Other · Local MCP server
Memtether
Cross-client AI memory hub: agents share one SQLite memory.db via file-level pointers.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.lanbass869-cell/memtether- Version
- 0.1.0a17
- Status
- Active
- Category
- other
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-10-04
- Updated
- 2026-10-04
- Publisher
- lanbass869-cell (GitHub)
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/lanbass869-cell) · how
- Listed under
- SQLite MCP servers
- Repository
- github.com/MemTether/MemTether
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | memtether | 0.1.0a17 | stdio |
How to connect Memtether
Memtether runs locally from a Python package published to PyPI: memtether version 0.1.0a17. 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 memtether. It reads these environment variables: MEM_DB and MEM_DEFAULT_SOURCE; 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": {
"memtether": {
"command": "uvx",
"args": [
"memtether"
],
"env": {
"MEM_DB": "<value>",
"MEM_DEFAULT_SOURCE": "<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 |
|---|---|
| MemPersistDurable, revision-pinned memory storage and retrieval for AI conversations. | Remote · HTTPLive check: sign-in required |
| MemphoraAdd persistent memory to AI assistants. Store and recall info across conversations. | Local · stdio |
| MemQ Team SyncShared project memory that keeps teammates and AI agents aligned across sessions. | Remote & Local · HTTP, stdioLive check: sign-in required |
| MemraPersistent memory for AI agents. EU-hosted, privacy-first, hybrid recall, contradiction detection. | Remote · HTTPLive check: ✓ handshake |
| MemtrustIndependent, reproducible benchmark harness for agent-memory backends. | Local · stdio |
| MemxusPersistent memory layer that saves and recalls your project context and preferences. | Remote · HTTPLive check: ✓ handshake |
| MencoroTrack and manage how your brand appears in AI answers: rank, mentions, sentiment, share of voice. | Remote & Local · HTTP, stdioLive check: sign-in required |
| MendriftMCP server for ML drift detection, MLflow registry diffing, and HMAC-gated model rollback. | Local · stdio |