Statecore MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 45 installs a week from npm. Last commit 1 Oct 2026.
Auditable memory for coding agents: evidence chains, supersession history, keyless embedded SQLite
We read the source, 2 h ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
eval(script: string, numkeys: number, key: string, token: string): Promise<number>;
await fetch(`https://api.telegram.org/bot${workerEnv.telegramBotToken}/sendMessage`, {
document.getElementById('api-status').innerHTML = dot('green') + 'running';
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add statecore-mcp -- npx -y statecore-mcp
{
"mcpServers": {
"statecore-mcp": {
"args": [
"-y",
"statecore-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.statecore-mcp]
command = "npx"
args = ["-y", "statecore-mcp"]
{
"mcpServers": {
"statecore-mcp": {
"args": [
"-y",
"statecore-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"statecore-mcp": {
"args": [
"-y",
"statecore-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
STATECORE_SCOPE (Override the memory scope name (defaults to the git repository root, else the working directory)), FEATURE_LLM (Set to 'true' together with MODEL_* variables to enable background distillation of conversational events; everything else works without it), MODEL_API_KEY (OpenAI-compatible API key for background distillation (DeepSeek, OpenAI, Ollama, ...); not required for core memory, audit, and recall), MODEL_BASE_URL (OpenAI-compatible base URL for the distillation model (e.g. https://api.deepseek.com/v1)), MODEL_NAME (Model used for background distillation (e.g. deepseek-chat)).
The author declared them in the registry entry; get the values from the project itself.
Local-first memory for coding agents — MCP server, single SQLite file, local embeddings
Cross-session memory for AI coding agents via six tools; local-first SQLite store.
Persistent local memory for MCP-compatible AI coding agents, stored per repository in SQLite.
Local MCP memory for coding agents. SQLite on your machine — preferences persist across chats.
Persistent, verified, cross-session memory for AI agents. 26 tools. SQLite + sync.
Persistent, verified, cross-session memory for AI agents. 26 tools. SQLite + sync.
Persistent, structured project memory for AI coding agents, stored locally in SQLite.
Local-first persistent memory for AI agents — SQLite + local embeddings, MCP-native, no cloud.
Answers built from our own checks of this server.