Other · Local MCP server
Memphora
Add persistent memory to AI assistants. Store and recall info across conversations.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.Memphora/memphora- Version
- 0.1.3
- Status
- Active
- Category
- other
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2025-12-10
- Updated
- 2025-12-10
- Publisher
- Memphora (GitHub)
- Repository
- github.com/Memphora/memphora-mcp
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | memphora-mcp | 0.1.3 | stdio |
How to connect Memphora
Memphora runs locally from a Python package published to PyPI: memphora-mcp version 0.1.3. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx memphora-mcp. It reads these environment variables: MEMPHORA_API_KEY (required, secret) and MEMPHORA_USER_ID; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"memphora": {
"command": "uvx",
"args": [
"memphora-mcp"
],
"env": {
"MEMPHORA_API_KEY": "<secret>",
"MEMPHORA_USER_ID": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More other servers
| Server | Runs |
|---|---|
| MemoryLayerLocal-first persistent memory for AI agents, with reasoning and formal verification. | Local · stdio |
| MemoryPluginGive every AI you use one shared, permanent memory. Store once, recall in whichever AI you open. | Remote · HTTP, SSE |
| MemoweftPortable AI memory as MCP tools: five reads and three controlled writes. | Local · stdio |
| MemPersistDurable, revision-pinned memory storage and retrieval for AI conversations. | Remote · HTTP |
| MemraPersistent memory for AI agents. EU-hosted, privacy-first, hybrid recall, contradiction detection. | Remote · HTTP |
| MemtetherCross-client AI memory hub: agents share one SQLite memory.db via file-level pointers. | Local · stdio |
| MemtrustIndependent, reproducible benchmark harness for agent-memory backends. | Local · stdio |
| MemxusPersistent memory layer that saves and recalls your project context and preferences. | Remote · HTTP |