AI & Machine Learning

quantifyme.ai

Manages machine learning model training, deployment, and strategy generation.

1 endpoint13 known toolsFirst detected May 22, 2026Last detected September 10, 2026

ENDPOINT 1

https://mcp.quantifyme.ai/mcp

No auth detected

MCP server metadata

Name: quantifyme
Version: 0.1.0

Capabilities

experimentalpromptsresourcestools

Server instructions

QuantifyMe is a no-code quant trading platform. A trial API key is created automatically for this session — no signup. TO DEPLOY: call `one_shot` EXACTLY ONCE, passing the user's request as `prompt` (their words) plus `symbol`/`timeframe` if given. Do NOT pre-decide presets or community strategies, and do NOT ask the user 'existing or custom?' first — the platform routes automatically: a VAGUE request ('deploy a 15min EURUSD model', 'generate a strat') deploys a proven COMMUNITY strategy; a SPECIFIC rule-based description ('buy when RSI < 30') generates a fresh one. NEVER call one_shot more than once for one request (extra calls create duplicate deploy cards). `one_shot` returns a job_token immediately and the LIVE CARD then streams progress and renders the backtest chart by itself. After it returns, call `get_deploy_result(job_token)` ONCE to get the final stats as text so you can summarize — you do NOT need `get_model_chart` (the live card already shows the chart). If `get_deploy_result` returns source='community', tell the user it deployed a PRE-EXISTING strategy by @<author> (built by an AI agent or user), share the live_url as the Live dashboard link, and ASK whether they'd like to GENERATE A CUSTOM strategy instead (only then call one_shot again, with their rules as the prompt). Use `list_models` / `list_deployed` to inspect state; `find_strategy` is available if a user explicitly wants to browse for a match.

Known tools 13

one_shot

End-to-end deploy: generate strategy → train → deploy live.

Inferred read-only

get_deploy_result

Wait for a `one_shot` deploy to finish and return its final result.

Inferred read-only

link_account

Link this chat to the user's existing QuantifyMe account.

Inferred read-only

list_models

List the user's trained models with pre-computed train/test stats.

Inferred read-only

list_deployed

List the user's currently deployed (live) models.

Inferred read-only

top_up

Fund your QuantifyMe credits with crypto (USDC) — no signup, no human, no card.

Inferred read-only

generate_strategy

Generate Python strategy code (no training/deploy).

Inferred read-only

browse_community

Browse the public community leaderboard of published strategies, ranked by a composite performance score (best first).

Inferred read-only

find_strategy

Find an existing PROVEN strategy that matches a plain-English idea, so you can offer the user a choice — deploy the existing one, or generate a fresh custom one.

Inferred read-only

get_strategy_code

Get the actual Python code behind a community leaderboard strategy.

Inferred read-only

get_quote

Get the latest price for a G7 FX pair — a quick "what's it at now" check.

Inferred read-only

get_model_chart

Visualize a trained model's backtest — a cumulative-return chart + trade log + stats.

Potential side effects

stream_test

Diagnostic: test whether LIVE data streaming works in this client.

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.quantifyme]
url = "https://mcp.quantifyme.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "quantifyme": {
      "type": "http",
      "url": "https://mcp.quantifyme.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: quantifyme
Remote MCP URL: https://mcp.quantifyme.ai/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": {
    "quantifyme": {
      "url": "https://mcp.quantifyme.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "quantifyme": {
      "type": "http",
      "url": "https://mcp.quantifyme.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "quantifyme",
  "transport": "streamable-http",
  "url": "https://mcp.quantifyme.ai/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.