Learning Optimizer MCP server
Commit Nov 13, 2026Schedules spaced reviews and exam study plans by modeling individual forgetting curves using advanced spaced-repetition algorithms.
Also known as Saify-Technologies/saifs-ai-mcps-docs, learning-optimizer
- Stars
- 4
- Tools
- 6
- Downloads, 30 days
- —
- Latest version
- 1.0.1
- Last commit
- Nov 13, 2026
- License
- MIT
What is Learning Optimizer MCP?
Learning Optimizer schedules spaced reviews and exam study plans by modeling individual forgetting curves using advanced spaced-repetition algorithms. It exposes 6 tools, such as schedule_review, due_reviews, predict_retention.
Summary generated from the project's README
About Learning Optimizer MCP server
Learning Optimizer acts as a personalized spaced-repetition engine designed to help students manage long-term memory through scientific modeling. It uses algorithms like FSRS, Half-Life Regression, and SM-2 to calculate individual forgetting curves for specific items. This allows the system to schedule the minimum number of reviews required to reach a specific retention goal.
Users connect to this remote server via Streamable HTTP using the registry name ai.saifs/learning-optimizer. It requires OAuth 2.1 authentication with PKCE, meaning your client will prompt you to sign in through a web page during the first use. You can integrate it into VS Code, GitHub Copilot, Claude Desktop, or Claude Code by pointing your client to the provided endpoint.
The server provides specialized tools such as schedule_review for calculating recall probability and optimize_study_plan for creating comprehensive schedules. It also includes explain_schedule to provide the reasoning behind specific intervals and forgetting_curve to show fitted decay parameters.
What you can do with it
- 1Calculate next review timingAsk the AI to determine the next optimal review time and the predicted probability of recall for a specific item.
- 2Generate daily study queuesRequest a priority-ordered list of all items that a learner needs to review today.
- 3Create exam preparation schedulesInstruct the AI to build a complete study plan for an entire item bank that ensures memory retention peaks on a specific exam date.
- 4Analyze memory decayUse the tool to view the fitted decay curve and specific parameters for a single learner-item.
Written from the project's README. Every use case is checked against a quote from it.
How to install Learning Optimizer MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Learning Optimizer MCP in Claude Code
$ claude mcp add --transport http learning-optimizer https://learning-optimizer-mcp.saifs.ai/mcpInstall Learning Optimizer MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"learning-optimizer": {
"url": "https://learning-optimizer-mcp.saifs.ai/mcp"
}
}
}Install Learning Optimizer MCP in VS Code
.vscode/mcp.json
{
"servers": {
"learning-optimizer": {
"type": "http",
"url": "https://learning-optimizer-mcp.saifs.ai/mcp"
}
}
}Install Learning Optimizer MCP in VS Code CLI
$ code --add-mcp '{"name":"learning-optimizer","type":"http","url":"https://learning-optimizer-mcp.saifs.ai/mcp"}'Install Learning Optimizer MCP in Codex
$ codex mcp add learning-optimizer --url https://learning-optimizer-mcp.saifs.ai/mcpInstall Learning Optimizer MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.learning-optimizer] url = "https://learning-optimizer-mcp.saifs.ai/mcp"
Install Learning Optimizer MCP in Gemini CLI
$ gemini mcp add -s user --transport http learning-optimizer https://learning-optimizer-mcp.saifs.ai/mcpInstall Learning Optimizer MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"learning-optimizer": {
"url": "https://learning-optimizer-mcp.saifs.ai/mcp",
"type": "http"
}
}
}Learning Optimizer MCP tools 6
Detected from the READMEschedule_reviewdue_reviewspredict_retentionoptimize_study_planforgetting_curveexplain_schedule
| schedule_review | — | |
| due_reviews | — | |
| predict_retention | — | |
| optimize_study_plan | — | |
| forgetting_curve | — | |
| explain_schedule | — |
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 · What to fix for more points
- 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 model6 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 GitHubLearning Optimizer
A personalised spaced-repetition engine: it models each learner’s forgetting curve per item and schedules the fewest reviews that still hit a target retention. Built on Ebbinghaus, Leitner / SM-2 (Anki’s baseline), Half-Life Regression and FSRS. Also builds a full study plan that peaks retention by exam day.
| Registry name | ai.saifs/learning-optimizer |
| Endpoint | https://learning-optimizer-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-learning-optimizer": {
"type": "http",
"url": "https://learning-optimizer-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://learning-optimizer-mcp.saifs.ai/mcp
Claude Code
claude mcp add --transport http saifs-learning-optimizer https://learning-optimizer-mcp.saifs.ai/mcp
Any other MCP client
Point it at https://learning-optimizer-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 |
|---|---|
schedule_review |
Next optimal review time and predicted recall probability for one learner-item after the last result. |
due_reviews |
Today’s review queue for a learner, priority-ordered. |
predict_retention |
Probability of recall for an item at a future date. |
optimize_study_plan |
Full schedule over an item bank so retention peaks on exam day. |
forgetting_curve |
Fitted decay curve and parameters for one learner-item. |
explain_schedule |
Why this interval: model, evidence and confidence. |
Example prompts
- “This student just missed item 142. When should they review it next, and what’s P(recall) then?”
- “What should this learner review today, in priority order?”
- “Exam is 28 days out. Build a study plan over this item bank so they peak on the day.”
Support
- Website: https://saifs.ai
- Issues: https://github.com/Saify-Technologies/saifs-ai-mcps-docs/issues
- Privacy: https://saifs.ai/privacy_policy
Learning Optimizer MCP questions
How do I add Learning Optimizer MCP to Claude Code?
Run claude mcp add --transport http learning-optimizer https://learning-optimizer-mcp.saifs.ai/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Learning Optimizer 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 Learning Optimizer MCP provide?
It exposes 6 tools, including schedule_review, due_reviews, predict_retention, optimize_study_plan, forgetting_curve.
What algorithms does the server use for scheduling?
The engine is built on Ebbinghaus, Leitner / SM-2, Half-Life Regression, and FSRS.
How can I create a study plan for an upcoming exam?
You can use the optimize_study_plan tool to build a full schedule over an item bank so that retention peaks on your exam day.