CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

instrument-mcp-server

Instrument a Node/TypeScript MCP server with Amplitude's @amplitude/mcp-analytics SDK so tool calls, sessions, and rationale are tracked as Amplitude events. Use this skill whenever the user wants to add Amplitude analytics to their MCP server, mentions "MCP Analytics", "@amplitude/mcp-analytics", "instrument my MCP server", "track MCP tool calls", "add rationale to my MCP tools", or wants agent traffic (Claude, Cursor, ChatGPT) attributed back to Amplitude. Also use for adding UTM tagging to MCP-returned links, or for troubleshooting identity/user_id mismatches between MCP events and web/mobile Amplitude data.

72

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

75%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, actionable guide that adds genuine non-obvious value (identity joinability, rationale schema injection, UTM prerequisite) while correctly deferring volatile SDK details to the fetched README. It is concise and clearly sequenced with only minor narrative padding and no explicit error-recovery loop.

Suggestions

Tighten the motivational prose in Step 3 ('Unlike a human clicking a button…') to a single sentence to improve token efficiency.

Add an explicit validate→fix→retry loop for the Step 1-2 invariants (e.g. 'if an invariant fails, re-fetch the README's relevant section, correct, and re-verify') to push workflow_clarity toward 5.

Consider extracting the UTM helper and rationale schema snippets into a bundled scripts/ or references/ file so the SKILL.md body stays a lean overview.

DimensionReasoningScore

Conciseness

Mostly efficient and focused on what Claude doesn't already know (SDK invariants, schema-injection convention, UTM prerequisite), with only minor narrative padding such as the motivational 'Unlike a human clicking a button…' framing.

4 / 5

Actionability

Steps 3-4 provide copy-paste-ready TypeScript (zod rationale field, instrumentTool wrapper, addUtmParams), while steps 1-2 deliberately defer install/API to the README—mostly executable with a justified gap.

4 / 5

Workflow Clarity

A clearly ordered four-step flow with required/recommended labels, invariants to verify, and a 'Common mistakes to flag' checklist; lacks an explicit validate→fix→retry feedback loop, but the operations are not destructive/batch so the cap at 3 does not apply.

4 / 5

Progressive Disclosure

Well-organized single-file guide with clear section headers and one-level-deep external references (the SDK README and Amplitude docs); no nested skill references and content is appropriately scoped, though no bundle files exist to split further.

4 / 5

Total

16

/

20

Passed

Description

100%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, third-person description that states concrete capabilities and pairs them with explicit, natural trigger phrases and a clear use-when clause. It is specific, distinct, and comprehensive with no noticeable gaps.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—'track tool calls, sessions, and rationale', 'add UTM tagging', 'troubleshoot identity/user_id mismatches'—against a named SDK and domain, giving comprehensive coverage rather than just 1-2 actions.

5 / 5

Completeness

Explicitly answers 'what' (instrument an MCP server so tool calls/sessions/rationale become Amplitude events) and 'when' via a concrete 'Use this skill whenever…' clause with named trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger coverage including the package name '@amplitude/mcp-analytics', phrases users would say ('instrument my MCP server', 'track MCP tool calls', 'add rationale to my MCP tools'), and client names (Claude, Cursor, ChatGPT).

5 / 5

Distinctiveness Conflict Risk

Narrow niche (Amplitude analytics for Node/TypeScript MCP servers via a specific SDK) with distinct triggers and a named package, leaving minimal overlap with other skills.

5 / 5

Total

20

/

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

amplitude/builder-skills

Path

engineering-skills/skills/instrument-mcp-server/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.