Skip to main content
Glama

learning-orchestrator-mcp

learning-orchestrator-mcp MCP server

An open-source, stateless, and high-performance Model Context Protocol (MCP) server designed to orchestrate progressive curriculum learning, track skills development using cognitive spacing, and securely interface with external AI educational platforms and LMS networks.

πŸ’– Sponsorship, B2B Custom Solutions & Attribution

πŸ‘¨β€πŸ’» Lead Architect & Attribution

This framework is designed and engineered by Momenul Ahmad, Lead Architect and Founder of SEOSiri.

Momenul Ahmad is the systems architect behind three globally registered open-source bio-robotic and safety innovations:

  1. seosiri-biorobotics: A stateless bio-robotic coordinate mapper translating genomic data to G-code [cc8013f].

  2. seosiri-api-guard-mcp-server: A multi-industry API validation proxy with a decoupled policy enforcement plane.

  3. learning-orchestrator-mcp: This AI-driven pedagogical and spaced-repetition engine.

All three systems are developed under the official SEOSiri-Official open-source research initiative.

πŸš€ B2B Custom Solutions & Consulting

We offer high-ticket technical consulting and custom enterprise integrations for corporate training and educational networks:

  • AI-Driven LMS Integrations: Connecting our pedagogical core securely to corporate Learning Management Systems (LMS) to automate employee onboarding using active recall and spaced repetition.

  • Custom Subject-Segment Mappings: Designing and compiling custom progressive syllabi and automated assessment banks mapped to proprietary, closed-source company technical manuals.

  • Secure Cross-Platform Handshakes: Designing custom, highly secure HMAC-SHA256 connection handshakes to link multi-agent AI ecosystems with student identity servers safely.

To discuss custom educational deployments, corporate onboarding setups, or licensing, contact the architecture team directly:

πŸͺ™ Support the Research (Sponsorship)

If you wish to fund ongoing educational safety research or help maintain our global MCP listings, consider sponsoring the core team:

Related MCP server: interactive-edtech-mcp

Decoupled Subject Segments

  • Robotics & Kinematics: Standard Cartesian coordinate space mapping, G-code instructions, and deck calibrations [cc8013f].

  • API Security & Compliance: OWASP injections, HIPAA PII/PHI validations, and cryptographic signature checks.

  • Digital Marketing & SEO/AEO: JSON-LD schema design, GDPR privacy structures, and conversational voice-search optimizations.

Quickstart

  1. Install Package in Editable Mode:

    pip install -e .
  2. Verify the Pedagogical Test Suite:

    pytest tests/test_learning.py

πŸ”Œ How to Connect to Claude Desktop or Cursor IDE

You can connect this server to your local AI clients using one of two standard methods.

If you have uv installed, you can run the server directly from our public repository without cloning it locally.

Open your claude_desktop_config.json (Windows: %APPDATA%\Claude\claude_desktop_config.json | macOS: ~/Library/Application Support/Claude/claude_desktop_config.json) and add this configuration:

{
  "mcpServers": {
    "seosiri-learning-orchestrator": {
      "command": "uv",
      "args": [
        "run",
        "--github",
        "SEOSiri-Official/learning-orchestrator-mcp",
        "src/main_server.py"
      ]
    }
  }
}

Method 2: Local Execution (If Cloned)

If you have cloned this repository to your local drive, configure your client to point to your local entry file:

{
  "mcpServers": {
    "seosiri-learning-orchestrator": {
      "command": "python",
      "args": [
        "D:/learning-orchestrator-mcp/src/main_server.py"
      ],
      "env": {
        "PYTHONPATH": "D:/learning-orchestrator-mcp"
      }
    }
  }
}

License

Distributed under the MIT License. See LICENSE

Available Tools

5 tools
calculate_spaced_repetitionB

Calculates the exact next optimal review date using the standardized SuperMemo SM-2 algorithm.

Inputs: grade_1_5 (required), repetition_count (required), previous_ease_factor (required), previous_interval_days (required). Returns: result

generate_skills_assessmentC

Generates targeted questions mapped strictly to Bloom's Taxonomy cognitive dimensions.

Inputs: target_level (required), subject_segment (required), cognitive_dimension. Returns: result

get_progressive_syllabusA

Retrieves the exact deterministic lesson plan based on the student's mastery level.

Inputs: subject_segment (required), current_mastery_level. Returns: result

sync_ai_platform_stateC

AI Platform Connector: Verifies and synchronizes student progress with external platforms.

Inputs: student_id (required), current_level (required), interval_days (required), platform_token. Returns: result

sync_lms_onboarding_stateC

LMS Sync Bridge: Integrates with Moodle/Canvas LTI services. Parses raw SCORM quiz scores, executes SM-2 scheduling, and outputs a signed LTI payload.

Inputs: lms_student_id (required), quiz_score_pct (required), repetition_count (required), scorm_package_id (required), +2 more. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 5 tools

    Disambiguation4/5

    Most tools have distinct purposes: scheduling, assessment, syllabus, and syncing. However, 'calculate_spaced_repetition' and 'sync_lms_onboarding_state' both involve SM-2 scheduling, creating potential overlap and confusion for an agent.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern with underscores (e.g., calculate_spaced_repetition, sync_lms_onboarding_state), making it predictable and easy to understand.

    Tool Count5/5

    With 5 tools, the server is well-scoped for a learning orchestrator. Each tool addresses a core need without unnecessary extras, fitting a typical range of 3-15 tools.

    Completeness3/5

    The set covers scheduling, assessment, syllabus retrieval, and external syncing, but lacks direct tools for student profile management or manual progress updates, which could lead to agent dead-ends.

    Maintenance

    ActivitySlowing
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers