Reach120 MCP Server
OfficialClick 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., "@Reach120 MCP Server Can you show me a TOEFL writing prompt?"
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.
Reach120 MCP server
An MCP server that gives an AI agent a governed path to the Reach120 TOEFL iBT practice API: fetch Writing practice prompts, and score a learner's written response.
Reach120 is an independent practice platform. It is not affiliated with, endorsed by, or administered by ETS. TOEFL® is a registered trademark of ETS. Reach120 is not affiliated with, endorsed by, or approved by ETS.
Tools
Tool | What it does | Cost |
| List Writing practice prompts, with the id used to score against one | Reads stored rows, runs no model |
| Fetch one prompt with its full scenario or discussion context | Reads a stored row, runs no model |
| Score a written response, returning an automated practice score and a short rationale | Runs the scorer; metered against your key |
Related MCP server: agent-validator-mcp-server
You bring the key
This server carries no credential. It forwards the key you place in
REACH120_API_KEY and returns the API's answer unchanged.
That is a design decision, not an omission. Every limit that matters lives on the server side of the API and is evaluated on every call — a per-key request window, a per-key daily scoring allowance, and a service-wide spending gate. A client that enforced its own limits would only be enforcing them on people who chose to keep using the client, so this one enforces none and cannot be a way around any of them. Delete this package and call the endpoint directly and you get identical refusals.
There is no unauthenticated scoring path. An agent with no key receives a refusal naming where a key comes from, and nothing is sent.
Request a key and read the full limit, error-code and version policy at https://www.reach120.com/developers.
Install
This package is not published on npm. The install path is this repository, and
it is the only one — @reach120/mcp-server does not resolve on the public npm
registry and no other package name stands in for it.
npx -y github:reach120/reach120-mcpnpm compiles the TypeScript during that install through the prepare script, so
there is no separate build step.
Or clone it and run it from source:
git clone https://github.com/reach120/reach120-mcp.git
cd reach120-mcp
npm install
npm run build
node dist/index.jsConfigure
Claude Desktop (claude_desktop_config.json), Claude Code, or any MCP client that
speaks stdio:
{
"mcpServers": {
"reach120": {
"command": "npx",
"args": ["-y", "github:reach120/reach120-mcp"],
"env": {
"REACH120_API_KEY": "r120_live_your_key_here"
}
}
}
}Variable | Required | Default | Meaning |
| yes | — | Your Reach120 API key. Tools refuse without it. |
| no |
| Point at another deployment. |
| no | see | Per-request timeout, in milliseconds. |
What a refusal looks like
Limits refuse with a machine-readable code rather than degrading. A call that hits
the key's daily allowance is not quietly scored on a cheaper engine and handed back
as if it were the engine you asked for — the code names what happened, and the
error table on /developers says what each one means.
Verify it locally
npm install
npm run build
npm run verifynpm run verify starts the built server over stdio, completes a real MCP
handshake with the SDK client, prints the advertised tools, and calls one tool
without a key to show the refusal path.
Scores are practice feedback
score_writing_response returns automated practice feedback produced by Reach120.
It is not an ETS score and is not reported on the official scale. This README deliberately does not name the scale the number is on: that fact is published beside a mandatory limitation the claims ledger requires, which a package page cannot render. The response shape is documented on https://www.reach120.com/developers.
TOEFL® is a registered trademark of ETS. Reach120 is not affiliated with, endorsed by, or approved by ETS.
Licence
MIT. See LICENSE.
Available Tools
3 toolsget_practice_promptFetch one TOEFL Writing practice promptARead-only
Fetch a single Writing practice prompt by its id, including the full scenario or discussion context a learner is asked to respond to. Reads a stored row and runs no model. TOEFL® is a registered trademark of ETS. Reach120 is not affiliated with, endorsed by, or approved by ETS.
Inputs: item_id (required).
list_practice_promptsList TOEFL Writing practice promptsARead-only
List Writing practice prompts from the Reach120 bank — the Write an Email task and the Writing for an Academic Discussion task. Returns each prompt with the id you pass to score_writing_response. Reads stored rows and runs no model, so it spends nothing against your daily scoring allowance, but it does count against your per-minute request window. TOEFL® is a registered trademark of ETS. Reach120 is not affiliated with, endorsed by, or approved by ETS.
Inputs: limit, offset, task_type.
score_writing_responseScore a TOEFL Writing responseA
Score a learner's written response to a TOEFL iBT Writing task and return an automated practice score with a short rationale. The response shape, the limits and the error codes are documented at https://www.reach120.com/developers. Supply either item_id from the prompt tools, or task_type plus the prompt inline for your own coursework. This call runs an AI scorer and is metered: it draws on the daily spend ceiling attached to your API key, and refuses with a machine-readable code rather than quietly scoring on a cheaper engine when a limit is reached. Reach120 is an independent practice platform. It is not affiliated with, endorsed by, or administered by ETS. TOEFL® is a registered trademark of ETS. Reach120 is not affiliated with, endorsed by, or approved by ETS.
Inputs: response (required), prompt, item_id, task_type.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clear, distinct role: listing prompts, fetching a single prompt by id, and scoring a written response. The list/get pair follows a standard convention without meaningful overlap, and scoring is wholly separate.
All tool names follow a consistent verb_noun snake_case pattern: list_practice_prompts, get_practice_prompt, score_writing_response. The naming clearly communicates both the action and the target resource.
Three tools is well-scoped for this server's narrow purpose: browsing a fixed prompt bank and scoring responses. Each tool serves a distinct step in the workflow without redundancy.
The tool surface covers the full intended workflow: discover prompts, retrieve full prompt details, and score a response using either a bank item or inline task type. Since the prompt bank is read-only, no create/update/delete tools are necessary.
Related MCP Connectors
Turn any task into the right API calls: discover, evaluate, and integrate public APIs.
Discover, compare, route, and execute machine-accessible capabilities for AI agents.
660+ data tools for agents: TikTok, Douyin, Instagram, YouTube, X, weather, GitHub. Pay per call.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Related MCP Servers
AlicenseNot gradedqualityDmaintenanceEnables LLMs to convert documents to Google Forms, edit questions, list and publish forms, and run AI form assistant tools through the Formswrite API.MIT- AlicenseAqualityDmaintenanceEnables testing and validation of APIs for AI agent compatibility, providing scores, grades, and actionable recommendations.343 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to discover, search, and call any REST API described by an OpenAPI or Swagger document. Supports multiple API endpoints with authentication and parameter handling.14 npmMIT
- AlicenseAqualityDmaintenanceEnables AI agents to create and edit Google Docs and draft Gmail emails through natural language.7ISC