servers in Claude Code plugins. It falls short of a 5 because the capability statement itself is a single generic action ("Provides comprehensive guidance for integrating...") with mild buzzword padding rather than a comprehensive list of distinct capabilities.

4 / 5

Completeness

It explicitly answers "when" with an opening "This skill should be used when the user asks to..." clause listing concrete trigger phrases, and answers "what" with "Provides... guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration". Both are explicit and concrete, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Trigger terms include natural user phrasings ("integrate MCP", "set up Model Context Protocol"), the full protocol name plus acronym ("Model Context Protocol"/"MCP"), a config filename (".mcp.json"), and transport types (SSE, stdio, HTTP, WebSocket). Coverage of synonyms and file extensions is comprehensive, matching the top anchor; it is not below it since no common variation is obviously missing.

5 / 5

Distinctiveness Conflict Risk

Triggers like "MCP", ".mcp.json", "${CLAUDE_PLUGIN_ROOT} with MCP", and the transport types are highly distinctive of this niche, but the generic phrase "connect external service" could plausibly fire for other integration-related skills, creating minor overlap risk (anchor 4) rather than the minimal conflict risk of anchor 5.

4 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (555 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

anthropics/claude-plugins-official

Path

plugins/plugin-dev/skills/mcp-integration/SKILL.md

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.