Get up and running with Meshagent and the Basic Memory MCP Server in the cloud:

1. Install Meshagent CLI and all dependencies:

pip install "meshagent[all]"

2. Sign up and authenticate:

Follow the instructions at Meshagent CLI Getting Started.

3. Start the MCP service in a Meshagent Room:

meshagent service test --room=test --role=agent --image=meshagent/mcp-basic-memory:latest --env MESHAGENT_PORT=8001  --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" --name=mcp-basic-memory-service
  • This command launches a Meshagent Room named test with the MCP server available inside.
  • If rooms go inactive, they will auto-close.

4. Start a chatbot in the Meshagent Room with the MCP toolkit:

meshagent chatbot join --room=test --agent-name=sample --name=sample --toolkit=mcp-basic-memory
  • This joins the test room with a chatbot that can use the Basic Memory toolkit.
  • You can include multiple toolkits and agents in a single room.
  • The output of this command provides a link you can open in your browser to interact with the tools in your room.

​
Tools Available

The following tools are provided by the Basic Memory MCP Server integration:

ToolShort Description
build_contextBuild context from a memory:// URI to continue conversations naturally.
canvasCreate an Obsidian canvas file to visualize concepts and connections.
delete_noteDelete a note by title or permalink.
project_infoGet information and statistics about the current Basic Memory project.
read_contentRead a file’s raw content by path or permalink.
read_noteRead a markdown note by title or permalink.
recent_activityGet recent activity from across the knowledge base.
search_notesSearch across all content in the knowledge base.
write_noteCreate or update a markdown note.

​
Tool Details

​
build_context

Build context from a memory:// URI to continue conversations naturally. Useful for following up on previous discussions or exploring related topics.

  • Parameters:
    • url (string)
    • depth (string, optional)
    • max_related (integer, optional)
    • page (integer, optional)
    • page_size (integer, optional)
    • timeframe (string, optional; natural language or standard format)

​
canvas

Create an Obsidian canvas file to visualize concepts and connections.

  • Parameters:
    • edges (array)
    • folder (string)
    • nodes (array)
    • title (string)

​
delete_note

Delete a note by title or permalink.

  • Parameters:
    • identifier (string)

​
project_info

Get information and statistics about the current Basic Memory project.

​
read_content

Read a file’s raw content by path or permalink.

  • Parameters:
    • path (string)

​
read_note

Read a markdown note by title or permalink.

  • Parameters:
    • identifier (string)
    • page (integer, optional)
    • page_size (integer, optional)

​
recent_activity

Get recent activity from across the knowledge base. Supports natural language or standard timeframes.

  • Parameters:
    • depth (integer, optional)
    • max_related (integer, optional)
    • page (integer, optional)
    • page_size (integer, optional)
    • timeframe (string, optional)
    • type (string, optional)

​
search_notes

Search across all content in the knowledge base.

  • Parameters:
    • query (string)
    • after_date (string, optional)
    • entity_types (string, optional)
    • page (integer, optional)
    • page_size (integer, optional)
    • search_type (string, optional)
    • types (string, optional)

​
write_note

Create or update a markdown note. Returns a markdown formatted summary of the semantic content.

  • Parameters:
    • content (string)
    • folder (string)
    • title (string)
    • tags (string, optional)

​
Additional Resources