Add persistent memory to AI assistants. Store and recall info across conversations.
Add persistent memory to AI assistants. Store and recall info across conversations. Exposed over MCP by the memphora mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
Add persistent memory to Claude, Cursor, Windsurf, and other AI assistants using the Model Context Protocol (MCP).
This MCP server connects your AI assistant to Memphora, giving it the ability to:
Everything the assistant can do here goes through one of these:
memphora_search — Search memories for relevant informationmemphora_store — Store new information for future recallmemphora_extract_conversation — Extract memories from a conversationmemphora_list_memories — List all stored memoriesmemphora_delete — Delete a specific memoryCursor — The Cursor tool exposed by this serverWindsurf — The Windsurf tool exposed by this serverTesting — The Testing tool exposed by this serverInstallation goes through your MCP client rather than a global install: point it at memphora-mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
You will need 2 environment variables: MEMPHORA_API_KEY, MEMPHORA_USER_ID. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Memphora's toolset — memphora_search, memphora_store, memphora_extract_conversation and 5 more — is a fair guide to whether it matches your workflow. It is maintained by Memphora; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Memphora's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| memphora_search | Search memories for relevant information |
| memphora_store | Store new information for future recall |
| memphora_extract_conversation | Extract memories from a conversation |
| memphora_list_memories | List all stored memories |
| memphora_delete | Delete a specific memory |
| Cursor | The Cursor tool exposed by this server. |
| Windsurf | The Windsurf tool exposed by this server. |
| Testing | The Testing tool exposed by this server. |
{
"mcpServers": {
"memphora": {
"command": "uvx",
"args": ["memphora-mcp"],
"env": {
"MEMPHORA_API_KEY": "your-value",
"MEMPHORA_USER_ID": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| MEMPHORA_API_KEY | Credential the server authenticates with. | Yes |
| MEMPHORA_USER_ID | Configuration value read at startup. | 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.