Integrates with Google Gemini to generate educational content such as multiple-choice questions (MCQs), flashcards, and lesson plans.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Educhain MCP Server Generate 5 MCQs about the solar system for a science quiz"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
This project devises an MCP server that handles various functions like: generating MCQs, flashcards, lesson-plans etc.,
Claude Desktop(Front end) <-> MCP Server <-> LLM (google Gemini)Related MCP server: EduChain MCP Server
Packages Manager: uv (Recommended) or pip
git clone Anudeep-CodeSpace/educhain_mcp_server.git
cd educhain_mcp_serverpip install uv # universal
brew install uv # mac os onlyuv init # initialize an already existing project# They contain all the required sub -packages in them
uv add "educhain" "mcp[cli]"# inside .env file
GOOGLE_API_KEY=<Your Google api key without quotes>uv run mcp dev main.pyIt produces a tokenised proxy server at
http://localhost:6274/?PROXY_API_TOKEN=<proxy token>Paste it and navigate to the link in a browser. Click "Connect" and you can debug your tools, resources and prompts in that site.
Install Claude Desktop app and login with your account(can be new).
In the git repo folder run
# Adds the MCP Server to Claude Desktop client
uv run mcp install main.pyAfter that your claude_desktop_config.json should look like this:
{
"mcpServers": {
"Educhain - MCP server": {
"command": "absolute/path/to/uv",
"args": [
"run",
"--with",
"mcp[cli]",
"mcp",
"run",
"absolute/path/to/main/main.py"
]
}
}
}All the logs are located at:
%APPDATA%\\Claude\\logs\\mcp.log # in windows
~/Library/Logs/Claude/mcp.log # in macOSget_info(about://info) resource lists out all the tools and resources provided by this server
Modularity: Separating the server initialization (server.py), route handling (handlers.py), and the main entry point (main.py) makes the codebase clean, scalable, and easy to maintain.
Clear Schema Definitions: Use of Pydantic models in the schema directory. It ensures strong data validation, clear API contracts, and self-documenting code for requests and responses.
Dependency Injection: Passing the mcp server instance to handler functions (handle_resources(mcp)) is a good practice. It avoids circular dependencies and global state issues.
Use of Decorators: The @mcp.resource and @mcp.tool decorators provide a clean and declarative way to define the server's capabilities.
For Example Claude Desktop client cannot access the generate_lessonplan resource(uri = lessonplan://{topic}) cannot be used directly as it is in beta stage and doesn't support dynamic resource uri's!!!
So Generate a lesson plan to teach algebra cannot invoke the generate_lessonplan tools!
Claude being a powerful llm cannot direclty generate content according to our tools and resources! (Hence I am using Gemini)
Myself(Anudeep-CodeSpace), Chatgpt, Perplexity AI, Gemini(Free LLM)
Node js(LTS) version is required for debugging pyenv is not recommended(That wasted a lot of time for me ðŸ˜)
Tool to generate Flash cards about a given topic.
| Name | Required | Description | Default |
|---|---|---|---|
| request | Yes |
| Name | Required | Description |
|---|---|---|
| title | Yes | |
| flashcards | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool generates flashcards but doesn't explain how (e.g., AI-based, template-driven), what the output format is, or any constraints like rate limits or permissions. This leaves significant gaps in understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized for a simple tool, though it could be slightly more informative without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has an output schema (which handles return values) and low complexity, the description is minimally complete. However, with no annotations and low schema coverage, it lacks details on behavior and parameters, making it adequate but with clear gaps for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 1 parameter ('request') with 0% description coverage, and the description doesn't add any parameter details beyond implying a 'topic'. Since schema coverage is low, the description should compensate but only partially does so by hinting at the topic parameter, resulting in a baseline score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool's purpose ('generate Flash cards about a given topic') with a specific verb ('generate') and resource ('Flash cards'), which is clear. However, it doesn't distinguish this tool from its sibling 'generate_mcq' (which likely generates multiple-choice questions), leaving the differentiation vague.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'generate_mcq'. There's no mention of context, prerequisites, or exclusions, leaving the agent with no usage direction beyond the basic purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool to generate Multiple Choice Questions(mcqs) about a given topic.
| Name | Required | Description | Default |
|---|---|---|---|
| request | Yes |
| Name | Required | Description |
|---|---|---|
| questions | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the basic action of generating MCQs without any details about how it works (e.g., source of information, quality of questions, potential rate limits, or authentication needs). For a tool with no annotations, this is a significant gap in transparency, as it doesn't reveal important behavioral traits beyond the surface-level purpose.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise and front-loaded, consisting of a single sentence that directly states the tool's purpose. There's no wasted language or unnecessary details, making it easy to parse quickly. Every word earns its place by conveying essential information without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that there's an output schema (which likely defines the structure of generated MCQs), the description doesn't need to explain return values. However, with no annotations, 0% schema description coverage, and a sibling tool, the description is incomplete. It covers the basic purpose but lacks details on usage, behavior, and parameters, making it only minimally adequate for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description mentions 'about a given topic,' which hints at the 'topic' parameter, but it doesn't cover the other parameters ('difficulty' and 'num') or provide any additional meaning beyond what the input schema already defines. With 0% schema description coverage, the description adds minimal value, but since there's only one parameter count (a nested object 'request'), the baseline is adjusted. However, it doesn't fully compensate for the lack of schema descriptions, warranting a score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'generate Multiple Choice Questions (mcqs) about a given topic.' It specifies the verb (generate) and resource (MCQs), making it easy to understand what the tool does. However, it doesn't explicitly differentiate from its sibling tool 'generate_flashcard' (which might generate different educational content), so it doesn't reach the highest score of 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention the sibling tool 'generate_flashcard' or any other context for choosing between them. There's no information about prerequisites, limitations, or specific scenarios where this tool is preferred, leaving the agent with minimal usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0generate_flashcardgenerate_mcqThe two tools have clearly distinct purposes: one generates flash cards and the other generates multiple-choice questions, both focused on educational content creation but for different formats. There is no overlap in functionality, making it easy for an agent to choose the right tool based on the desired output type.
Both tools follow a consistent 'verb_noun' naming pattern (generate_flashcard, generate_mcq), using the same verb 'generate' and descriptive nouns that clearly indicate the output. This uniformity enhances readability and predictability across the tool set.
With only 2 tools, the server feels thin for an educational domain like 'Educhain', which might imply broader functionality such as managing content, quizzes, or user interactions. The limited scope may hinder agents from performing comprehensive tasks, suggesting an underdeveloped tool surface.
The server is severely incomplete for an educational domain; it only offers content generation tools without any CRUD operations (e.g., create, read, update, delete for flashcards or MCQs) or lifecycle management. This creates significant gaps, as agents cannot retrieve, modify, or organize generated content, leading to potential dead ends in workflows.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
The CustomGPT.ai MCP server is a fully managed, RAG-powered endpoint that connects large language models with private knowledge bases and external data sources. It provides tools for retrieval-augmented generation queries (send_message), data ingestion (upload_file), and source listing, enabling AI agents to query private documents like PDFs with high accuracy and real-time citations.
MCP server for building and testing AI agents with multi-model experimentation and insights.
The Google Compute Engine MCP server is a fully-managed Model Context Protocol server that provides tools to manage Google Compute Engine resources through AI agents. It enables capabilities including instance management (creating, starting, stopping, resetting, listing), disk management, handling instance templates and group managers, viewing machine and accelerator types, managing images, and accessing reservation and commitment information. The server operates as a zero-deployment, enterprise-grade endpoint at https://compute.googleapis.com/mcp with built-in IAM-based security.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Anudeep-CodeSpace/educhain_mcp_server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
