MCP‑Memory Server

A lightweight FastMCP based key/value store for agent memory with support for namespaces.

Server – memory_server.py
Client – memory_client.py

The server exposes the following tools:

Tool	Description
`save`	Store a value by key.
`get`	Retrieve a value by key.
`delete`	Remove a key/value pair.
`list_keys`	List all stored keys.
`save_with_namespace`	Store a value under a namespace and key.
`get_by_namespace`	Retrieve a value from a specific namespace/key.

📦 Installation

# Clone the repo (or copy the files)
git clone https://github.com/yourname/mcp-memory-server.git
cd mcp-memory-server

# Create a virtual environment (optional but recommended)
python -m venv .venv
source .venv/bin/activate   # On Windows: .\.venv\Scripts\activate

# Install dependencies
pip install fastmcp

Tip: If you want to run the client and server on different machines, make sure the host machine is reachable from the client.

🚀 Running the Server

python memory_server.py

The server starts listening on localhost:8000 by default.
You can change the port or host by editing the MCPServer initialization in memory_server.py.

🧩 Using the Client

python memory_client.py

The client script demonstrates how to call each tool:

Save a key/value pair

result = await client.call("save", {"key": "name", "value": "Alice"})
print(result)  # → "Значение сохранено под ключом 'name'."

Retrieve the value

value = await client.call("get", {"key": "name"})
print(value)  # → "Alice"

List all keys

keys = await client.call("list_keys")
print(keys)  # → {"keys": ["name"]}

Delete a key

result = await client.call("delete", {"key": "name"})
print(result)  # → "Ключ 'name' удалён."

Namespace operations

await client.call("save_with_namespace", {"namespace": "user1", "key": "age", "value": 30})
age = await client.call("get_by_namespace", {"namespace": "user1", "key": "age"})
print(age)  # → 30

Feel free to modify memory_client.py or write your own scripts that use the same RPC pattern.

📚 Example Workflow

# Terminal 1 – start server
$ python memory_server.py
Server listening on http://localhost:8000

# Terminal 2 – run client demo
$ python memory_client.py
Значение сохранено под ключом 'name'.
Alice
{'keys': ['name']}
Ключ 'name' удалён.

🔧 Troubleshooting

Issue	Fix
`ModuleNotFoundError: No module named 'fastmcp'`	Ensure you installed the package in the active virtual environment. Run `pip install fastmcp`.
Connection refused	Verify that the server is running and listening on the correct host/port.
Unexpected RPC errors	Check that the tool names match exactly (`save`, `get`, etc.).

3.1 KiB Raw Permalink Blame History Unescape Escape