write-mcp-host-eval

write-mcp-host-eval is a skill for Claude Code, Codex from gleanwork/mcp-server-tester. It costs 64 tokens per session (4,319 once invoked), scanned A, original, MIT.

A test generator for MCP servers, which let AI assistants discover and use tools. It uses real language models to simulate how an assistant chooses tools from ordinary requests.

In plain words
What is it for?
For creating test scenarios and runners that check tool discovery, parameter selection, and whether descriptions match actual behavior.
Why use it?
It reveals whether tool names, descriptions, and inputs are clear enough for an AI assistant to use without hints. This catches problems that fixed input-and-output tests cannot.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/gleanwork/mcp-server-tester/write-mcp-host-eval
Any agent
npx skills add gleanwork/mcp-server-tester --skill write-mcp-host-eval
Clone the repo
git clone --depth 1 https://github.com/gleanwork/mcp-server-tester

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.

agentmods badge for write-mcp-host-eval

README.md
[![agentmods](https://agentmods.dev/badge/skills/gleanwork/mcp-server-tester/write-mcp-host-eval.svg)](https://agentmods.dev/skills/gleanwork/mcp-server-tester/write-mcp-host-eval)
Your own site
<a href="https://agentmods.dev/skills/gleanwork/mcp-server-tester/write-mcp-host-eval"><img src="https://agentmods.dev/badge/skills/gleanwork/mcp-server-tester/write-mcp-host-eval.svg" alt="Measured on agentmods" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.04319
Opus 5 $0.00032 $0.02159
Sonnet 5 $0.00013 $0.00864
Haiku 4.5 $0.00006 $0.00432

Measured 5d ago against content hash b0370263bac2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

write-mcp-host-eval 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.

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/write-mcp-host-eval/SKILL.md · 563 lines

How it starts

The opening of the file, as written. The whole thing — 563 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Write MCP Host Simulation Evals

Generate LLM host simulation evals for MCP servers using @gleanwork/mcp-server-tester. In mcp_host mode, a real LLM receives a natural language scenario and decides which MCP tools to call — testing tool discoverability, parameter clarity, and description quality.

When to Use mcp_host Mode

Use mcp_host mode when you need to verify:

  • Does the LLM know which tool to call for a given task?
  • Does the LLM fill in parameters correctly without hints?
  • Does the tool description accurately represent what the tool does?

Use direct mode instead for:

  • Regression testing known inputs/outputs (faster, free, deterministic)
  • Testing tool logic and error handling
  • Schema validation

mcp_host mode calls a real LLM API. Each test costs ~$0.003–0.02 depending on the provider and tool count.

Prerequisites

Install the Vercel AI SDK and your provider package:

# Pick your provider
npm install ai @ai-sdk/anthropic    # Anthropic
npm install ai @ai-sdk/openai       # OpenAI
npm install ai @ai-sdk/google       # Google
npm install ai @ai-sdk/mistral      # Mistral
npm install ai @ai-sdk/azure        # Azure OpenAI
npm install ai @ai-sdk/deepseek     # DeepSeek
npm install ai @ai-sdk/xai          # xAI (Grok)
npm install ai @ai-sdk/google-vertex  # Vertex AI (Anthropic models)
npm install ai @openrouter/ai-sdk-provider  # OpenRouter

Set the corresponding API key environment variable (e.g., ANTHROPIC_API_KEY, OPENAI_API_KEY).

Step 1 — Understand the Case Structure

mcp_host cases differ from direct mode cases:

Field Direct mode mcp_host mode
mode "direct" (default) "mcp_host" (required)
toolName Required Not used
args Required Not used
scenario Not used Required — natural language prompt
mcpHostConfig Not used Provider, model, host type
expect Response assertions Tool call assertions + response assertions

Read the full file on GitHub · 563 lines

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.

  1. 5d ago First seen · 563 lines · 64 tokens per session scan A b0370263bac2

Subscribe to this mod's changes

write-mcp-host-eval is a skill published in the GitHub repository gleanwork/mcp-server-tester (19 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 4,319 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens