Skip to content
Forecall logo

Forecall

Scores MCP tool descriptions with a static linter and runs evaluations to measure whether agents call tools correctly.

Actively maintained

Developer toolsEvaluationFree tier
forecall.dev ↗XGitHubProduct Hunt
Open forecall.devAlternativesSet it up for my teamIs Forecall yours? Claim the card →
At a glanceswept Oct 14, 2026

2.8k installs/mo

Established

For
developers building MCP servers whose tool descriptions AI agents must choose and call correctly
Activity
Actively maintainedrelease 13 days ago · site updated 9 days ago
Company
Mirai Studio, Inc. · Domain since 2026privacy policy · domain registered
Runs as
CLI
Used for
  • score MCP tool descriptions from a tools list JSON file
  • find near-identical tool descriptions within an MCP server
  • measure how often real models call your tools correctly
Worth knowingcomputed from what we read · each with its source
Pricing

Price not read

Trial & discounts

Your datawhat they publish, each line with its page · read Oct 15, 2026

“We do not sell personal information, and we do not use your content to train models.”

privacy policy ↗

These are Forecall's own statements, read from its pages. We did not audit them. A line that is missing was not found on the pages we read; it does not mean the practice is absent.

How a program reaches itfound, not claimed · read Oct 15, 2026
  • MCP serverdev.forecall/forecall-kbverified in the MCP registry
  • Stateanswers, requires sign-inchecked 2026-10-15
  • Address to connectmcp.forecall.dev/mcp

MCP server details →

This card as JSON, for your agent →

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.

Alternatives in Developer toolsby use, among tools still maintained

Figure and bar: visits/mo, estimate · year: online since

Compare Forecall with

Pick up to two.

All 10 alternatives to Forecall →

All Developer tools tools →

Not it? Say what you need

beta

Three tools from the Atlas for the job you describe, each with what fits and what does not.

From people who use itnot part of the reading

No notes yet. What do you use Forecall for?

Sign in to leave a note
Questions this page answers
  • What is Forecall?

    Scores MCP tool descriptions with a static linter and runs evaluations to measure whether agents call tools correctly. It is listed in the Atlas under Developer tools and made by Mirai Studio, Inc.

  • Who is Forecall for?

    developers building MCP servers whose tool descriptions AI agents must choose and call correctly

  • Do people use Forecall?

    Established: 2.8k installs/mo (npm).

  • Is Forecall still maintained?

    Actively maintained: release 13 days ago · site updated 9 days ago.

  • Who owns Forecall?

    Forecall is run by Mirai Studio, Inc., per its privacy policy (2026-10-15).

  • Does Forecall train AI on your data?

    No, per its privacy policy (2026-10-15): “We do not sell personal information, and we do not use your content to train models.”

  • Is Forecall safe?

    We do not audit vendors. What Forecall publishes, read 2026-10-15: on training with your data, “We do not sell personal information, and we do not use your content to train models.”.

  • How do I cancel Forecall?

    In its own words (terms of service, 2026-10-15): “You can cancel at any time in the dashboard; the plan stays in use until the end of the month you have paid for.”

  • What are alternatives to Forecall?

    In Developer tools, by use: ServBay, FetchSandbox MCP, StackResolve, Kaiva · AI infrastructure for real systems, MCP Junction, Scalebrowser.

How we read a tool

No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.

  • Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
  • Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
  • Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
  • The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.

How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.

How we read every tool → · By INITE Atlas Desk