Install MCP Agent Memory

Pick your client, copy the command, done.

Manual setup required. The maintainer's config contains paths only you know - edit the placeholders below before adding it to Claude Code.

Run this once before adding it to Claude Code.

pip install mcp pydantic
python3 shared_memory_mcp.py

claude mcp add mcp-agent-memory -- python3 /path/to/shared_memory_mcp.py

Replace any placeholder paths in the command with the real path on your machine.

Available Tools (9)

Once configured, MCP Agent Memory gives your AI agent access to:

add_memoryCreate new entry with tags, priority, and metadata.

agent_namecontenttagspriority

read_memoryRead memory entries with advanced filtering and sorting.

filtersort

update_memoryModify existing memory entries.

idcontenttagspriority

delete_memoryRemove specific memory entries.

id

get_memoryRetrieve a single memory entry by its ID.

id

search_memoryPerform full-text search across all memory fields.

query

get_memory_statsRetrieve memory analytics and statistics.

clear_memoryClear all memory entries with an automatic backup.

health_checkCheck the system health status.

After setup, try these prompts with your AI agent:

→Add a memory entry noting that the project analysis is complete and found 3 key insights.

→Search my shared memory for any entries related to 'analysis' to see what previous agents found.

→Get the current memory statistics to see how many entries are stored.

→Delete the memory entry with ID 123 as it is no longer relevant.

Prerequisites & system requirements

An MCP-compatible client (Claude Code, Cursor, Windsurf, Claude Desktop, or Codex)
Python 3.8+ with pip installed

Conare · memory for coding agents

Save the docs, env vars, and workflow around MCP Agent Memory in Conare so Claude Code, Codex, and Cursor remember it next time.