Demand Forecasting MCP server
Commit Nov 13, 2026Forecasts product demand from historical sales data using various statistical models and provides prediction intervals.
Also known as Saify-Technologies/saifs-ai-mcps-docs, demand-forecasting
- Stars
- 4
- Tools
- 2
- Downloads, 30 days
- —
- Latest version
- 1.0.1
- Last commit
- Nov 13, 2026
- License
- MIT
What is Demand Forecasting MCP?
Demand Forecasting forecasts product demand from historical sales data using various statistical models and provides prediction intervals. It exposes 2 tools, such as demand_forecaster, demand_forecaster_get_engine.
Summary generated from the project's README
About Demand Forecasting MCP server
Predicting product demand from historical sales data is what this remote MCP server enables for inventory managers and analysts. By connecting via Streamable HTTP, users can process Excel, Tally, or CSV exports to generate forecasts on daily, weekly, or monthly intervals. The system automatically selects the most accurate statistical model through backtesting and includes prediction intervals for every value. It specifically handles intermittent or slow-moving items using Croston and SBA methods.
Developers use the demand_forecaster tool to process up to 200 products and 2,500 rows of data, providing lead-time demand that integrates with the Inventory Intelligence & Optimizer server. For larger datasets where privacy is a priority, the demand_forecaster_get_engine tool generates a local Python script so data remains on the user's machine. Setup requires OAuth 2.1 authentication, which triggers a sign-in page during the first connection through clients like Claude or VS Code.
What you can do with it
- 1Predicting future sales volumesAsk the AI to calculate how many units of specific items will be sold over a set number of weeks using a Tally export.
- 2Managing slow-moving inventoryIdentify products with low turnover and determine their expected demand for the upcoming month.
- 3Generating statistical demand rangesRequest a monthly demand forecast for a specific spare part including a 95% prediction interval.
- 4Processing large datasets locallyObtain a Python script to run forecasts on massive sales files without uploading the raw data to the cloud.
Written from the project's README. Every use case is checked against a quote from it.
How to install Demand Forecasting MCP
Formats verified 10 Nov 2026Install Demand Forecasting MCP in Claude Code
$ claude mcp add --transport http demand-forecasting https://demand-forecaster-mcp.saifs.ai/mcpInstall Demand Forecasting MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"demand-forecasting": {
"url": "https://demand-forecaster-mcp.saifs.ai/mcp"
}
}
}Install Demand Forecasting MCP in VS Code
.vscode/mcp.json
{
"servers": {
"demand-forecasting": {
"type": "http",
"url": "https://demand-forecaster-mcp.saifs.ai/mcp"
}
}
}Install Demand Forecasting MCP in Codex
~/.codex/config.toml
[mcp_servers.demand-forecasting] url = "https://demand-forecaster-mcp.saifs.ai/mcp"
Install Demand Forecasting MCP in Gemini CLI
~/.gemini/settings.json
{
"mcpServers": {
"demand-forecasting": {
"httpUrl": "https://demand-forecaster-mcp.saifs.ai/mcp"
}
}
}Demand Forecasting MCP tools 2
Detected from the READMEdemand_forecasterdemand_forecaster_get_engine
| demand_forecaster | — | |
| demand_forecaster_get_engine | — |
Automated checks
Ran Nov 13, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work
- Source repository linked and reachablesaify-technologies/saifs-ai-mcps-docs is public and reachablegithub.com/saify-technologies/saifs-ai-mcps-docs ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-13github.com/saify-technologies/saifs-ai-mcps-docs ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model2 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeHTTPS endpoint answered 401 (sign-in required)Pass
README
View on GitHubDemand Forecasting
Forecasts demand per product (and optionally per region or channel) from sales history — daily, weekly or monthly — with a range for every number. It picks the best-fitting model by backtest, handles slow and intermittent movers (Croston/SBA), refuses to guess when history is too short, and hands lead-time demand to the Inventory Intelligence & Optimizer server for safety stock. Reads Excel, Tally and CSV exports with their own column names.
| Registry name | ai.saifs/demand-forecasting |
| Endpoint | https://demand-forecaster-mcp.saifs.ai/mcp |
| Transport | Streamable HTTP (remote, nothing to install) |
| Auth | OAuth 2.1 — PKCE (S256) and dynamic client registration; your client opens a sign-in page on first use |
| Publisher | SAIFS AI |
Install
VS Code / GitHub Copilot
Add to .vscode/mcp.json (workspace) or your user mcp.json:
{
"servers": {
"saifs-demand-forecasting": {
"type": "http",
"url": "https://demand-forecaster-mcp.saifs.ai/mcp"
}
}
}
Then start the server from the MCP view and sign in when prompted.
Claude (claude.ai, Desktop)
Settings → Connectors → Add custom connector, and paste:
https://demand-forecaster-mcp.saifs.ai/mcp
Claude Code
claude mcp add --transport http saifs-demand-forecasting https://demand-forecaster-mcp.saifs.ai/mcp
Any other MCP client
Point it at https://demand-forecaster-mcp.saifs.ai/mcp using the Streamable HTTP transport. The server returns 401 with a
WWW-Authenticate: Bearer … resource_metadata=… challenge, so OAuth-aware clients sign in automatically.
Tools
| Tool | What it does |
|---|---|
demand_forecaster |
Forecasts demand from sales rows (date + quantity is enough; SKU, region, channel and lead time optional) for up to about 200 products and 2,500 rows. Returns forecasts with prediction intervals, the chosen model and its backtest score, and lead-time demand for reordering. |
demand_forecaster_get_engine |
For larger sales files: returns a runnable Python script that produces the same forecasts locally, so the data never leaves the user's machine. |
Example prompts
- “Here's our Tally sales export. How much of each item will we sell over the next 13 weeks?”
- “Which products are slow movers, and what should we expect from them next month?”
- “Forecast monthly demand for spare part SP-220 with a 95% range.”
Support
- Website: https://saifs.ai
- Issues: https://github.com/Saify-Technologies/saifs-ai-mcps-docs/issues
- Privacy: https://saifs.ai/privacy_policy
Demand Forecasting MCP questions
How do I add Demand Forecasting MCP to Claude Code?
Run claude mcp add --transport http demand-forecasting https://demand-forecaster-mcp.saifs.ai/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Demand Forecasting MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Demand Forecasting MCP provide?
It exposes 2 tools, including demand_forecaster, demand_forecaster_get_engine.
What data formats does the server support?
The server can read Excel, Tally, and CSV exports, even with custom column names.
How can I handle large sales files without uploading data?
You can use the demand_forecaster_get_engine tool to receive a runnable Python script that generates forecasts locally on your machine.
What information is included in the forecast results?
The tool returns forecasts with prediction intervals, the selected model, its backtest score, and lead-time demand for reordering.