MCP Adr Analysis Server runs on your own machine — the client starts it, so there is no endpoint to ping. 1 092 installs a week from npm. Last commit 17 Sep 2026.
ADR drift detection, content safety, and decision memory for architectural decisions
We read the source, 19 min ago · rules 3dff92dd89df
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.
## Update Requirements
- **Update Type**: ${updateType}
- **Focus Areas**: ${
updateType === 'content'
? 'Decision content and rationale'
: updateType === 'status'
? 'Decision status and lifecycle'
: updateType === 'consequences'
…
testOutput = execSync(command, {
const adrDirectory = path.join(projectPath, this.config.adrDirectory);
for (const [key, value] of Object.entries(process.env)) {
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
export MCP_GATEWAY_DOCKER_COMMAND='docker run -i --rm --network host -v /var/run/docker.sock:/var/run/docker.sock -e MCP_GATEWAY_PORT -e MCP_GATEWAY_DOMAIN -e MCP_GATEWAY_API_KEY -e MCP_GATEWAY_PAYLOAD_DIR -e MCP_GATEWAY_PAYLOAD_SIZE_THRESHOLD -e DEBUG -e MCP_GATEWAY_LO…
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 mcp-adr-analysis-server -- npx -y mcp-adr-analysis-server
{
"mcpServers": {
"mcp-adr-analysis-server": {
"args": [
"-y",
"mcp-adr-analysis-server"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-adr-analysis-server]
command = "npx"
args = ["-y", "mcp-adr-analysis-server"]
{
"mcpServers": {
"mcp-adr-analysis-server": {
"args": [
"-y",
"mcp-adr-analysis-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-adr-analysis-server": {
"args": [
"-y",
"mcp-adr-analysis-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
PROJECT_PATH (Path to the project directory to analyze (defaults to current directory)), OPENROUTER_API_KEY (OpenRouter API key for AI-powered analysis (required for full execution mode)), EXECUTION_MODE (Execution mode: 'ce-mcp' (default), 'full' for AI results, or 'prompt-only' for prompts), ADR_DIRECTORY (ADR directory relative to project path (default: docs/adrs)).
The author declared them in the registry entry; get the values from the project itself.
Persistent memory and drift detection for AI agents across session restarts.
Architectural decision memory for LLM-native workflows — markdown for humans, a graph for agents.
Session memory for coding agents: local-first recall, drift detection, on-device inference.
Persistent decision memory for agents — learns which action works in which context
Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
Local MCP server for architectural decisions, traceability, and non-authoritative proposals.
Episodic memory and architectural policy for AI agents. Frames, Atlas, and Policy.
MCP server for Architectural Decision Records: navigate, author, validate, link, and analyze them.
Answers built from our own checks of this server.