Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@chatgpt-plugin-one-tool Score my WHO-5 well-being answers: 3, 3, 2, 2, 3"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A minimal MCP server with one read-only tool, written to show how small a ChatGPT plugin server can be. No framework, no dependencies, no sign-in, no storage. About 180 lines of code and 12 tests.
It comes with REVIEW.md: the step-by-step story of how our plugin Ladder by Aizhan Li went through OpenAI review and was approved for the ChatGPT plugin directory on 4 November 2026. In Russian: REVIEW.ru.md.
This repository does not contain the code of the Ladder plugin or of 108psy.com. It is a teaching example built on the same pattern.
who5_score scores the WHO-5 Well-Being Index:
five answers from 0 to 5 give a score from 0 to 100 and a band (low, reduced, normal).
The score is not a diagnosis, and the tool description tells the model so.
Why this tool: it is deterministic, needs no network or model, and still shows the parts reviewers look at: a clear description of when to use the tool and when not to, an input schema, an output schema, annotations, readable errors and safe wording for a low result.
Related MCP server: PlainGrade
npm test
npm startThen call it:
curl -s -X POST http://localhost:8787/mcp -H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"who5_score","arguments":{"answers":[3,3,2,2,3]}}}'Deploy to Cloudflare Workers with npx wrangler deploy. The endpoint is /mcp.
You can also open it in MCP Inspector.
For clients that start the server themselves, run it over stdio (npm run stdio).
In Claude Desktop, add to claude_desktop_config.json:
{
"mcpServers": {
"who5-one-tool": { "command": "node", "args": ["/path/to/chatgpt-plugin-one-tool/src/stdio.mjs"] }
}
}Or in a container: docker build -t who5-one-tool . && docker run -i --rm who5-one-tool.
src/tool.mjs: the tool definition and the scoring. Start reading here.
src/mcp.mjs: JSON-RPC over Streamable HTTP: initialize, ping, tools/list, tools/call.
src/worker.mjs: Cloudflare Workers entry.
src/node.mjs: local run on Node 18+.
src/stdio.mjs: the same server over stdio, one JSON-RPC message per line.
Dockerfile: runs the stdio server in a container.
example/plugin.json, example/mcp.json: a submission package template with review test cases.
test/mcp.test.mjs, test/stdio.test.mjs: protocol, tool and stdio tests (node --test).
Stateless. Each POST is one JSON-RPC message. No sessions, so any instance can answer.
Plain JSON, no SSE. The MCP spec allows a JSON response to a POST. GET returns 405.
Tool errors are results. Wrong input returns isError: true with a sentence the model can fix.
Protocol errors (unknown method, unknown tool) are JSON-RPC errors.
Read-only annotations. readOnlyHint: true, destructiveHint: false, openWorldHint: false.
Nothing is logged. The server never writes the answers anywhere.
The Ladder method, its structure and pilot data are described in a preprint (in Russian):
Li, A. (2026). Онлайн-самопроверка внутренних препятствий на пути к цели: структура, операционализация и пилотные данные методики «Лестница». Zenodo. https://doi.org/10.5281/zenodo.23960425
Aizhan Li, author of the Ladder method, 108psy.com. The plugin, the site and this repository were built by one person with Claude Code.
MIT, see LICENSE. WHO-5 is by the WHO Collaborating Centre in Mental Health; this repository contains only its scoring rule, not the item wording.
Scores the WHO-5 Well-Being Index. Use it when the user has answered the five WHO-5 items about the last two weeks and wants their score. Pass exactly five integers from 0 (at no time) to 5 (all of the time), in item order. Returns the score from 0 to 100 and a band: low (28 or less), reduced (29 to 50) or normal. The score is not a diagnosis. Do not use it for symptoms, illnesses or medication.
| Name | Required | Description | Default |
|---|---|---|---|
| answers | Yes | Five WHO-5 answers in item order, each an integer from 0 to 5. |
| Name | Required | Description |
|---|---|---|
| band | Yes | |
| score | Yes | |
| message | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and non-destructive behavior, so the safety profile is covered. The description adds genuinely non-obvious context: the score band cutoffs (28 or less / 29 to 50 / normal) and the clinical caveat that the score is not a diagnosis. It stops short of explaining how the raw 0-5 sum scales to 0-100, but the scoring behavior is otherwise well disclosed.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Five short sentences with the purpose first, then the trigger condition, then the input format, then the return shape, then the safety caveat. Nothing is repeated and no sentence could be dropped without losing a distinct fact.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a single-parameter scoring tool with an output schema and full annotation coverage, the description supplies everything still missing: input scaling anchors, band thresholds, and the clinical-use exclusion. No gap remains that would cause a misinvocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and already constrains the array to five integers of 0-5, so the baseline would be 3. The description earns above baseline by supplying the response anchors ('0 at no time' to '5 all of the time') and stressing item order, meaning an agent would not reverse-scale or reorder the answers.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Scores the WHO-5 Well-Being Index') and immediately scopes it to the exact input the tool consumes. An agent knows precisely what the tool produces and what it needs without opening the schema.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives an explicit when-to-use condition ('user has answered the five WHO-5 items about the last two weeks and wants their score') and an explicit when-not-to-use boundary ('Do not use it for symptoms, illnesses or medication'). No sibling tools exist, so no alternative routing is needed.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0who5_scoreScored across 1 tool
There is only one tool, so there is no possibility of misselection between competing options. Its purpose (scoring five WHO-5 item responses) is stated unambiguously, along with explicit negative guidance about what it must not be used for.
The single name `who5_score` is clear snake_case, combining a domain identifier with an action noun. With one tool there is no convention mixing to evaluate, and the name reads predictably.
The server is explicitly designed as a one-tool plugin, and that tool is a deterministic computation that fully earns its place. The surface is deliberately minimal rather than accidentally thin, though one more tool (e.g. returning the questionnaire items) would add value.
For the stated purpose of scoring WHO-5 responses, the tool covers the whole operation: input validation, 0-100 raw score, and interpretation bands. The only gap is that it cannot surface the five item texts or the band thresholds as reusable data, so an agent must supply the questionnaire itself.
Checks a public website in six areas and returns scores from 0 to 100. Free, no key needed.
WHO Regional Office for Europe — Data Warehouse API v5.
Build, publish and read scored forms and quizzes where the score picks the next screen.
Hosted MCP app for guided anxiety, depression, and well-being self-checks.