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.
npx skills add manufactinc/manufact-cursor-plugin --skill mcp-plugin-testinggit clone --depth 1 https://github.com/manufactinc/manufact-cursor-pluginWrote 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.
[](https://agentmods.dev/skills/manufactinc/manufact-cursor-plugin/mcp-plugin-testing)<a href="https://agentmods.dev/skills/manufactinc/manufact-cursor-plugin/mcp-plugin-testing"><img src="https://agentmods.dev/badge/skills/manufactinc/manufact-cursor-plugin/mcp-plugin-testing/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.
<a href="https://agentmods.dev/skills/manufactinc/manufact-cursor-plugin/mcp-plugin-testing"><img src="https://agentmods.dev/badge/skills/manufactinc/manufact-cursor-plugin/mcp-plugin-testing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00076 | $0.01366 |
| Opus 5.5 | $0.00030 | $0.00546 |
| Sonnet 5.5 | $0.00015 | $0.00273 |
| Haiku 4.5 | $0.00008 | $0.00137 |
Grade A, and why
mcp-plugin-testing 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test an MCP server or plugin in real clients
Evals run a saved conversation against the server's production endpoint in one
or more clients, then a judge scores the result against passing criteria. They
show whether models actually discover and call the right tools, with the right
arguments, and give useful answers. They complement the publishing checklist,
which inspects protocol and metadata only (see the mcp-plugin-publishing
skill).
1. Pick the server
- Reuse organization and server IDs already established in the conversation.
- Otherwise call
list_serverswithoutorganizationIdto search every accessible organization, and confirm the server withget_server. Eval tools need both the server'sorganizationIdandserverId. - The server needs a healthy production deployment, because evals always target
the production endpoint. If it has none, use the
mcp-plugin-deployskill first. To test a branch, promote or merge it first; preview URLs are not eval targets. - If the server requires OAuth, complete
authenticate_deploymentfirst as described inmcp-plugin-publishing, so clients can connect.
2. Discover clients and models
Call get_eval_options before choosing clients. Use only what it returns:
- Inspector: the Manufact chat client. Choose any number of OpenRouter
models with
list_eval_models(filter withqueryorprovider). Each model runs as its own execution. Omitting clients uses Inspector with the default model. - Web clients (
webClients): ChatGPT and Claude on the web. Each runs once per suite with no model choice and does not enforcedisallowedTools. - Runtimes: agent harnesses such as Codex, Claude Code, or Cursor. Pick
only runtimes with
available: true, choose a model from that runtime'smodels, and tell the user about anylimitationsor thereasonit is unavailable.
Other MCP clients can still connect to the server's MCP URL, but they can't be
tested here unless get_eval_options lists them. Say so instead of implying
coverage.
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.
- 4d ago First seen · 108 lines · 76 tokens per session scan A c6214576f20a
mcp-plugin-testing is a skill published in the GitHub repository manufactinc/manufact-cursor-plugin (0 stars, last pushed 4d ago), licensed MIT. It adds 76 tokens to every session and 1,366 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-12.
mcp-plugin-testing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| mcp-plugin-testingmanufactinc/manufact-cursor-plugin | Skill | 0 | 4d ago | MIT | A | 76 | Cursor |
| create-verification-skillYeachan-Heo/oh-my-claudecode | Skill | 41k | today | MIT | A | 45 | Claude Code |
| verify-omnigentomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 100 | Claude Code, Codex |
| test-masterJeffallan/claude-skills | Skill | 12k | yesterday | MIT | A | 104 | Claude Code |
| eval-dataset-designbojieli/ai-agent-book | Skill | 58k | 1mo ago | Apache-2.0 | A | 138 | Claude Code, Codex |
| dogfoodcallstack/agent-device | Skill | 5.4k | today | MIT | A | 55 | Claude Code |
| cua-driverdavidondrej/skills | Skill | 4.3k | yesterday | MIT | A | 68 | Claude Code, Codex |