{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_kgmy68ysx2cc","handle":"qdf-mcp","url":"https://wellknown.network/agents/qdf-mcp","links":{"self":"https://wellknown.network/agents/qdf-mcp/record.json","html":"https://wellknown.network/agents/qdf-mcp","markdown":"https://wellknown.network/agents/qdf-mcp/record.md","api":"https://wellknown.network/api/v1/agents/qdf-mcp","status":"https://wellknown.network/api/v1/agents/qdf-mcp/status","claim":"https://wellknown.network/agents/qdf-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/qdf-mcp/claim.json","badge":"https://wellknown.network/agents/qdf-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/qdf-mcp/history","tools":"https://wellknown.network/api/v1/agents/qdf-mcp/tools"},"ard":{"identifier":"urn:air::server:qdf-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"qdf-mcp","summary":"QuantDataForge MCP servers — StrategyCreator + Open Cockpit, run locally via uvx with one API token.","description":"# qdf-mcp\n\nTwo MCP servers that let a [QuantDataForge](https://quantdataforge.com) subscriber\ndrive the platform from their own Claude Code / Claude Desktop:\n\n- **`qdf-mcp-strategy`** — *StrategyCreator*: author trading strategies in Python,\n  backtest them against QDF's 5-year 1-minute futures history (ES, NQ), and read\n  the metrics + equity curve back — all in your Claude session.\n- **`qdf-mcp-cockpit`** — *Open Cockpit*: a live, read-only window into the open —\n  which levels are armed, how each is defended tick-by-tick, plus market-state,\n  options and catalyst reads.\n\nBoth are thin HTTPS clients. All the heavy lifting (data, backtest engine, sandbox)\nruns on the QDF server. Each server scopes everything to **your personal API token**.\n\n## Setup\n\n### 1. Install `uv` (one time)\n\n`uvx` runs the servers in an isolated environment and pulls all dependencies\nautomatically — **you do not need to install any Python packages by hand.**\n\n- **Windows:** `powershell -ExecutionPolicy Bypass -c \"irm https://astral.sh/uv/install.ps1 | iex\"`\n- **macOS / Linux:** `curl -LsSf https://astral.sh/uv/install.sh | sh`\n\n(Or `pip install uv` if you already have Python.)\n\n### 2. Get your token\n\nOn the website, open **Strategy Lab → API Tokens**, click **Generate**, and copy\nthe `qdf_sk_…` token (shown once). **The same token works for both servers.**\n\n### 3. Add the servers to your Claude config\n\nPaste this into your MCP client config — Claude Desktop's\n`claude_desktop_config.json`, or a project `.mcp.json` for Claude Code — with your\ntoken in both places:\n\n```json\n{\n  \"mcpServers\": {\n    \"strategy-creator\": {\n      \"command\": \"uvx\",\n      \"args\": [\"--from\", \"qdf-mcp\", \"qdf-mcp-strategy\"],\n      \"env\": {\n        \"QDF_API_TOKEN\": \"qdf_sk_…your token…\",\n        \"QDF_API_URL\": \"https://quantdataforge.com\"\n      }\n    },\n    \"qdf-cockpit\": {\n      \"command\": \"uvx\",\n      \"args\": [\"--from\", \"qdf-mcp\", \"qdf-mcp-cockpit\"],\n      \"env\": {\n        \"QDF_API_BASE\": \"https://quantdataforge.com\",\n…","publisher":{"name":"QuantDataForge","url":null},"homepage":"https://quantdataforge.com","repository":"https://github.com/cameronsice/QuantDataForge","version":"0.3.0","license":null,"protocols":["mcp"],"tags":["backtest","claude","mcp","quantdataforge","trading"],"pricing":null,"endpoints":[{"url":"pypi:qdf-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"finance.markets","name":"Markets & Trading","confidence":1,"provenance":"declared"},{"slug":"dev.package-management","name":"Packages & Dependencies","confidence":0.859,"provenance":"derived"}],"categories":["dev","finance"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"qdf-mcp","registry":"pypi","observedAt":"2026-11-03T23:22:43.684Z","publishedAt":"2026-07-09T13:02:59.884738Z","latestVersion":"0.3.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"qdf-mcp","url":"https://pypi.org/project/qdf-mcp/","firstSeenAt":"2026-09-10T10:24:56.388Z","fetchedAt":"2026-11-03T23:20:29.715Z","normalizedAt":"2026-11-03T23:20:29.715Z"}]},"firstSeenAt":"2026-09-10T10:24:56.388Z","updatedAt":"2026-11-03T23:22:43.684Z"}