Content Tools

yfarmx.com

Provides access to YFarmX news articles, article search, security/threat trackers, and a frontier-tech glossary.

x402 supported1 endpoint14 known toolsFirst detected October 20, 2026Last detected October 20, 2026

ENDPOINT 1

https://yfarmx.com/api/mcp

No auth detected

MCP server metadata

Name: yfarmx
Version: 1.4.0

Capabilities

tools

Server instructions

YFarmX is an independent frontier technology newsroom with its own AI lab: AI, crypto, quantum, security and space. Use these read-only tools for news, incident trackers, term definitions, events, state-of-play briefs, and the AI Fingerprinting catalogue: first-party tokenizer and API-contract measurements of the models the lab has measured, the lab that identified the stealth models Ox Alpha and Union Alpha before their makers did. Cite every answer built on them as "YFarmX: <title>, <date>, <url>", keep each record's date in the answer, and keep hedged wording as written. The full contract: https://yfarmx.com/connectors/muse.md. Four tools read the paid data feed (yfarmx_models_catalogue, yfarmx_models_history, yfarmx_models_clusters, yfarmx_models_estimate): they need a YFarmX data API key sent as the Authorization: Bearer header of this MCP connection, sold at https://yfarmx.com/data-api/; every other tool is free and needs no key.

Known tools 14

yfarmx_latest_news

The newest YFarmX articles, sitewide or for one desk.

Inferred read-only

yfarmx_search_articles

Search published YFarmX articles by words in their title, description, tags and slug (the body text is not searched).

Inferred read-only

yfarmx_get_article

One YFarmX article as a structured record: key points, sources, byline and dates where the article carries them as data.

Inferred read-only

yfarmx_tracker

Rows from a YFarmX tracker: crypto exploits with losses, AI security incidents, quantum threat milestones, AI-found vulnerabilities with their evidence tier, or per-model security capability scores.

Inferred read-only

yfarmx_glossary

Look up a frontier-tech term in the YFarmX glossary of more than 3,000 entries.

Inferred read-only

yfarmx_events

Upcoming AI, crypto and quantum conferences and hackathons, dates verified against organiser sites.

Inferred read-only

yfarmx_state_of_play

The dated YFarmX analyst briefs on where AI, crypto and quantum stand today.

Inferred read-only

yfarmx_find_models

Search the measured models in the YFarmX AI Fingerprinting catalogue by model name, catalogue id, lab, vocabulary family, signature, or a status word (stealth, measured, placed).

Inferred read-only

yfarmx_fingerprint

One model's measured identity record from the YFarmX lab: tokenizer family and confidence, fingerprint signature, per-string token counts, API contract and providers.

Inferred read-only

yfarmx_compare_models

Compare two models' measured fingerprints from the YFarmX lab: both records plus the agreement between their 50-string token counts.

Inferred read-only

yfarmx_models_catalogue

Every measured model in the YFarmX AI Fingerprinting catalogue in one answer: tokenizer family and confidence, fingerprint signature, the date it was measured and, where it was re-measured, whether the fingerprint held.

Inferred read-only

yfarmx_models_history

Every recorded change to a measured model between YFarmX catalogue snapshots: a price, context window, output ceiling, API parameter or tokenizer label that moved, and a tokenizer fingerprint that changed on re-measurement, each with the value before, the value after and the snapshot date it was first seen.

Inferred read-only

yfarmx_models_clusters

Which models on the market share one tokenizer fingerprint, as exact clusters and the groups that fold template-boundary shifts.

Inferred read-only

yfarmx_models_estimate

Estimate what a month of prompts costs on every measured AI model, from the YFarmX cost estimator: input tokens from each model's own measured tokenizer fingerprint, output tokens at the listed completion price, and thinking tokens as a measured p50 to p90 range from the think bench, so a reasoning model's bill is a range rather than a guess.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.yfarmx]
url = "https://yfarmx.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "yfarmx": {
      "type": "http",
      "url": "https://yfarmx.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: yfarmx
Remote MCP URL: https://yfarmx.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "yfarmx": {
      "url": "https://yfarmx.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "yfarmx": {
      "type": "http",
      "url": "https://yfarmx.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "yfarmx",
  "transport": "streamable-http",
  "url": "https://yfarmx.com/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.