Integrates with Ollama to run local language models as an agent within the server.
Click on "Deploy 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., "@Asgard MCP Server search for files about AI in the project folder"
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 modular web-http based MCP + webapp(uvicorn/fastAPI) + ollama agent stack written in python; Frontend/ Javascript placeholder written by LLMs*
After install activate a python virtual environment in the repository root, then open two terminals and run in one line for each in order:
python server.py
python chat_server.pyAfterwards, open localhost:8000 in browser to access the interface.
Related MCP server: MCP Server
The base tooling content of is bulky and still in development and testing; If using this app, you may simply exclude the unnecesarry libraries and remove the tool's code; It includes:
search_files
fetch_url
read_text_file
search_knowledge_base
embedImage
[*] - Provisional code;
This server cannot be deployed
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for agentverse documentation, generated by doc2mcp.
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
