Koskamo

What Led To MCP

An official Model Context Protocol server providing access to source-backed timelines of technology, gaming, and business events. It allows AI agents to list timelines, retrieve specific entries with verbatim quotes and sources, search across entries, and access structured data about parties and upcoming events without requiring authentication.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

What Led To MCP logo, by What Led ToVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by What Led To
MCP endpoint (Streamable HTTP)
https://whatledto.com/mcp
Vendor documentation

What its tools do

7 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

7 of 7 have a description · 0 of 7 declare behavior hints · 6 of 6 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to whatledto.com ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Retrieve detailed timelines of long-running events with source citations
  • Search for specific entries across all timelines using keywords or dates
  • Access structured JSON data about companies, people, and regulators
  • Get verbatim quotes and sources for fact-checking and citation

Source and maintenance

Vendor evidenceRegistry 1.1.0

Protocol and capabilities

Server
whatledto 1.4.1
MCP protocol negotiated in check
2025-11-25
Tools
7 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

For a why or how question ("why did X become dominant", "what led to Y"), call ask first: it returns an editor-written chain of dated, sourced entries when one exists, and otherwise the questions that do exist. A chain's steps are ordered by argument, not by date: each step carries its date and a group (the strand of the argument), strands come in argument order and steps inside a strand run forward in time, so present them in that order and do not re-sort them by date. search_entries matches keywords, so use concrete nouns (product names, company names, a law, a number) rather than abstract words like dominant or important; for a company, person or regulator, call get_party with its id to get its timelines first, then narrow search_entries by timeline. What Led To (whatledto.com) keeps living, source-backed timelines of long-running events: one page per event, one dated entry per fact, every entry with the page it was taken from and a verbatim quote, re-checked against that page before publication and reviewed by an editor. Timelines cover the technology industry (Nvidia, AMD, Intel, TSMC, OpenAI, Apple, Tesla, SpaceX, chip export controls, HBM memory) and the US economy and policy (the Fed, Social Security, Medicare, student loans, tariffs, layoffs). Use search_entries to find dated facts, get_timeline for the full story of one event (pass since= for what changed after a date), get_entry when you need the exact quote and source, get_party for everything the site knows about one company, person or regulator across timelines, and upcoming for scheduled dates. Results are JSON. When you use an entry, cite it by its url (the #n<id> fragment addresses the entry) and name the outlet the quote came from. Treat causes relations as the editors' reading of the sources, not as facts of the same standing as an entry. Do not republish whole timelines; reuse terms: https://whatledto.com/methodology#reuse

Tools

7 advertised

list_timelines — List timelines
Advertised by the server during the last successful anonymous check.

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.

list_timelines input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {}
}
get_timeline — Get a timeline
Advertised by the server during the last successful anonymous check.

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).

get_timeline input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "pattern": "^[a-z0-9-]+$",
      "description": "Timeline slug, from list_timelines or a page URL (/events/<slug>)."
    },
    "limit": {
      "type": "integer",
      "maximum": 200,
      "minimum": 1,
      "description": "Most recent entries to return (default 60)."
    },
    "since": {
      "type": "string",
      "pattern": "^\\d{4}(-\\d{2}(-\\d{2})?)?$",
      "description": "Only entries dated on or after this day. Pass the updated_at you last saw to get what changed since."
    }
  },
  "additionalProperties": false
}
get_entry — Get an entry
Advertised by the server during the last successful anonymous check.

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, so pass the slug the entry came from.

get_entry input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "slug",
    "id"
  ],
  "properties": {
    "id": {
      "type": "integer",
      "description": "The entry's id on that timeline: the id field of a search_entries result or a get_timeline node, and the number in a page's #n<id> fragment."
    },
    "slug": {
      "type": "string",
      "pattern": "^[a-z0-9-]+$",
      "description": "The timeline the entry sits on."
    }
  },
  "additionalProperties": false
}
get_party — Get a company, person or regulator
Advertised by the server during the last successful anonymous check.

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 is named when the editors listed it among an entry's parties, not merely when the name appears in the text.

get_party input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "id"
  ],
  "properties": {
    "id": {
      "type": "string",
      "pattern": "^[a-z0-9-]+$",
      "description": "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.json."
    },
    "limit": {
      "type": "integer",
      "maximum": 200,
      "minimum": 1,
      "description": "Entries to return, newest first (default 40)."
    }
  },
  "additionalProperties": false
}
search_entries — Search entries
Advertised by the server during the last successful anonymous check.

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.

search_entries input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "to": {
      "$ref": "#/properties/from",
      "description": "Latest entry date to include."
    },
    "from": {
      "type": "string",
      "pattern": "^\\d{4}(-\\d{2}(-\\d{2})?)?$",
      "description": "Earliest entry date to include."
    },
    "limit": {
      "type": "integer",
      "maximum": 100,
      "minimum": 1,
      "description": "Results to return (default 20); total says how many matched."
    },
    "party": {
      "type": "string",
      "pattern": "^[a-z0-9-]+$",
      "description": "Only entries naming this party id."
    },
    "query": {
      "type": "string",
      "maxLength": 200,
      "description": "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."
    },
    "timeline": {
      "$ref": "#/properties/party",
      "description": "Only entries on this timeline slug."
    }
  },
  "additionalProperties": false
}
upcoming — Upcoming dates
Advertised by the server during the last successful anonymous check.

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 month carries precision=month and is matched on the month.

upcoming input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "properties": {
    "days": {
      "type": "integer",
      "maximum": 730,
      "minimum": 1,
      "description": "How far ahead to look, in days from today (default 90)."
    },
    "timeline": {
      "type": "string",
      "pattern": "^[a-z0-9-]+$",
      "description": "Only dates belonging to this timeline slug."
    }
  },
  "additionalProperties": false
}
ask — Ask a why or how question
Advertised by the server during the last successful anonymous check.

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.

ask input schema
{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "question"
  ],
  "properties": {
    "since": {
      "type": "string",
      "pattern": "^\\d{4}(-\\d{2}(-\\d{2})?)?$",
      "description": "Also return what changed on the chain since this day (its changelog entries after it); pass the updated_at you last saw."
    },
    "question": {
      "type": "string",
      "maxLength": 300,
      "minLength": 3,
      "description": "The question in plain words, e.g. \"Why did Nvidia become so dominant in AI?\""
    }
  },
  "additionalProperties": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
572 ms
95th percentile latency
572 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 572 ms · metadata changed · 7 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http what-led-to-mcp https://whatledto.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add what-led-to-mcp --url https://whatledto.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable what-led-to-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "what-led-to-mcp": {
      "url": "https://whatledto.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "what-led-to-mcp": {
      "type": "streamableHttp",
      "url": "https://whatledto.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start what-led-to-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "what-led-to-mcp": {
      "type": "http",
      "url": "https://whatledto.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http what-led-to-mcp https://whatledto.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://whatledto.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "what-led-to-mcp": {
      "serverUrl": "https://whatledto.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like What Led To MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run What Led To MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing