Provides a local Ollama model with sandboxed file management tools, allowing the model to read, write, list, and remove files within a controlled workspace directory, along with a demo arithmetic tool and health check.
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., "@Ollama MCP Server list the files in my workspace"
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.
I maded this Projects because I wanted to learn more about Model Context Protocols and to learn how to create better README's. I have added simple tools just to have my LLM complete simple task, I plan to add more tool in the future.
A small Model Context Protocol (MCP) server that gives a local Ollama model a set of safe, sandboxed tools — most importantly the ability to read, write, list, and remove files inside a workspace directory you control.
Everything runs locally. The model, the tools, and your files never leave your machine.
┌─────────────┐ chat + tool calls ┌────────────────────┐ MCP (stdio) ┌──────────────────┐
│ You (CLI) │ ───────────────────▶ │ Ollama client │ ──────────────▶ │ MCP server │
│ │ ◀─────────────────── │ (ollama_clients) │ ◀────────────── │ (server.py) │
└─────────────┘ responses └────────────────────┘ tool results └──────────────────┘
│ │
▼ ▼
local Ollama model sandboxed workspace
(e.g. qwen2.5:14b) (~/Projects/…)You type a message in the client.
The client sends it to your local Ollama model along with the list of tools the MCP server exposes.
If the model decides to call a tool, the client forwards that call to the MCP server over stdio, gets the result, and feeds it back to the model.
The model produces a final answer.
Related MCP server: mcp-coding
Sandboxed file tools — the model can only touch files inside the active
workspace. Absolute paths, ../ escapes, and protected directories (.git,
.venv, .trash, __pycache__) are all rejected.
Recoverable deletes — remove_project_file and overwrites don't hard-delete.
The previous version is moved into <workspace>/.trash/, preserving its layout.
Atomic writes — files are written to a temp file and os.replace'd into place,
so a crash mid-write can't corrupt an existing file.
Named workspace profiles — switch between project directories via config or an environment variable.
Size limits — configurable maximum file size for reads and writes.
Tool | Description |
| Read a UTF-8 text file from the workspace. |
| Create or overwrite a file (overwrite makes a |
| List files/directories in the workspace (recursive optional). |
| Move a file into |
| Health check — returns |
| Trivial demo tool that adds two numbers. |
Python 3.12+
Ollama installed and running, with a model pulled
(default: qwen2.5:14b).
Python packages: mcp[cli]==2.0.0, ollama
# 1. Clone
git clone <your-repo-url> mcp-server
cd mcp-server
# 2. Create a virtual environment
python3 -m venv .venv
source .venv/bin/activate
# 3. Install dependencies
pip install "mcp[cli]==2.0.0" ollama
# 4. Pull the model (if you haven't already)
ollama pull qwen2.5:14bAll settings live in config.toml:
[ollama]
model = "qwen2.5:14b" # any model available to your local Ollama
max_tool_rounds = 8 # max tool round-trips per user message
[mcp]
default_workspace = "ollama-workspace" # replace with desired workplace profile
max_list_results = 500
MAX_FILE_SIZE_BYTES = 1000000 # 1 MB read/write cap
[mcp.workspaces]
ollama-workspace = "~/Projects/ollama-workspace" # replace these for your workspace's path
custom-workspace = "~/Projects/Scripts" # replace these for your workspace's pathEach entry under [mcp.workspaces] is a named profile pointing at a directory the
tools are allowed to operate in. The directory is created automatically if it doesn't
exist.
Variable | Purpose |
| Override the model from |
| Select a named profile from |
| Point at a directory directly (bypasses named profiles — handy for testing). |
| Use a config file other than |
source .venv/bin/activate
python3 clients/ollama_clients.pyYou'll see the connected tools and a prompt. Try:
You: create a file called notes.txt that says "hello from ollama"
You: list the files in the workspace
You: read notes.txtType exit or quit to stop.
To use a different workspace or model for a session:
MCP_WORKSPACE_NAME="custom-workspace" \
OLLAMA_MODEL="qwen2.5:14b" \
python3 clients/ollama_clients.pyThe MCP CLI inspector lets you call the server's tools directly, without a model:
uv run --with "mcp[cli]==2.0.0" mcp dev ./server/server.pyBecause deletes are recoverable, .trash grows over time. The included script purges
trash entries older than a week:
scripts/clean_trash.sh # clean the configured workspaces
RETENTION_DAYS=14 scripts/clean_trash.sh # keep two weeks insteadTo run it automatically, add a cron entry (daily at 3 AM):
0 3 * * * /path/to/mcp-server/scripts/clean_trash.sh >> $HOME/.mcp-trash-clean.log 2>&1mcp-server/
├── server/
│ └── server.py # MCP server + tool definitions
├── clients/
│ └── ollama_clients.py # Ollama <-> MCP bridge (the chat loop)
├── scripts/
│ └── clean_trash.sh # purges .trash entries older than a week
├── config.toml # model + workspace configuration
├── tests/ # (add tests here)
└── README.mdThis server cannot be installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
An MCP server that gives your AI access to the source code and docs of all public github repos
Local-first RAG engine with MCP server for AI agent integration.
Person-owned, portable AI memory as a remote MCP server, readable and writable by any MCP client.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/gxm097/ollama-mcp-workspace'
If you have feedback or need assistance with the MCP directory API, please join our Discord server