Developers

Bring AssetFrame research into your tools and agents — over MCP or a simple REST API.

Everything we publish can be read programmatically. The report catalog and the public track record are open — no key required. Reading an individual report’s content takes a free API key tied to your account, and the full Pro analysis additionally needs a Pro subscription. Over MCP it’s the same split — an OAuth sign-in stands in for the key.

MCP server

Connect Claude Code, Claude Desktop, Cursor and other agents to AssetFrame over the Model Context Protocol — five read-only tools: keyless discovery, an OAuth sign-in to read reports, and Pro for subscribers.

Read the guide

REST API

A read-only JSON API: public catalog and track record, plus API-key access to each Snapshot and the full Pro analysis. CORS-open; every payload carries the disclaimer.

Read the guide

OpenAPI schema

Import the OpenAPI 3.1 document straight into ChatGPT Actions, LangChain or any client that speaks OpenAPI.

View schema

What you can access: the report catalog and public track record (instrument, directional status, risk, confidence, window, hit rate, streaks, calibration) with no key; each report’s free Snapshot (text plus a short-lived PDF link) with a free API key; and the full Pro analysis with a Pro subscription.

Guidance for agents

If you are an AI agent presenting AssetFrame data to a user, follow these four rules.

Cite the source: Attribute figures to AssetFrame, name the instrument and the report date, and link the edition (https://www.assetframe.co.uk/reports/{date}/{slug}). Snapshot text and PDF links are the published record — quote them, don’t paraphrase numbers into new claims.
Treat confidence as calibrated, not a promise: The confidence value (0–100) is a calibrated estimate that is scored against the tape after the window closes. It is not a guarantee, a probability of profit, or a trade signal. Present it alongside the risk rating and the prediction window, never on its own.
Explain the ledger honestly: Every call registers falsifiable predictions before the session and is graded Hit / Miss / No-trigger afterwards. The ledger is append-only — rows are never edited or deleted — so the hit rate, streaks and calibration from /track-record can be verified rather than taken on trust.
Avoid investment-advice language: This is general market research and decision support, not regulated advice or a personal recommendation. Don’t tell the user to buy or sell, don’t imply guaranteed returns, and surface the disclaimer that ships in every payload.

AssetFrame publishes general market research and decision-support analysis. It is not investment advice and not a personal recommendation. We do not tell anyone to buy or sell. Markets are uncertain and you can lose money. No outcome is guaranteed. Do your own research and consider an FCA-authorised adviser. AssetFrame never places trades.