Decode the tick. Find the edge.
Market intelligence for your AI assistant - algo-trading strategies, analytics and specialized research knowledge.
Just ask
- "What strategy works best on AAPL?"
- "Show me the top strategy's backtest - return, max drawdown, win rate."
- "How risky is BTC?"
- "How do I avoid overfitting a backtest?"
Getting started
Standard config works in most MCP clients:
{
"mcpServers": {
"decodetick": {
"url": "https://mcp.decodetick.com/mcp"
}
}
}
It works without an account; sign in with Decodetick for higher usage limits.
Cursor
Click the Add to Cursor button above, or add to ~/.cursor/mcp.json:
{
"mcpServers": {
"decodetick": {
"url": "https://mcp.decodetick.com/mcp"
}
}
}
VS Code
Click the Install in VS Code button above, or use the CLI:
code --add-mcp '{"name":"decodetick","type":"http","url":"https://mcp.decodetick.com/mcp"}'
or add to .vscode/mcp.json:
{
"servers": {
"decodetick": {
"type": "http",
"url": "https://mcp.decodetick.com/mcp"
}
}
}
Claude Code
claude mcp add --transport http decodetick https://mcp.decodetick.com/mcp
Add --scope user to enable it in every project.
Claude Desktop / claude.ai
Settings → Connectors → Add custom connector, then enter:
https://mcp.decodetick.com/mcp
Connectors are account-level, so the server is available in both the desktop app and claude.ai. Sign in with Decodetick when prompted, or skip it to continue without an account.
ChatGPT
Custom MCP connectors need Developer mode (Plus/Pro/Team/Enterprise/Edu):
- Settings → Connectors → Advanced - enable Developer mode.
- Settings → Connectors → Create - name it
Decodetick, set the MCP server URL tohttps://mcp.decodetick.com/mcp, pick OAuth (or No authentication to use it without an account), and create. - In a chat, open + → Developer mode and toggle Decodetick on.
Self-hosted (PyPI / Docker)
uvx decodetick-mcp # run straight from PyPI
pip install decodetick-mcp # or install
docker run -p 8080:8080 $(docker build -q .) # or containerized
uvx and pip run the server over stdio; the Docker image serves streamable
HTTP on localhost:8080. Sign-in with Decodetick is available on the hosted
server.
How it works
You ask in plain language. The AI picks the right tool. You get an answer with evidence - strategy metrics you can rank, or research passages you can cite - not a data dump.
| You ask | You get |
|---|---|
| "What strategy works best on AAPL?" | Strategies backtested on AAPL, ranked by their score on it |
| "How risky is BTC?" | The instrument dossier - volatility, drawdowns, character fingerprint |
| "What does the research say about position sizing?" | Ranked passages with slug + locale for citation |
Tools
Four read-only tools.
- leaderboard - the strategy leaderboard: published, backtested
strategies, ranked. Sort by score or by backtested APY -
apy_descranks bycagr_usd(annualized return in USD, comparable across markets; localcagris the fallback); filter by family or by instrument symbol ("what works best on AAPL?"). - strategy - one strategy's full dossier: metrics, risk mode, parameters, and the backtest summary.
- instrument - the catalog of covered markets, or one instrument's dossier: buy-and-hold facts and the six-axis character fingerprint.
- research - one search across the research: articles plus, on paid tiers, the deeper knowledge base. Returns cited passages.
Example prompts
Explore the leaderboard
What strategy works best on AAPL?
Show me the highest-APY strategy and its max drawdown.
Which strategy family performs best?
Dig into a strategy
Give me the full details on the MA Crossover strategy.
What's the win rate and risk mode of your top strategy?
Explore the markets
Which markets do you cover?
How risky is BTC - volatility, drawdowns, character?
Search the research
How do I avoid overfitting a backtest?
Find articles about position sizing and drawdown control.
Disclaimer
Strategy results are hypothetical backtests on historical data. They do not reflect actual trading, and past performance does not guarantee future results. Nothing this server returns is investment advice or a recommendation to buy or sell any instrument. See the risk disclosure.
Terms and privacy
Use of the hosted server is subject to the Decodetick Terms and Privacy Policy.
Security
Please report vulnerabilities privately, as described in SECURITY.md.
License
MIT - decodetick.com
Metadata
Release files for decodetick-mcp 2026.10.19
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| decodetick_mcp-2026.10.19.tar.gz | 23.1 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| decodetick_mcp-2026.10.19-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 51.7 kB
Release files / decodetick_mcp-2026.10.19.tar.gz
| Download URL | decodetick_mcp-2026.10.19.tar.gz |
|---|---|
| Size | 23.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
8d50b56331c45e3735e423451d577cc4a18dde6e22a94dcb80931b40171ce7a2
|
|
BLAKE2b-256 checksum How to use checksums |
ffb04e4b3dc710c2567696c5a0d5864ec3d192a3bee82371026422abc32fad8e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 18, 2026.
Transparency logRelease files / decodetick_mcp-2026.10.19-py3-none-any.whl
| Download URL | decodetick_mcp-2026.10.19-py3-none-any.whl |
|---|---|
| Size | 28.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0c4d773f954237df00e6d15d4bfa5e1de98bf1357416a17ebeae86a0ce1da9a4
|
|
BLAKE2b-256 checksum How to use checksums |
37e3c2677fb180967bb4efd9eac9da93bb8d0b8a21b5ab82852ed5b1b92eefb5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 18, 2026.
Transparency log