Global Agent Memory — Claude Code MCP server: what it does & setup
Provides local Markdown-backed shared memory for Claude Code and other agents, with a human review queue in a web dashboard.
claude mcp add global-agent-memory -- uvx global-memory-mcpWhat Global Agent Memory does
Global Agent Memory connects coding assistants like Claude Code and Codex to an Obsidian-compatible Markdown vault. Agents do not write directly to permanent records. Instead, they submit context as candidate notes, leaving approval, edits, or rejection to the developer through a local browser dashboard.
Search runs on SQLite FTS5 for local keyword matching, with optional semantic embeddings via Ollama and sqlite-vec. Background daemons are optional because CLI operations execute in-process when the service is idle. When running the dashboard, the process binds strictly to 127.0.0.1 with a bearer token.
Running the package via uvx requires Python 3.12 or newer on your machine. Sensitive context can also be marked as protected, stopping agents from reading it without owner confirmation.
What it helps with
- share architectural context across different coding agents
- review proposed agent notes before storing them permanently
- retain project conventions in plain Markdown files
- search past bug resolutions with local keyword and vector indexes
Example prompts for the agent
- Look up our database migration rules in project memory.
- Propose a memory candidate for our standard error response format.
- Search the vault for how we resolved the Docker socket permission issue.
How to install Global Agent Memory
Platform CLI
claude mcp add global-agent-memory -- uvx global-memory-mcpuvx runs the command named after the package; if the README names another one, use uvx --from global-memory-mcp <command>
Platform CLI
codex mcp add global-agent-memory -- uvx global-memory-mcpuvx runs the command named after the package; if the README names another one, use uvx --from global-memory-mcp <command>
Config file
{
"mcpServers": {
"global-agent-memory": {
"command": "uvx",
"args": [
"global-memory-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from global-memory-mcp <command>
Config file
{
"servers": {
"global-agent-memory": {
"type": "stdio",
"command": "uvx",
"args": [
"global-memory-mcp"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from global-memory-mcp <command>
Platform CLI
gemini mcp add global-agent-memory uvx global-memory-mcpuvx runs the command named after the package; if the README names another one, use uvx --from global-memory-mcp <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Global Agent Memory
How to install Global Agent Memory in Claude Code?
Run claude mcp add global-agent-memory -- uvx global-memory-mcp in your terminal. Python 3.12 or higher must be installed on your system.
What does Global Agent Memory do?
It provides a shared, local Markdown knowledge base for coding assistants. New knowledge entries appear as candidates that you approve or edit via a local web UI.
Does it require a persistent background daemon?
No, CLI and agent calls execute in-process without a daemon running. The local server on 127.0.0.1 is only needed when using the web dashboard or continuous file watching.
