Learning Assistant MCP Server
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., "@Learning Assistant MCP ServerSearch the web for the latest MCP protocol updates."
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.
Learning Assistant MCP Server
MCP capability server consumed by AI-Learning-Assistant-Service.
AI Learning Assistant ──MCP / Streamable HTTP──▶ this server ──▶ Web Search Provider (Tavily)Design doc: dev-docs/web-search-mcp-integration.md.
Capabilities
Tool | Purpose |
| Ranked public-web results (title, URL, snippet, score) for current/external info. |
Related MCP server: MCP Internet Server
Setup
uv sync
cp .env.example .env # then fill MCP_AUTH_TOKEN and TAVILY_API_KEYMCP_AUTH_TOKEN must match the assistant's MCP_SERVER_AUTH_TOKEN.
TAVILY_API_KEY lives only here — never in the assistant.
Run
uv run python -m app.main # Streamable HTTP on :8006 → POST/GET /mcp/Health check: GET http://localhost:8006/health.
Transport
Streamable HTTP (transport="http"). Single endpoint, works across independently
deployed services and through the Nginx gateway. Clients authenticate with
Authorization: Bearer <MCP_AUTH_TOKEN>.
Access path | MCP endpoint | Health |
Direct (service-to-service) |
|
|
Via API gateway |
|
|
Use the no-trailing-slash /mcp form; the server redirects /mcp/ → /mcp.
Layout
app/
main.py # composition root: FastMCP + auth + tool registration + /health
config.py # pydantic-settings
logging_config.py # structured JSON logging
auth.py # StaticBearerVerifier (shared-secret, constant-time)
rate_limit.py # in-process token bucket
schemas.py # WebSearchInput / WebSearchResultItem / WebSearchResponse
tools/web_search.py # register_web_search(mcp, provider, settings)
providers/
base.py # WebSearchProvider protocol + ProviderResult + errors
tavily.py # TavilyProvider
__init__.py # get_provider(settings) factoryAdding a tool
app/tools/<name>.pywithregister_<name>(mcp, deps).Call it from
app/main.py.If it wraps an external API, add a provider under
app/providers/.
No transport/auth/architecture changes required.
Tests
uv run pytest # unit
uv run pytest -m integration # hits Tavily; needs TAVILY_API_KEY
uv run ruff check .This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI assistants to perform real-time web searches, company research, content crawling, LinkedIn searches, and deep research using the Exa AI Search API. Provides comprehensive web information retrieval capabilities in a safe and controlled manner.225,4621MIT
- AlicenseNot gradedqualityBmaintenanceEnables web search and webpage content fetching with SSRF protections, returning structured results.MIT
- FlicenseAqualityCmaintenanceEnables MCP-compatible agents to perform web searches via the agent-web-search engine, returning ranked results with sources.1
- AlicenseAqualityCmaintenanceEnables MCP hosts to perform cited web searches and receive source-bearing results with titles, URLs, snippets, and sources for evidence-grounded answers.1240MIT
Related MCP Connectors
LLM-ready web search + instant answers + URL-to-clean-text fetch for agents and RAG.
Search Google straight from your AI agent. Web results, images, videos, news, products, scholarly ar
The best web search for your AI Agent
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Interactive-Digital-Learning-Platform/AI-Learning-Assistant-MCP-Server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server