Skip to content

fermi MCP server

io.github.Kromatic-Innovation/fermiKromatic-Innovationstreamable-httpv1.2.3Scanned

Calibrated probability ranges for forecasting questions, with the assumptions behind them.

7 tools: 1 can delete or cancel things, 1 do something that can't be undone, 3 change things and 2 only read.

Tools: 1 delete, 1 irreversible, 3 write, 2 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 2
  • 4 findings

Tools listed without sign-in. Remote posture

With Anlyon

1 tool here can delete or cancel things and 1 does something that can't be undone. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the fermi MCP server can do

The fermi MCP server is published by the GitHub account Kromatic-Innovation. It has 7 tools. It can delete or cancel things (1 tool: buy_credits), do things that cannot be undone, such as sending, paying or publishing (send_feedback) and create or change data (3 tools: estimate_quantity_or_probability, record_actual and check_account_and_credits). 2 tools only read.

4 tools bring in text other people can write (estimate_quantity_or_probability, get_estimate_result, send_feedback and 1 more); 2 tools can send data out of your system (estimate_quantity_or_probability and send_feedback).

The fixed checks matched 4 findings (long-description and credentials-mention). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in, and its tools changed 4 times since Anlyon Radar first saw them.

Last scanned Nov 21, 2026, version 1.2.3.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

7 tools

Deletes or cancels 1Claude Code: deny
  • buy_creditsCharges the user's saved payment card to buy Fermi credits, or, if no card is saved yet, returns a checkout link instead and charges nothing.Reads text others write1 finding

    Why it is in this group

    • The description's first verb is "charge": a word that usually means money moves, which cannot be taken back.
    • The server marks it destructive (destructiveHint: true).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description is 2,106 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: ".... Cost: real money -- charges the saved card $0.50 per credit. Needs an account."

      What this check looks for
    Description, as the server wrote it
    Charges the user's saved payment card to buy Fermi credits, or, if no card is saved yet, returns a checkout link instead and charges nothing. Use this when the user asks to buy or top up Fermi credits, including before the dollar amount is named and while the user is not signed in. Never call it on your own initiative. The user's authorization: before the call, tell the user the number of credits and the dollar charge (credits times $0.50; for example 10 credits is $5.00). The user's yes to that, or a request that already names both the credits and the dollar amount, authorizes that one call: make it then, without asking again, and make it again after a sign-in. It does not authorize a second purchase. A request that names only the credits ("buy 10 credits") is still a request for this tool: state the dollar charge, and make the call on the user's yes. A call refused because the user is not signed in charges nothing, so the call made again after the sign-in is still that one purchase. Returns credits_purchased, new_balance and payment_status after a charge. With no saved card, the first call charges nothing: it returns a checkout_url where the user saves a card in a browser, so that call needs no separate warning about a charge. Then call this again. One call can buy at most 100 credits; a larger request is refused and nothing is charged. Credits pay for estimates on an account (see estimate_quantity_or_probability for tier costs). To see the balance first, use check_account_and_credits. When the user is not signed in, call the tool as normal. If the user's app supports sign-in, it will ask the user to sign in, and you can call the tool again after that. Do not send the user to their connector or app settings to sign in first. Only if the user's app cannot sign in (a REST caller, or an agent with no connector), create an account with POST https://fermi.kromatic.com/api/v1/accounts (it returns an api_key once; a new account starts with 3 credits) and pass that key as the api_key argument. Cost: real money -- charges the saved card $0.50 per credit. Needs an account.

    Annotations the server declares

    • destructiveHint: true
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
    • title: Buy Fermi credits with your saved card
Can't be undone 1Claude Code: ask
  • send_feedbackSends a short report about Fermi to the team that builds it.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "send_feedback" says "send": a word for sending, and what is sent cannot be taken back.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe name "send_feedback" says "send": it sends or publishes something to other people.
    Description, as the server wrote it
    Sends a short report about Fermi to the team that builds it. Use this when the user wants to report a problem, an error, an estimate that looks wrong, something no Fermi tool can do, a missing option, or copy that was confusing, or when the user says yes after you offered to send a report. The team reads every report and uses it to fix problems and decide what to build. Send a report only when the user asks for one or agrees to one. When the user asks you to tell the Fermi team about something, that request is their go-ahead: send the report without asking again. If a report might help, ask first, for example: "Want me to send Fermi's team a short note about this?" If the user says no or does not answer, do not send it. Put several points in one report. Only message is required. Fill in the other fields that apply so the team can act without guessing. Write in your own words. Never include personal data (names, email addresses, company names), the user's own numbers or private context, secrets or keys, or the conversation transcript; describe the question and any wrong result in general terms instead. Add sender_email only if the user wants a reply; no copy is sent to it. If you are signed in, your account id is included. Returns status "sent". Cost: free. Works without an account.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
    • title: Send feedback or a bug report to the Fermi team
Changes things 3Claude Code: ask
  • check_account_and_creditsReports who you are to Fermi and what you can spend: whether you are using Fermi without an account or with one, your credit balance or free estimates left today, and what each tie…No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Reports who you are to Fermi and what you can spend: whether you are using Fermi without an account or with one, your credit balance or free estimates left today, and what each tier costs. Use this before a paid estimate to check the price or balance, after one to see what is left, or when the user asks about credits, free estimates or pricing. Returns billing (principal "anonymous" or "account", how you authenticated, credit_balance, anonymous_estimates_remaining_today and anonymous_quota_resets_at), tiers (credit_cost, delivery "sync" or "async" and whether it is available without an account, per tier), price_per_credit_usd, and recent_transactions (the account's last 10 credit movements; null without an account). Cost: free. Checking never spends credits and never uses up a free estimate.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: Check your account, credits and free estimates left
  • estimate_quantity_or_probabilityEstimates an uncertain number, or the probability that an event happens by a date, from a question in plain language, and returns a calibrated range and probability distribution.Reads text others writeCan send data out1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.callback_url): a request to a URL can carry data to whoever runs it.

    Findings

    • Info

      The description is 3,344 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...me question. `credits_charged` and `billing` in the result report what was spent."

      What this check looks for
    Description, as the server wrote it
    Estimates an uncertain number, or the probability that an event happens by a date, from a question in plain language, and returns a calibrated range and probability distribution. Use this when the user asks how much, how many, how big or how long something is or will be (market size, cost, count, price, duration), or asks a yes/no question about the future: "will X happen by <date>?", "what are the odds / chances / likelihood of X?". For a yes/no question, set unit to "probability (0-1)": point_estimate is then Fermi's best probability that the event happens (0.15 means 15%), and estimation_interval is how far that probability could plausibly be off (e.g. 0.05 to 0.35); the beta distribution describes the same uncertainty. There is no separate yes/no verdict. Returns point_estimate, estimation_interval (low/high: the range that should contain the true value, or for a yes/no question the true probability, with probability coverage_probability, default 90%), the fitted distribution (distribution_family and distribution_parameters), reasoning_summary, assumptions, estimate_id, and next_steps.simulate. To combine several estimates into a model with a time axis and get percentiles, NPV or payback out, feed them into neumann (https://neumann.kromatic.com) as simulation root nodes -- every successful estimate carries a next_steps.simulate block with the arguments already prepared. (neumann is Kromatic's companion Monte Carlo simulation server; fermi itself does not simulate.) The neumann URLs above are production. A non-production fermi still emits next_steps.simulate against its own configured neumann base URL, so read that block rather than these links whenever you are not on the production host. Tiers: 1 = fast, answers in the same call, no web search, and the only tier available without an account. 2 = grounded, answers in the same call, searches the web. 3 = deep research, runs in the background: the call returns status "pending" and an estimate_id; read the result later with get_estimate_result. Not for: running a simulation or combining estimates (use neumann); reading prediction-market prices or placing bets; financial, medical or legal advice. Tiers 2 and 3, and tier 1 once the free estimates are used up, need an account. If the user wants one of these and is not signed in, call the tool as normal. If the user's app supports sign-in, it will ask the user to sign in, and you can call the tool again after that. Do not send the user to their connector or app settings to sign in first. Only if the user's app cannot sign in (a REST caller, or an agent with no connector), create an account with POST https://fermi.kromatic.com/api/v1/accounts (it returns an api_key once; a new account starts with 3 credits) and pass that key as the api_key argument. Cost: without an account, 3 free tier-1 estimates per UTC day; once they are used up, calls are refused with a sign-in requirement until 00:00 UTC. With an account, tier 1/2/3 costs 1/3/10 credits ($0.50/$1.50/$5.00 at $0.50 per credit). Tiers 1 and 2 charge only if the estimate succeeds, and a failed call does not use up a free estimate; tier 3 charges when it starts and refunds if it fails. Every call is a new estimate and is charged again, even for the same question. `credits_charged` and `billing` in the result report what was spent.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
    • readOnlyHint: false
    • title: Estimate a number, or the probability an event happens by a date
  • record_actualRecords what actually happened for an estimate you made earlier, so the estimate can be compared with reality later (the calibration loop).No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Records what actually happened for an estimate you made earlier, so the estimate can be compared with reality later (the calibration loop). Use this when the real-world outcome of a question you estimated is now known. Returns estimate_id and the stored actual (value, unit, recorded_at, notes, source_inputs). Calling it again with the same values stores the same record. Account only: you can record an actual only on an estimate made by your own account, and an anonymous call is refused with a sign-in requirement. To find an estimate_id, use list_my_estimates. When the user is not signed in, call the tool as normal. If the user's app supports sign-in, it will ask the user to sign in, and you can call the tool again after that. Do not send the user to their connector or app settings to sign in first. Only if the user's app cannot sign in (a REST caller, or an agent with no connector), create an account with POST https://fermi.kromatic.com/api/v1/accounts (it returns an api_key once; a new account starts with 3 credits) and pass that key as the api_key argument. Cost: free, but account only: recording never spends credits or a free estimate, and without an account the call is refused with a sign-in requirement.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: false
    • title: Record the actual outcome (account only)
Only reads 2Show 2 read-only tools
  • get_estimate_resultReads one estimate you already requested, by its estimate_id.Reads text others write2 findings

    Why it is in this group

    • The name "get_estimate_result" says "get": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description mentions "credentials".

      Matched text

      description: "...only read estimates made with the same credentials. Without an account you are recognised..."

      What this check looks for
    • Info

      The input schema at properties.api_key.description mentions "credentials".

      Matched text

      inputSchema.properties.api_key.description: "...in). Estimates are visible only to the credentials that made them."

      What this check looks for
    Description, as the server wrote it
    Reads one estimate you already requested, by its estimate_id. Use this when a tier-3 (deep research) estimate came back with status "pending" and you want to know whether it is finished, or to show an earlier estimate again. Tier-3 results are only delivered this way (or to a callback_url, which chat clients usually cannot receive). Returns status: "pending" (with retry_after_seconds: how long to wait before asking again), "completed" (with the same fields a finished estimate returns), or "failed" (with error_detail; any credits taken are refunded). You can only read estimates made with the same credentials. Without an account you are recognised by IP address and browser or client, so a different network or client may not find the estimate. To find an id you lost, use list_my_estimates. Not for: making a new estimate. Cost: free. Reading a result never spends anything.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
    • readOnlyHint: true
    • title: Get the result of an estimate you already requested
  • list_my_estimatesLists the past estimates on your account, newest first.No findings

    Why it is in this group

    • The name "list_my_estimates" says "list": a word for reading.
    Description, as the server wrote it
    Lists the past estimates on your account, newest first. Use this when the user wants to find an earlier estimate ("what did I estimate last week?") or has lost an estimate_id. Returns estimates, each with estimate_id, created_at, question, unit, target_horizon, point_estimate, estimation_interval, distribution_family and status; and next_offset, the offset of the next page, or null on the last page. For an estimate's full detail, pass its estimate_id to get_estimate_result. Estimates made without an account cannot be listed. When the user is not signed in, call the tool as normal. If the user's app supports sign-in, it will ask the user to sign in, and you can call the tool again after that. Do not send the user to their connector or app settings to sign in first. Only if the user's app cannot sign in (a REST caller, or an agent with no connector), create an account with POST https://fermi.kromatic.com/api/v1/accounts (it returns an api_key once; a new account starts with 3 credits) and pass that key as the api_key argument. Cost: free, but account only: without an account the call is refused with a sign-in requirement.

    Annotations the server declares

    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
    • readOnlyHint: true
    • title: List your past estimates (account only)

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out2
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:58 UTC, unchanged since Nov 6, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
4
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • HighThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (1 destructive, 1 irreversible, 2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://fermi.kromatic.com/mcp: tools/list returned 6 tools to an anonymous client, including buy_credits (destructive), send_feedback (irreversible), estimate_quantity_or_probability (write), check_account_and_credits (write)

    What this check looks for

Posture changes

  1. Nov 6, 2026
    • Tools that change things, listed without credentials: 3 to 4
  2. Oct 29, 2026
    • HTTP status of an anonymous initialize: 202 to 200
    • Tools that change things, listed without credentials: 2 to 3
    • Legacy HTTP+SSE transport: yes to no

Findings

Matches of fixed checks, with the text they matched.

4 info

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. Tools5 changed.~5 changedView diff
  2. Tools1 added, 1 changed.+1 added~1 changedView diff
  3. Tools5 added, 3 removed, 1 changed.+5 added−3 removed~1 changedView diff
  4. PostureRemote posture changed. Tools that change things, listed without credentials: 3 -> 4.View diff
    • Tools that change things, listed without credentials: 3 to 4
  5. PostureRemote posture changed. HTTP status of an anonymous initialize: 202 -> 200; Tools that change things, listed without credentials: 2 -> 3; Legacy HTTP+SSE transport: yes -> no.View diff
    • HTTP status of an anonymous initialize: 202 to 200
    • Tools that change things, listed without credentials: 2 to 3
    • Legacy HTTP+SSE transport: yes to no
  6. Tools1 added, 3 changed.+1 added~3 changedView diff
    • Added:get_estimateOnly reads
    • Changed:buy_creditsDeletes or cancelstitleannotations
    • Changed:estimateChanges thingstitledescriptionannotations
    • Changed:feedbackChanges thingstitleannotations

Install

Pinned to version 1.2.3. Values in angle brackets are yours to fill in.

claude mcp add --transport http fermi https://fermi.kromatic.com/mcp
claude mcp add --transport http fermi https://fermi.kromatic.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__fermi__get_estimate_result",
      "mcp__fermi__list_my_estimates"
    ],
    "ask": [
      "mcp__fermi__estimate_quantity_or_probability",
      "mcp__fermi__record_actual",
      "mcp__fermi__send_feedback",
      "mcp__fermi__check_account_and_credits"
    ],
    "deny": [
      "mcp__fermi__buy_credits"
    ]
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as fermi. Review it before you use it.

Capability tags behind 4 rules
  • mcp__fermi__estimate_quantity_or_probability untrusted-input, outbound
  • mcp__fermi__get_estimate_result untrusted-input
  • mcp__fermi__send_feedback untrusted-input, outbound
  • mcp__fermi__buy_credits untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.Kromatic-Innovation/fermi/verify?hash=e071030089d2be1b62ce17d4f7fefe888fe1313dca4a628f85af9f29837bf7fb" | jq -e '.changed == false'

Pinned hash e071030089d2, from Nov 21, 2026, 13:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.Kromatic-Innovation/fermi/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.Kromatic-Innovation/fermi
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.Kromatic-Innovation/fermi.svg)](https://radar.anlyon.com/servers/io.github.Kromatic-Innovation/fermi)

Source: MCP Registry · repository. Synced Nov 21, 2026, 13:17 UTC.

fermi MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the fermi MCP server safe?

No scan can promise that. What its definitions show: 7 tools, 5 of which can change, send or delete something, and 4 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the fermi MCP server delete data?

Yes. 1 tool can delete, cancel or revoke something: buy_credits.

Can the fermi MCP server do things that cannot be undone?

Yes. 1 tool can send, pay, publish or merge: send_feedback.

What tools does the fermi MCP server have?

7 tools: 1 destructive, 1 irreversible, 3 write, 2 read. buy_credits, send_feedback, estimate_quantity_or_probability, record_actual, check_account_and_credits, get_estimate_result and list_my_estimates.

Does the fermi MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the fermi MCP server send data to outside services?

2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): estimate_quantity_or_probability and send_feedback.

Has the fermi MCP server changed its tools?

Yes, 4 times since Anlyon Radar started tracking it, most recently on Nov 21, 2026. Every change is on this page and in its Atom feed.