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., "@wikipedia-mcp-agent Explain quantum entanglement"
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.
A conversational AI agent that searches and reads Wikipedia using the Model Context Protocol (MCP), LangGraph, and AWS Bedrock (Claude Sonnet).
This project wires together three modern AI infrastructure pieces:
MCP (Model Context Protocol) ā a standard way to expose tools, prompts, and resources to an LLM
LangGraph ā a graph-based agent framework for multi-step reasoning with tool calls
AWS Bedrock ā managed LLM inference using Anthropic's Claude Sonnet
The agent launches an MCP server as a subprocess, dynamically loads its Wikipedia tools at runtime, and runs a stateful chat loop where the LLM can call tools as needed before answering.
Related MCP server: Wikipedia MCP Server
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā mcp_client.py ā
ā ā
ā āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā ā
ā ā LangGraph StateGraph ā ā
ā ā ā ā
ā ā START āāāŗ chat_node āāāŗ tool_node āāā ā ā
ā ā ā² ā ā ā
ā ā āāāāāāāāāāāāāāāāāāāāāā ā ā
ā ā ā END ā ā
ā āāāāāāāāāāāāāāāāāāāāāāāāāāā¼āāāāāāāāāāāāāāāāāāāāā ā
ā ā tool calls ā
ā stdin/stdout (MCP stdio transport) ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāā¼āāāāāāāāāāāāāāāāāāāāāāāāā
ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāā¼āāāāāāāāāāāāāāāāāāāāāāāāā
ā mcp_server.py ā
ā ā
ā Tools search_wikipedia ā
ā list_wikipedia_sections ā
ā get_section_content ā
ā ā
ā Prompts highlight_sections_prompt ā
ā ā
ā Resources suggested_titles ā
āāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāāā
ā
wikipedia Python libraryTool | Description |
| Search Wikipedia and return the summary + URL of the top result |
| List all section titles of a Wikipedia article |
| Fetch the full text of a specific section |
Prompt | Description |
| Ask the LLM to pick the 3ā5 most important sections of an article and explain why |
Resource | Description |
| Reads a local |
Python 3.10+
AWS account with Bedrock access enabled for anthropic.claude-sonnet-4-6 in eu-west-2
# Clone the repo
git clone https://github.com/sadeghetemad/wikipedia-mcp-agent.git
cd wikipedia-mcp-agent
# Create and activate a virtual environment
python -m venv venv
venv\Scripts\activate # Windows
# source venv/bin/activate # macOS / Linux
# Install dependencies
pip install -r requirements.txtConfigure your credentials via the AWS CLI or environment variables:
aws configureOr manually:
export AWS_ACCESS_KEY_ID=your_key
export AWS_SECRET_ACCESS_KEY=your_secret
export AWS_DEFAULT_REGION=eu-west-2Make sure your IAM user/role has the bedrock:InvokeModel permission.
python mcp_client.pyYou will see:
Wikipedia MCP agent is ready.
Type a question or use one of the slash commands below:
/prompts - list available prompt templates
/prompt <name> "arg1" ... - run a prompt template
/resources - list available resources
/resource <name or index> - view a resource
exit / quit / q - quitYou: What is quantum entanglement?
AI: Quantum entanglement is a physical phenomenon where two or more particles ...
You: /prompts
Available Prompts:
highlight_sections_prompt (topic)
You: /prompt highlight_sections_prompt "Black hole"
=== Prompt Result ===
ā¢ Formation ā explains how black holes arise from stellar collapse
ā¢ Event horizon ā the defining boundary of no return
...
You: /resources
Available Resources:
[1] suggested_titles
You: /resource 1
=== Resource Text ===
Artificial intelligence
Large language model
...suggested_titles.txtCreate this file in the project root (one topic per line) to populate the suggested_titles resource:
Artificial intelligence
Large language model
Model Context Protocol
Quantum computingwikipedia-mcp-agent/
āāā mcp_server.py # FastMCP server ā tools, prompts, resources
āāā mcp_client.py # LangGraph agent + interactive chat loop
āāā requirements.txt # Pinned Python dependencies
āāā suggested_titles.txt # (optional) topic suggestions for the resource
āāā README.mdLayer | Library |
LLM | AWS Bedrock via |
Agent framework | |
Tool protocol | MCP via |
Wikipedia data |
MIT
This server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search and fetch Wikidata entities, execute SPARQL queries, and resolve external identifiers.
Live Wikipedia edit feed, page summaries, trending pages, and Wikidata search.
Wikipedia MCP ā wraps Wikipedia REST API (free, no auth)
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/sadeghetemad/wikipedia-mcp-agent'
If you have feedback or need assistance with the MCP directory API, please join our Discord server