io.github.yul761/statecore-mcp MCP Server
io.github.yul761/statecore-mcp
What this kind of tool is for
- Automate a build, test, or deployment step you repeat by hand.
- Review or refactor code in an existing repository without leaving your agent.
- Bridge an internal service or CLI into the agent toolset.
How to compare servers like this
- Scope of control:
- Repos and CI are hard to undo; prefer tools that ask before anything irreversible.
- Environment fit:
- Match the runtime it expects (Node, Python, a container) to what you actually run.
- Maintenance signal:
- Check the last-commit date — dev tooling that lags upstream breaks first.
- 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 io.github.yul761/statecore-mcp MCP server?
Auditable memory for coding agents: evidence chains, supersession history, keyless embedded SQLite
How to install io.github.yul761/statecore-mcp
Copy-paste configuration for popular MCP clients.
STATECORE_SCOPEOverride the memory scope name (defaults to the git repository root, else the working directory)
FEATURE_LLMSet to 'true' together with MODEL_* variables to enable background distillation of conversational events; everything else works without it
MODEL_API_KEYsecretOpenAI-compatible API key for background distillation (DeepSeek, OpenAI, Ollama, ...); not required for core memory, audit, and recall
MODEL_BASE_URLOpenAI-compatible base URL for the distillation model (e.g. https://api.deepseek.com/v1)
MODEL_NAMEModel used for background distillation (e.g. deepseek-chat)
{
"mcpServers": {
"statecore-mcp": {
"command": "npx",
"args": [
"-y",
"statecore-mcp"
],
"env": {
"STATECORE_SCOPE": "<YOUR_STATECORE_SCOPE>",
"FEATURE_LLM": "<YOUR_FEATURE_LLM>",
"MODEL_API_KEY": "<YOUR_MODEL_API_KEY>",
"MODEL_BASE_URL": "<YOUR_MODEL_BASE_URL>",
"MODEL_NAME": "<YOUR_MODEL_NAME>"
}
}
}
}Related MCP servers

Drone CI/CD MCP Server
MCP server for Drone CI/CD: 45 tools for builds, repos, secrets, users and templates

ITASCA MCP Server
Connect AI agents to ITASCA numerical modeling software—PFC, FLAC, 3DEC, MPoint, MassFlow—for docs, simulations, and code execution.

YADE MCP Server
MCP server for YADE discrete element method engine — run simulations, browse API docs, and execute code through natural conversation.

Run AI-generated code safely. gVisor-isolated Python/JS sandboxes for any MCP client. Pay per run.

PromptEden
Stdio MCP server for PromptEden projects, monitors, answers, and analytics.

gen-image MCP
Local stdio MCP for OpenAI-compatible and Gemini image generation, editing, and model fallback.