A testing and improvement workflow for MCP servers, which let AI assistants call external tools. It checks whether tools have clear schemas and whether Claude chooses the right tool for a request.

Use it to inspect MCP tool schemas, test tool selection, diagnose tool confusion, and improve tool descriptions.

It finds confusing tool definitions and selection mistakes before they cause unreliable assistant behavior.

eval-mcp — Skill for Claude Code and Codex by pproenca

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add pproenca/dot-skills --skill eval-mcp

Clone the repo

git clone --depth 1 https://github.com/pproenca/dot-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/pproenca/dot-skills/eval-mcp/github.svg)](https://agentmods.dev/skills/pproenca/dot-skills/eval-mcp)

Your own site

<a href="https://agentmods.dev/skills/pproenca/dot-skills/eval-mcp"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/eval-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/pproenca/dot-skills/eval-mcp"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/eval-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,308 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00074	$0.02308
Opus 5	$0.00037	$0.01154
Sonnet 5	$0.00015	$0.00462
Haiku 4.5	$0.00007	$0.00231

Measured 5d ago against content hash 9a21243770ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

eval-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/analyze-schemas.sh, scripts/fetch-tools.sh, scripts/grade-selection.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/.experimental/eval-mcp/SKILL.md · 300 lines

How it starts

The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evaluate MCP Tools

Tool descriptions are prompt engineering — they land directly in Claude's context window and determine whether Claude picks the right tool with the right arguments. This skill makes tool quality measurable and improvable instead of guesswork.

Three levels of testing, each building on the last:

Static Analysis — deterministic schema quality checks (no Claude calls)
Selection Testing — does Claude pick the right tool for each intent?
Description Optimization — iterative improvement based on confusion patterns

When to Apply

User wants to check if their MCP tool schemas are well-designed
User wants to test whether Claude selects the right tools for user intents
User is debugging tool confusion (Claude picks the wrong tool)
User wants to optimize tool descriptions for better selection accuracy
User has finished scaffolding with build-mcp-server and wants to validate quality

Workflow Overview

Phase 1: Connect → Phase 2: Static Analysis → Phase 3: Selection Testing → Phase 4: Optimize
                                                            ↑__________________________|

Phase 4 loops back: apply rewrites → refetch schemas → retest → compare accuracy.

Prerequisites

Node.js >= 18 — required for the MCP Inspector CLI (npx)
jq — required for schema analysis scripts
A running MCP server — the server must respond to tools/list. Use build-mcp-server/scripts/test-server.sh to verify connectivity first.

Phase 1 — Connect & Inventory

Connect to the user's MCP server and fetch the tool schemas.

1a: Get connection details

Ask the user how to reach their server:

HTTP/SSE: URL (e.g., http://localhost:3000/mcp)
stdio: spawn command (e.g., node dist/server.js)

1b: Fetch tool schemas

bash scripts/fetch-tools.sh <url-or-command> <transport> <workspace>/tools.json

This calls tools/list via the MCP Inspector CLI and saves the schemas.

Read the full file on GitHub · 300 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

5d ago First seen · 300 lines · 74 tokens per session scan A 9a21243770ef

Subscribe to this mod's changes

eval-mcp is a skill published in the GitHub repository pproenca/dot-skills (205 stars, last pushed 24d ago), licensed MIT. It adds 74 tokens to every session and 2,308 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Building agents Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

eval-mcp