MCP server exposing agent-memory-daemon to Kiro, Claude Desktop, Cursor, and any MCP-compatible client.
MCP server exposing agent-memory-daemon to Kiro, Claude Desktop, Cursor, and any MCP-compatible client. The mcp agent memory mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 4 defined tools rather than through you.
Everything the assistant can do here goes through one of these:
memory_read — Read the agent memory index (MEMORY.md) and optionally specific topic files. Call with no arguments to load only the lightweight index (cheap). Passmemory_append_session — Append a session summary to the sessions directory. The daemon will later extract durable memories from it. Call this at the end of meaningfulmemory_search — Search memory files for a substring. Use this to recall specific facts without loading everythingCursor — Add to ~/.cursor/mcp.json with the same server block (including autoApprove)You will need 2 environment variables: MEMORY_DIRECTORY, SESSION_DIRECTORY. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Installation goes through your MCP client rather than a global install: point it at mcp-agent-memory on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
Plenty of knowledge and memory servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. MCP Agent Memory's toolset — memory_read, memory_append_session, memory_search and 1 more — is a fair guide to whether it matches your workflow. It is maintained by tverney; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| memory_read | Read the agent memory index (MEMORY.md) and optionally specific topic files. Call with no arguments to load only the lightweight index (cheap). Pass topics only when you need the full content of a specific topic file. |
| memory_append_session | Append a session summary to the sessions directory. The daemon will later extract durable memories from it. Call this at the end of meaningful exchanges. Keep summaries focused on durable findings and decisions (target 3 |
| memory_search | Search memory files for a substring. Use this to recall specific facts without loading everything. |
| Cursor | Add to ~/.cursor/mcp.json with the same server block (including autoApprove). |
{
"mcpServers": {
"agent-memory": {
"command": "npx",
"args": ["-y", "mcp-agent-memory"],
"env": {
"MEMORY_DIRECTORY": "your-value",
"SESSION_DIRECTORY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| MEMORY_DIRECTORY | Filesystem location the server is allowed to use. | Optional |
| SESSION_DIRECTORY | Filesystem location the server is allowed to use. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.