Lets an AI client obtain calibrated yes/no judgments, multiple-choice selections, or numerical scores for single items or batches of up to 1000 rows.
Also known as foreverworks/mcps, @foreverworks/mcp-typesafe
- Stars
- 5
- Tools
- 3
- Downloads, 30 days
- 678
- Latest version
- 0.1.3
- Last commit
- Nov 16, 2026
- License
- MIT
What is TypeSafe MCP?
TypeSafe lets an AI client obtain calibrated yes/no judgments, multiple-choice selections, or numerical scores for single items or batches of up to 1000 rows. It exposes 3 tools, such as health, ask, ask_batch.
Summary generated from the project's README
About TypeSafe MCP server
TypeSafe provides an interface for AI assistants to obtain calibrated, typed judgments through the Jev model. It allows users to request yes/no probabilities, multiple-choice selections from up to 255 options, or numerical scores on custom scales. This server is designed for developers who need to triage large datasets, such as transactions, emails, or reviews, without requiring the AI to perform multi-step reasoning or text generation.
Users can process single items using the ask tool or handle batches of up to 1000 rows at once via ask_batch. The server supports reading data from JSONL files and can automatically save full results to an outbox directory. To use it, you must provide a TypeSafe account and an API key via the TYPESAFE_API_KEY_FILE environment variable. It is a read-only service where costs are determined by input tokens, and responses typically arrive in about half a second.
What you can do with it
- 1Batch classify transactionsAn AI can sort hundreds of credit card transactions into specific categories like groceries or transport.
- 2Triage support communicationsA developer can use the server to determine the urgency of incoming emails and assign them to the correct department.
- 3Identify high-risk customersYou can rate customer reviews to find the specific individuals most likely to churn.
- 4Filter specific data rowsThe server can extract only the items from a large dataset that meet certain criteria or confidence thresholds.
Written from the project's README. Every use case is checked against a quote from it.
How to install TypeSafe MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall TypeSafe MCP in Claude Code
$ claude mcp add --env 'TYPESAFE_API_KEY_FILE=<TYPESAFE_API_KEY_FILE>' typesafe -- npx -y @foreverworks/mcp-typesafeInstall TypeSafe MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"typesafe": {
"command": "npx",
"args": [
"-y",
"@foreverworks/mcp-typesafe"
],
"env": {
"TYPESAFE_API_KEY_FILE": "<TYPESAFE_API_KEY_FILE>"
}
}
}
}Install TypeSafe MCP in VS Code
.vscode/mcp.json
{
"servers": {
"typesafe": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@foreverworks/mcp-typesafe"
],
"env": {
"TYPESAFE_API_KEY_FILE": "<TYPESAFE_API_KEY_FILE>"
}
}
}
}Install TypeSafe MCP in VS Code CLI
$ code --add-mcp '{"name":"typesafe","type":"stdio","command":"npx","args":["-y","@foreverworks/mcp-typesafe"],"env":{"TYPESAFE_API_KEY_FILE":"<TYPESAFE_API_KEY_FILE>"}}'Install TypeSafe MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"typesafe": {
"command": "npx",
"args": [
"-y",
"@foreverworks/mcp-typesafe"
],
"env": {
"TYPESAFE_API_KEY_FILE": "<TYPESAFE_API_KEY_FILE>"
}
}
}
}Install TypeSafe MCP in Codex
$ codex mcp add typesafe --env 'TYPESAFE_API_KEY_FILE=<TYPESAFE_API_KEY_FILE>' -- npx -y @foreverworks/mcp-typesafeInstall TypeSafe MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.typesafe] command = "npx" args = ["-y", "@foreverworks/mcp-typesafe"] [mcp_servers.typesafe.env] TYPESAFE_API_KEY_FILE = "<TYPESAFE_API_KEY_FILE>"
Install TypeSafe MCP in Gemini CLI
$ gemini mcp add -s user -e 'TYPESAFE_API_KEY_FILE=<TYPESAFE_API_KEY_FILE>' typesafe npx -- -y @foreverworks/mcp-typesafeInstall TypeSafe MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"typesafe": {
"command": "npx",
"args": [
"-y",
"@foreverworks/mcp-typesafe"
],
"env": {
"TYPESAFE_API_KEY_FILE": "<TYPESAFE_API_KEY_FILE>"
}
}
}
}TypeSafe MCP tools 3
Detected from the READMEhealthaskask_batch
| health | — | |
| ask | — | |
| ask_batch | — |
Configuration
TYPESAFE_API_KEY_FILERequiredPath of a file holding your TypeSafe API key.
| Name | Description | |
|---|---|---|
| TYPESAFE_API_KEY_FILE | Path of a file holding your TypeSafe API key. | Required |
Automated checks
Ran Nov 12, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSNot checked
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubTypeSafe MCP server
Ask TypeSafe's Jev for typed, calibrated judgments from
your AI assistant: how likely a yes/no statement is to hold, which of your
options fits, or where something sits on your own scale. Put the same
questions to one state or to up to 1000 rows at once, so the assistant can
triage postings, transactions or emails without reading each one. Every tool
is a read: nothing changes anywhere, and no tool is money.
You need a TypeSafe account and an API key from its console. Calls are billed by input tokens, a fraction of a cent each, and Jev answers in about half a second.
What you can ask
- "Go through the 300 postings in postings.jsonl and list the remote senior roles, with how sure Jev is of each."
- "Is this support email urgent, and which team should take it: billing, technical or sales?"
- "Sort last month's 600 card transactions into groceries, transport, software or other, and count each."
- "Rate these 40 reviews on how likely the customer is to leave, and show me the ten most at risk."
- "Which of these passages answer 'how do I reset my password'? Flag the ones Jev is unsure about for me to read."
Install
With Claude Code:
claude mcp add typesafe -e TYPESAFE_API_KEY_FILE="<path to API key file>" -- npx -y @foreverworks/mcp-typesafe
Claude Desktop (Settings, Developer, Edit Config) and most other clients read the same command as JSON:
{
"mcpServers": {
"typesafe": {
"command": "npx",
"args": ["-y", "@foreverworks/mcp-typesafe"],
"env": {
"TYPESAFE_API_KEY_FILE": "<path to API key file>"
}
}
}
}
Each runs the published package on Node 22.19 or newer. VS Code and the Claude Desktop bundle ask for TYPESAFE_API_KEY_FILE as they add the server. Cursor reads it from your environment instead (${env:TYPESAFE_API_KEY_FILE}), so set it before you start Cursor. Configuration says what it holds.
From a clone
git clone https://github.com/foreverworks/mcps.git && cd mcps
npm ci && npm run build
claude mcp add typesafe -e TYPESAFE_API_KEY_FILE="<path to API key file>" -- node "$PWD/servers/typesafe/dist/index.js"
In a JSON configuration, the command is node and its one argument the full path of servers/typesafe/dist/index.js. To share one running copy between several clients over HTTP, see docs/deploying.md.
Configuration
| Variable | Required | Meaning |
|---|---|---|
TYPESAFE_API_KEY_FILE |
yes | File holding the API key. For a local run, TYPESAFE_API_KEY may hold the key itself instead. |
TYPESAFE_MODEL |
no | The model a call uses when it names none. Default jev-latest, which tracks the newest Jev. |
TYPESAFE_BASE_URL |
no | Default https://api.typesafe.ai. |
TYPESAFE_OUTBOX_DIR |
no | Where ask_batch with save writes its JSONL. Default outbox/ in the state folder. Files are written 0640, so a deployment can share the folder with the user's group. |
TYPESAFE_STATE_DIR |
no | The state folder; the default is in docs/configuration.md. |
Without a key the server still starts and lists its tools, and each call
answers a config error naming the variable. ask_batch reads an
items_file from MCP_FILE_ROOTS; that and the other variables every server
shares are in docs/configuration.md.
Getting an API key
- Sign in at https://console.typesafe.ai and open Keys.
- Create a key and write it to a file only you (or the server's user) can read.
- Point
TYPESAFE_API_KEY_FILEat that file.
Give each deployment its own key, so you can revoke one alone and tell them apart on the console's usage page. Only a key from TypeSafe's own console works; a reseller's key works only through the reseller's gateway.
First run
Ask your assistant to run TypeSafe's health check. It answers with the API
it talks to, the default model, and the models your key reaches. A missing key
shows up here as config, a refused one as auth, before any batch starts.
Tools
read changes nothing; every tool here is a read (billing by input tokens is metering, not a payment).
| Tool | Access | What it does |
|---|---|---|
health |
read | Whether the key is present and accepted, and which models it reaches. |
ask |
read | Every question about one state in one round trip; the answers as TypeSafe returns them, less a Score's legend. |
ask_batch |
read | The same questions over up to 1000 states, typed in or from a file, 8 in flight by default: a summary per question and compact rows, with save the full rows as JSONL in the outbox. Optional act, review or abstain verdicts from your thresholds, and where, top and counts to list only the rows that matter. |
A question is a noul (the probability that a yes/no statement holds), a
choice (one of 2 to 255 options, with a probability for each) or a score
(the state placed on 2 to 10 levels you order from lowest to highest).
Troubleshooting
config. No key: set TYPESAFE_API_KEY_FILE to a file holding a key from
console.typesafe.ai/keys, or TYPESAFE_API_KEY for a local run.
auth. TypeSafe refused the key. Check it still exists at
console.typesafe.ai/keys, and replace the file if it was revoked.
input. The question cannot be answered as asked; the message names the
field (a choice needs at least two options, a score 2 to 10 levels). Above 20
rows, every row needs an id.
rate_limited. TypeSafe is still throttling or overloaded after the
server's own retries. Wait a minute, or send the batch with a lower
concurrency.
api. Any other refusal, a 5xx that outlived its retries, or no connection
(status 0). Retry once; if it persists, run health and read the server's log.
drift. TypeSafe answered in a shape this server does not know (its SDK's
types may have moved on). Please report it.
How it works
The network. An evaluation has no side effect, so every request
(POST /v1/systemone, GET /v1/models) may repeat: a 5xx or a dropped
connection is tried again, and a 429 or 529 ("overloaded") waits as a rate
limit, as TypeSafe's SDK does. A call times out after a minute. Every answer
is checked against the SDK's types (@typesafe-ai/sdk, types only, in
src/domain/schema.ts).
Batches. A batch goes on past a failed row and reports it, but stops at a failure that would fail every row (no key, a refused key), so a thousand rows do not each earn a 401. Answers join their rows by id, required above 20 rows: a position is only safe to join on while you can check the rows by eye.
Rows from a file. Instead of typing rows into items, pass items_file:
JSONL with one {"id", "state"} object per line, or a JSON array of them, by
path inside MCP_FILE_ROOTS (or as content_base64 with its sha256, from a
script). The rows never pass through a model, so they cannot change on the
way; a malformed row fails the call with its line number before anything is
sent. The reply names the file's sha256 and size.
Verdicts. With thresholds for a question, each row's answer gets act
(sure enough to act on), review (a person should look) or abstain (do not
use it), from the answer's certainty: for a noul |p - 0.5| x 2 (p 0.95 and
p 0.05 are both 0.9), for a choice or a score the confidence TypeSafe returns.
The certainty is rounded down to three places, the number the row shows, and
must be strictly above act_above to act and above review_above to be
reviewed. Once thresholds are tuned, pin model to a versioned Jev:
jev-latest can move under them.
Choosing rows. where lists only the answered rows meeting every
condition you give per question: true or false for a noul (a yes is
p >= 0.7, a no p <= 0.3, as the summary counts them), labels for a choice,
min and max on the value a row shows, and verdict. top keeps the k
rows with the highest p or score for one question, and counts tallies the
answers of the rows where kept; the summary still covers every row. Every
condition is checked before a request is sent, so a label that is not an
option fails the call, not a thousand rows.
npx tsx scripts/smoke.ts drives the built server against the real API, for
a few thousand input tokens: health, one ask per question type, a
five-row batch saved to the outbox, and one input failure that never reaches
TypeSafe.
Limitations
- Judgments only. Jev writes no text and does no multi-step reasoning.
Keep rules, lookups and arithmetic in code, and threshold the probabilities
(
thresholdsdoes it per question). wherejoins conditions with "and" only. For "or", read the rows from a saved JSONL, or ask a question that states the alternatives.- At most 1000 rows a call; split a larger set.
- A batch's reply lists every row unless
listsays otherwise. For a large batch, passlist: "none"or"failed"withsave, and read the JSONL.
Other servers for TypeSafe
Searched 2026-10-15. TypeSafe publishes none: its GitHub organisation has the SDKs, agent skills and an n8n node. Two community servers are on npm:
typesafe-mcp: stdio under Bun, the key in an environment variable, batches over files matched by a glob, with an act, review or abstain verdict per answer.@y0usaf/typesafe-mcp: stdio, oneevaluatetool.
This one exists for what neither offers: it also runs over HTTP as a service
of its own, with its key in a file the calling client never reads; it saves a
batch's full answers as JSONL in an outbox and names the file's SHA-256; and
it follows the conventions every server in this repository shares. Its
verdicts and its where, top and counts follow typesafe-mcp's, with
thresholds set per question rather than per call.
TypeSafe MCP questions
How do I add TypeSafe MCP to Claude Code?
Run claude mcp add --env 'TYPESAFE_API_KEY_FILE=<TYPESAFE_API_KEY_FILE>' typesafe -- npx -y @foreverworks/mcp-typesafe in your terminal. Add --scope user to make it available in every project.
How do I add TypeSafe MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does TypeSafe MCP provide?
It exposes 3 tools, including health, ask, ask_batch.
What kind of answers can I get from TypeSafe?
You can get 'noul' (probability of a yes/no statement), 'choice' (one of 2 to 255 options), or 'score' (a value on a 2 to 10 level scale).
How many rows can I process at once?
You can process up to 1000 rows in a single batch request.
Does using TypeSafe change my data?
No, all tools provided by the server are read-only operations.