Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.
Nothing to run from here
FamilyLore is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
9
tools declared
remote
at its publisher
—
calls last 7d
What it does
Reads handwritten family letters in old scripts and translates them, with notes on what they meant.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http familylore-mcp https://familylore.ai/mcp
# 2 — ask your agent for something these tools do
# real_letters, script_guide, read_letter and 6 more
FamilyLore costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
FAAll 1 server
familylore1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http familylore-mcp https://familylore.ai/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
9 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
FamilyLore's shelf of 16 real handwritten letters from 1758 to 1943, each with FamilyLore's reading: the transcription in the original script, an English translation, and notes on what the letter meant at the time. Use this when someone wants to see a real historical letter: one written in a given script (such as Kurrent, Sütterlin or old Russian cursive), in a given language, from a period or nea
| Parameter | Type | Required | Notes |
|---|---|---|---|
| letter | no | A letter's id from this tool's list, such as de-1858-kilian, for that letter's whole reading | |
| script | no | The handwriting: German Kurrent, Sütterlin, Russian, Ukrainian, Polish, English, Latin, Swedish, French, Hebrew | |
| language | no | The letter's language: German, English, Latin, Russian, Polish, Ukrainian, Swedish, French, Hebrew | |
| period | no | I · The age of the quill (1750–1800); II · Emancipations and emigrations (1830–1866); III · The long 19th century ends (1875–1914); IV · Field post (1914–1945) | |
| year | no | Letters nearest this year first |
FamilyLore's guide to the 137 letters of five old handwriting styles: Russian cursive, German Kurrent, Sütterlin, Hebrew cursive, American cursive. For one letter: how it was written (its forms, with images), what to look for, the letters it is mistaken for and how to tell them apart, and printed copybook plates where FamilyLore has them. Use this when someone asks how a letter was written in one
| Parameter | Type | Required | Notes |
|---|---|---|---|
| letter | no | The letter: as written (ѣ, G, ך), by name (yat, alef), or as transliterated | |
| hand | no | The handwriting: Russian cursive, German Kurrent, Sütterlin, Hebrew cursive, American cursive |
Read a photo of an old handwritten letter, postcard or document with FamilyLore: the transcription in its own script, a translation and notes on what it meant then. Use it when the person attaches a photo of a handwritten page and asks what it says. It reads pre-1918 Russian and Ukrainian cursive, German Kurrent and Sütterlin, and Yiddish. It needs the person's FamilyLore account and uses one page
| Parameter | Type | Required | Notes |
|---|---|---|---|
| photo | no | The photo of the page the person attached | |
| page_id | no | A page already on FamilyLore that hasn't been read, from FamilyLore's own photo upload | |
| language | no | The letter's language, if the person says it or it is plain: ru_uk = Russian or Ukrainian, de_kurrent = German (Kurrent or Sütterlin), yi = Yiddish. Leave it out and FamilyLore tells. | |
| year | no | The year it was written, if the person knows it roughly (1912 for 'about 1912') | |
| target_language | no | The language to translate it into: en (English), de (German), ru (Russian). English if left out. |
The reading of a page in the person's FamilyLore account: the transcription in its own script with the words FamilyLore was unsure of marked, the translation, notes on what it meant, how sure the reading is, and the page's link. Use it with the page id read_letter answered, to show the reading once it is done or to see whether it is still being read.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| page_id | string | yes | The page's id, from read_letter or FamilyLore |
Where a page's reading is, for FamilyLore's card while the page is read.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| page_id | string | yes | The page's id |
The pages in the person's FamilyLore account, newest first: each letter's title, language, the date it was added, whether it has been read, and its page id. Use it when the person asks about letters they have read on FamilyLore; pass a page id to get_reading for that letter's reading.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | How many pages to list, newest first |
Ask FamilyLore a question about one page in the person's account: what a phrase meant then, who someone was, what the letter says about something. The answer comes with the letter's lines it rests on, or says that the letter doesn't say. Use it with a page id from read_letter, my_letters or get_reading, once the page has been read. Questions the reading already answers (who is named, what the tran
| Parameter | Type | Required | Notes |
|---|---|---|---|
| page_id | string | yes | The page's id, from read_letter, my_letters or get_reading |
| question | string | yes | The question about the letter, in the person's words |
How many pages the person's FamilyLore account has left to read: today for a free account, this month otherwise, and when more come. Reading a page in the chat uses the same allowance as on the site.
No parameter schema on file.
A one-time link where the person sends FamilyLore the photo of a page, for FamilyLore's card.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| language | no | The letter's language, if known | |
| year | no | The year it was written, if known | |
| target_language | no | The language to translate it into: en (English), de (German), ru (Russian). English if left out. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install FamilyLore or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.7.0 · scanned 30 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digest180864b53dcb4295ceb11078e34fa4df5a158c2fd884959d19519cec59b369da
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| real_letters | no tags | |
| script_guide | no tags | |
| read_letter | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| get_reading | no tags | |
| reading_status | no tags | |
| my_letters | no tags | |
| ask_letter | no tags | |
| my_allowance | no tags | |
| upload_slot | state-write | state-write: declares readOnlyHint: false |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest180864b53dcb4295
Scanned2026-10-30
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.7.0.
1.7.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish FamilyLore can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.