MADB — Agent Memory Database MCP Server
io.github.spshkar84/madb-memory
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the MADB — Agent Memory Database MCP server?
Durable causal memory for AI agents — semantic recall, causal lineage, and skills. Local-first.
How to install MADB — Agent Memory Database
Copy-paste configuration for popular MCP clients.
MADB_DATA_DIRWhere MADB stores your causal memory — local, on your machine (default ~/.madb/data).
MADB_TENANT_IDTenant namespace key for separating memory streams (e.g. per project). Defaults to a built-in namespace.
MADB_TELEMETRYSet to 'off' to disable anonymous, count-only usage telemetry.
{
"mcpServers": {
"madb-memory": {
"command": "uvx",
"args": [
"madb-mcp-server"
],
"env": {
"MADB_DATA_DIR": "<YOUR_MADB_DATA_DIR>",
"MADB_TENANT_ID": "<YOUR_MADB_TENANT_ID>",
"MADB_TELEMETRY": "<YOUR_MADB_TELEMETRY>"
}
}
}
}Related MCP servers

io.github.spuentesp/lain
High-performance knowledge graph MCP server for AI coding agents with semantic search.
Ping 134+ free coding LLMs across 17 providers, rank by latency, pick the fastest.

Kosha Model Discovery
Tells your agent which model to use and what it costs, across 45 providers and local runtimes.

Tokens and cost for Claude Code, Codex and 14 more AI coding agents, from local session files.

io.github.sqemo/sqemo
Design ERDs with your team's naming standards: query/edit entities and relationships, SQL/DBML
