MCP Server Decisions runs on your own machine — the client starts it, so there is no endpoint to ping. 66 installs a week from pypi. Last commit 3 Sep 2026.
Decision tracking with prediction validation and outcome gates for AI agents
Today is the operative word: we check MCP Server Decisions every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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-server-decisions -- uvx mcp-server-decisions
{
"mcpServers": {
"mcp-server-decisions": {
"args": [
"mcp-server-decisions"
],
"command": "uvx"
}
}
}
[mcp_servers.mcp-server-decisions]
command = "uvx"
args = ["mcp-server-decisions"]
{
"mcpServers": {
"mcp-server-decisions": {
"args": [
"mcp-server-decisions"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"mcp-server-decisions": {
"args": [
"mcp-server-decisions"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
MCP_DECISIONS_LOG_PATH (Path to decisions log file (default: ~/.local/share/mcp-decisions/decisions_log.json)).
The author declared them in the registry entry; get the values from the project itself.
Tamper-evident decision audit trail and outcome-weighted memory for AI trading agents.
AI tech lead for coding agents with validation and impact analysis
Live competitive-game predictions, meta data and decision tools for AI agents.
Output quality control and validation for AI agents
Decision learning for AI agent actions. Evaluate, score, decide, and learn from outcomes.
Semilattice lets agents make predictions about audiences for content testing and decision making.
Multi-agent governance: task orchestration, compliance, decision validation, and ML predictions.
Korean business record validation and workflow safety gates for AI agents.
Answers built from our own checks of this server.