Privacy policy
What information Forecall collects, why, who receives it, how long it is kept, and how to have it shown, corrected or deleted.
Last updated: 2026-10-16
On this page
This policy explains how 株式会社みらいスタジオ (Mirai Studio, Inc.; "we") handles information in
Forecall: the website at forecall.dev, the dashboard at app.forecall.dev, the API at
api.forecall.dev, the Failure KB at mcp.forecall.dev and the forecall command-line tool. We handle personal information under Japan's
Act on the Protection of Personal Information.
What we collect
- Your account: your email address, your name and GitHub login when you sign in with GitHub, and the language you choose. We do not keep your GitHub avatar. Signing in with GitHub asks only for your public profile and email address.
- Your organization: its name, its members and their roles, and on the Team plan the email addresses its owners and admins invite, with who invited each.
- Sign-in sessions: the IP address and browser of each signed-in session, kept with the session.
- What you submit: the tool definitions you paste or register, your servers' details, their scores, for evaluations the test utterances written from your tools and each model's answers, and for rewrite proposals the descriptions proposed and which tools the models called with them.
- Claims and official answers: the npm package your organization proves it publishes, with the token it puts in public to prove it, and the answers your organization's owners and admins write to the Failure KB's records of that package, with who last changed each. An answer is published with its record under the package's name; neither your organization's name nor the writer's is shown.
- Monitoring (on the paid plans): whether to email your organization's owners, the webhook address you enter, and the outcome of each weekly check.
- What your agents send to the Failure KB (mcp.forecall.dev, with an Agents key): reports of
failures (the server's and the tool's names, the error text, the workaround and notes, the names,
types and lengths of the call's arguments but never their values, and the model, client and
server version), confirmations and disputes of workarounds, and lookups (kept as a hash of what
was looked up, with the records returned). Before anything is stored, secrets, email addresses,
file paths, IP addresses and identifiers are replaced by placeholders such as
<SECRET>. Redaction recognizes known forms only, so agents are asked not to send raw data. - The sensor, only if you add it with
forecall setup --sensor: after each call of another MCP server's tool in Claude Code, the result's text, redacted on your computer and again by us and cut to 2,000 characters, with the server's and the tool's names, the arguments' names, types and lengths, and the client's name. - API keys: only a hash of each key and its first eight characters, to tell keys apart. The key itself is shown once and never stored.
- Usage: the units your organization uses, what each evaluation cost us, and a log of API keys created and revoked (without IP addresses).
- Payments (on the paid plans): Stripe's identifiers for your organization and its payments. Card details go to Stripe, never to us.
- Visits: for each request to the website, categories only (the kind of page, the language, whether the visitor is a person or a bot, the kind of site it came from, the response's status). We do not record IP addresses, the full address of the page, or cookies in these statistics.
forecall lint scores tool definitions on your computer and sends nothing to us, and
forecall dump connects only to the server you name. The command-line tool sends us something
only through the sensor, and only once you add it.
How we use it
We use this information to provide the service: to sign you in, to score and evaluate your tools and propose better descriptions, to evaluate the new versions of monitored servers and tell your organization's owners and its webhook when a model's accuracy drops or the units run out, to show your results to your organization, to show its members each other's names, email addresses and roles, to email the invitations it sends, to count usage against your plan, to bill paid plans, to answer your questions, to run the Failure KB (to judge whether a report or an observation is a failure, a duplicate or spam, or may still hold a secret; to publish the records that agents of two other organizations reproduced, without saying who reported them; to publish an official answer with its record under the package's name; and to show anonymous counts of observed failures by public server), to keep the service secure and stop abuse (for instance by counting requests per IP address for rate limits), and to understand, in aggregate, how the service is used so we can improve it. We do not sell personal information, and we do not use your content to train models.
Who receives it
We share information only with the companies that help us provide the service, for that purpose:
| Company | What it does for us | What it receives |
|---|---|---|
| Cloudflare, Inc. (United States) | Runs the website, dashboard and API, sends sign-in, invitation and notification emails, stores backups, and relays requests to AI models | Everything the service handles, while it runs on Cloudflare |
| Neon, Inc. (United States) | Hosts the database, in Singapore | Everything stored in the database |
| GitHub, Inc. (United States) | Signs you in when you choose GitHub | The sign-in request |
| Anthropic, PBC and OpenAI, L.L.C. (United States) | Run the AI models of an evaluation and of a rewrite proposal, and write the test utterances and the proposed descriptions. For the Failure KB, OpenAI turns error texts into embeddings to find similar failures, and Anthropic translates published records between English and Japanese | Your tool definitions, the tools of any distractor servers you choose, the test utterances, the proposed descriptions and which tools the models called; the redacted error texts of reports; the workarounds and notes of published records |
| TypeSafe AI, Inc. (United States) | Judges the Failure KB's reports, confirmations and sensor observations, predicts a known failure before a call, and narrows down the descriptions of a rewrite proposal (its model jev) | The redacted reports, confirmations and observations, the records they are compared with, for a prediction the tool's definition and the arguments' shape, and for a rewrite proposal the tools' descriptions and argument names, with the tools' names replaced by symbols, and the test utterances |
| Stripe, Inc. (United States) | Takes payments for the paid plans | Your email address, your organization's name and your payment details |
| Google LLC (United States) | Measures visits to the public website (Google Analytics) | What the page on external transmission lists |
| Product Hunt, Inc. and Ory Group LLC (Orynth) | Show their badges on the public website | What the page on external transmission lists |
Requests to Anthropic's and OpenAI's models go through Cloudflare's AI Gateway with its logs turned off, so the gateway keeps no copy of your tool definitions; requests to jev go to TypeSafe directly. Each provider handles the data under its terms for API customers: Anthropic, OpenAI, TypeSafe. We disclose information to others only when the law requires it or with your consent.
To check a claim, the dashboard reads the package's public data from the npm registry and GitHub, sending them only the package's and the repository's names. When you enter a webhook for monitoring, we post its notices (the server's name, how each model's accuracy changed, and links to the dashboard) to that address, and the service behind it handles them under its own terms.
Outside Japan
These companies are outside Japan, most of them in the United States, and the database is in Singapore. Before relying on a company outside Japan, we check that its terms commit it to protect personal information to a standard equivalent to Japanese law. The Personal Information Protection Commission publishes information on the laws of other countries. You can ask us for more detail on these measures.
Cookies
- On the dashboard, a session cookie keeps you signed in, and a cookie protects forms against cross-site requests. Both are used only by app.forecall.dev.
- On the website, a cookie lets the browser that made a linter result delete it, for 30 days, and a cookie protects forms.
- On the public website only, Google Analytics and the badges set their own cookies, as the page on external transmission describes. The dashboard and the result pages load nothing from them.
How long we keep it
| Information | Kept |
|---|---|
| A linter result made without signing in | 30 days, or until the browser that made it deletes it |
| Your account, your organization and what it registered | Until you delete them, or ask us to |
| Sign-in sessions | 7 days from the last use |
| Invitations to an organization | Until accepted, declined or revoked, and at most 7 days, with a day's margin to delete |
| What your agents sent to the Failure KB | As long as the KB holds the records it concerns |
| Claims and official answers | Until they are released or taken back, or the server or organization is deleted |
| Sensor observations | 30 days; one we make into a record lives on as that record |
| Visit statistics | 3 months |
| Database backups | Up to 7 days in the database's history, and up to 56 days in encrypted weekly backups |
When you ask us to delete your account, we delete it and the organizations you are the only member of, with everything they registered (their claims and official answers included, which leave the public pages), within 30 days. You leave the organizations that have other members, and what you registered there stays with them; if you are such an organization's only owner, we ask you to make another member owner first, and otherwise make its longest-standing admin or member the owner. Copies in the backups disappear as the backups expire, within 56 days. What your agents sent to the Failure KB stays, without any link to you or your organization: records are knowledge shared with every agent, with secrets and identifiers removed. Ask us to remove a record that should not be there. Records of the sign-in, invitation and notification emails sent to you are kept by Cloudflare under its own policy. To remove Forecall's access to your GitHub account, revoke it in GitHub's settings.
Your rights
You can ask us to show you the personal information we hold about you, to correct it, to stop using it or to delete it, and to show you the records of its provision to others. Write to support@forecall.dev from the address you sign in with; we will answer without delay, as the law requires.
Security
All connections are encrypted. API keys and one-time tokens are stored as hashes, sign-in tokens from GitHub are encrypted, backups are encrypted with a key only we hold, and copies of the data used for testing have personal information replaced first. Access to the production systems is limited to the people who run the service.
Children
The service is meant for developers and is not directed at children under 16.
Changes
We will publish any change to this policy on this page with the date it takes effect, and tell you in advance of a change that affects how we use your information.
Contact
株式会社みらいスタジオ (Mirai Studio, Inc.), person responsible: Hiroki Nomura (野村弘樹). Our address is disclosed on request. support@forecall.dev