Agentic Memory MCP
Agentic Memory provides persistent memory for AI agents, enabling short-term recall, semantic search, and auto-summarized long-term knowledge. The MCP server exposes 17 tools via stdio, allowing agents to store, recall, search, and bootstrap context across sessions without managing infrastructure.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
Checks and signals
Each line is separate evidence, not a trust score.
- Popularity 1 GitHub star
What you can do with it
- Store and recall recent conversation messages for short-term context
- Perform semantic search across past conversations to find relevant information
- Bootstrap full agent context including messages, entries, and scratchpad
- Manage long-term memory entries and entities for agent knowledge
Source and maintenance
- Last repository push
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
agmry 1.10.0
{
"version": "1.10.0",
"transport": "stdio",
"identifier": "agmry",
"runtimeHint": "npx",
"registryType": "npm",
"registryBaseUrl": "https://registry.npmjs.org",
"runtimeArguments": [
{
"type": "positional",
"value": "mcp-serve",
"isRequired": true
}
],
"environmentVariables": [
{
"name": "AGMRY_API_KEY",
"description": "Agentic Memory API key (amk_...). Optional for tool discovery; required to call a tool. Get one instantly with `agmry signup my-project` — no browser, no card, live for 48h; $0 card-auth starts the free 7-day trial."
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Maintenance history
Public check and source-refresh events. Editorial and ownership records remain private.
- · repository · passed · metadata changed · updated
- · backfill · recorded · Pre-expansion baseline; unobserved rich metadata remains unknown
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"agentic-memory-mcp": {
"command": "npx",
"args": [
"-y",
"agmry@1.10.0"
],
"env": {
"AGMRY_API_KEY": "<YOUR_AGMRY_API_KEY>"
}
}
}
}Cline
{
"mcpServers": {
"agentic-memory-mcp": {
"command": "npx",
"args": [
"-y",
"agmry@1.10.0"
],
"env": {
"AGMRY_API_KEY": "<YOUR_AGMRY_API_KEY>"
}
}
}
}VS Code
{
"servers": {
"agentic-memory-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agmry@1.10.0"
],
"env": {
"AGMRY_API_KEY": "<YOUR_AGMRY_API_KEY>"
}
}
}
}Claude Desktop
{
"mcpServers": {
"agentic-memory-mcp": {
"command": "npx",
"args": [
"-y",
"agmry@1.10.0"
],
"env": {
"AGMRY_API_KEY": "<YOUR_AGMRY_API_KEY>"
}
}
}
}Let your agent find its tools
Find servers like Agentic Memory MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.