Other · Local MCP server
Memory Arbiter MCP
Local SQLite MCP memory: evidence-based recall, advisory conflict notices, authorized governance.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.billy12151/memory-arbiter-mcp- Version
- 0.16.12
- Status
- Active
- Category
- other
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-09-22
- Updated
- 2026-09-22
- Publisher
- billy12151 (GitHub)
- Repository
- github.com/billy12151/memory-arbiter-mcp
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPI | memory-arbiter-mcp | 0.16.12 | stdio |
How to connect Memory Arbiter MCP
Memory Arbiter MCP runs locally from a Python package published to PyPI: memory-arbiter-mcp version 0.16.12. 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 memory-arbiter-mcp. It reads these environment variables: MEMORY_ARBITER_CONFIG, MEMORY_ARBITER_CLIENT, MEMORY_ARBITER_AGENT_ID, MEMORY_ARBITER_DB_PATH, MEMORY_ARBITER_BACKUP_JSONL and MEMORY_ARBITER_MCP_TRANSPORT; 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": {
"memory-arbiter-mcp": {
"command": "uvx",
"args": [
"memory-arbiter-mcp"
],
"env": {
"MEMORY_ARBITER_CONFIG": "<value>",
"MEMORY_ARBITER_CLIENT": "<value>",
"MEMORY_ARBITER_AGENT_ID": "<value>",
"MEMORY_ARBITER_DB_PATH": "<value>",
"MEMORY_ARBITER_BACKUP_JSONL": "<value>",
"MEMORY_ARBITER_MCP_TRANSPORT": "<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 |
|---|---|
| MemoroPersonal AI memory layer on your own computer. Read/write durable memory across MCP clients. | Local · stdio |
| MemoryShared, persistent memory for AI agents — works with Claude, Kiro, Cursor, or any MCP client. | Local · stdio |
| MemoryLong-term memory for AI assistants. Isolated per-user storage, recall across conversations. | Remote · HTTP |
| MemoryChinese-first brain-inspired memory MCP — hybrid recall, 7-layer user profile, workspace assembly. | Remote · HTTP |
| Memory Key CountCount keys in a JSON object. Values discarded. | Remote · HTTP |
| Memory PulseCorrections that outlive the session. A guard blocks the edit that writes the old value back. | Local · stdio |
| Memory VaultPortable AI memory shared across models and harnesses - plain markdown you own. | Remote & Local · HTTP, stdio |
| MemoryLayerLocal-first persistent memory for AI agents, with reasoning and formal verification. | Local · stdio |