mcpField
E
EvolutionDB Long-Term Memory

EvolutionDB Long-Term Memory

Local
github.com/alptekinMemory & Knowledge

About EvolutionDB Long-Term Memory

Persistent long-term memory for Claude Desktop / Claude Code, backed by EvolutionDB

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"alptekin-evolutiondb-memory": {
"command": "uvx",
"args": [
"mcp-server-evolutiondb"
],
"env": {
"EVOSQL_HOST": "<EVOSQL_HOST>",
"EVOSQL_PORT": "<EVOSQL_PORT>",
"EVOSQL_USER": "<EVOSQL_USER>",
"EVOSQL_PASSWORD": "<EVOSQL_PASSWORD>",
"EVOSQL_DATABASE": "<EVOSQL_DATABASE>",
"MCP_USER_ID": "<MCP_USER_ID>",
"MCP_STORE_PREFIX": "<MCP_STORE_PREFIX>"
}
}
}
}
Run commanduvx mcp-server-evolutiondb
Environment variables to set
EVOSQL_HOSTHostname where EvolutionDB is reachable on the PostgreSQL wire (port 5433).
EVOSQL_PORTEvolutionDB's PostgreSQL-protocol port.
EVOSQL_USERDatabase user.
EVOSQL_PASSWORDSecretDatabase password.
EVOSQL_DATABASEDatabase name to use.
MCP_USER_IDSticky namespace identifier for every memory Claude writes through this server. Server-side override — the LLM cannot fragment your namespace by inventing other IDs.
MCP_STORE_PREFIXPrefix for the auto-created MEMORY STORE / ENTITY STORE catalog objects.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-server-evolutiondb1.17.0

Tools

32

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
factstringYesConcise statement of what to remember.
tagsarrayNoCategorisation labels (e.g. work, preference, family). Optional.
derived_fromarrayNoIf this fact is SYNTHESIZED from other stored memories (e.g. a summary or inference), list their keys here. The row is then marked synthesized and traceable back to those sources; search_memory returns an evidence_chain for it. Optional.

Details

The maintainer has not added details yet. Check the README in the repository.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.