Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.
What Led To 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.
What it does
Living, source-backed timelines of long-running events, with a quote and source per entry.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http what-led-to-mcp https://whatledto.com/mcp
# 2 — ask your agent for something these tools do
# list_timelines, get_timeline, get_entry and 4 more
What Led To costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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.
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 what-led-to-mcp https://whatledto.com/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
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.
7 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.
Every timeline on the site with its topic, tags, entry count, date range, last update and a short summary. Start here to find the slug for get_timeline.
No parameter schema on file.
One timeline in full: TL;DR, dated entries newest first with sources and quotes, relations between entries, links to other timelines, what to watch next and open questions. Pass since=YYYY-MM-DD to get only entries dated on or after that day (what changed recently).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | Timeline slug, from list_timelines or a page URL (/events/<slug>). |
| since | string | no | Only entries dated on or after this day. Pass the updated_at you last saw to get what changed since. |
| limit | integer | no | Most recent entries to return (default 60). |
One dated entry in full: its summary, type, the parties it names, every source with the outlet, the publication date and the verbatim quote it was read from, plus the relations and cross-timeline links it takes part in. Use it after search_entries or get_timeline has found an entry and you need the exact wording and source URL to cite. Entry ids are unique within a timeline, not across the site, s
| Parameter | Type | Required | Notes |
|---|---|---|---|
| slug | string | yes | The timeline the entry sits on. |
| id | integer | yes | The entry's id on that timeline: the id field of a search_entries result or a get_timeline node, and the number in a page's #n<id> fragment. |
Everything the site records about one company, person or regulator across every timeline: its role on each, the parties it most often appears alongside, and every dated entry that names it, newest first, with sources. Use it instead of search_entries when you want one actor's whole history rather than a keyword match. Returns at most limit entries, with total_entries saying how many exist; a party
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Party id: a lowercase slug such as nvidia, jensen-huang or federal-reserve. search_entries results and timeline entities carry it, and the parties that have a page are listed under parties in /index.j |
| limit | integer | no | Entries to return, newest first (default 40). |
Find dated entries across every timeline by keywords, party id, timeline slug and date range. Every keyword must match (title, summary, party or timeline name); results are ranked, newest first among equals. Returns the entry text and url; call get_entry for quotes and sources.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | no | Keywords. Every one must match, in the entry's title, summary, a party name or the timeline name; omit it to browse by filter alone. |
| party | string | no | Only entries naming this party id. |
| timeline | no | Only entries on this timeline slug. | |
| from | string | no | Earliest entry date to include. |
| to | no | Latest entry date to include. | |
| limit | integer | no | Results to return (default 20); total says how many matched. |
Scheduled dates the timelines are watching — earnings, rulings, launches, rule deadlines — each with why it matters, the timeline it belongs to and a source where one exists. Use it to answer what happens next across the site, rather than reading each timeline for its own catalysts. Returns the dates from today to the horizon, oldest first, echoing back today and horizon; a date known only to the
| Parameter | Type | Required | Notes |
|---|---|---|---|
| days | integer | no | How far ahead to look, in days from today (default 90). |
| timeline | string | no | Only dates belonging to this timeline slug. |
Answer a why/how question as a chain: an ordered set of dated, sourced entries from the timelines with one line on why each led to the next, written by the editor rather than generated. Returns the best-matching chain with every step's entry (URL, date, summary, sources), or, when no chain fits, the questions that do exist and how to research the answer with the other tools.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| question | string | yes | The question in plain words, e.g. "Why did Nvidia become so dominant in AI?" |
| since | string | no | Also return what changed on the chain since this day (its changelog entries after it); pass the updated_at you last saw. |
- 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 What Led To or to call it, at any volume.
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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
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 1.1.0.
No release note was published with this version.
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.
Any signed-in account that does not publish What Led To can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.