# See repository for install instructions
{
"mcpServers": {
"aiseaotter-otterscore": {
"command": "npx",
"args": []
}
}
}
{
"mcpServers": {
"aiseaotter-otterscore": {
"command": "npx",
"args": []
}
}
}
{
"mcpServers": {
"aiseaotter-otterscore": {
"command": "npx",
"args": []
}
}
}
TRY THIS MCP
About This MCP Server
The ai.seaotter/otterscore server is a Model Context Protocol server that operates as a hostile-by-default critic, evaluating the output of AI agents against a predefined acceptance policy. It enables remote connections, allowing developers to integrate this critical evaluation capability into their AI workflows. Developers would use this server to ensure their AI agents are producing output that meets specific acceptance criteria, providing a layer of quality control and validation in AI-driven applications.
Hostile-by-default critic that grades AI agent output against your acceptance policy.. This is a Model Context Protocol (MCP) server that extends AI assistants like Claude with ai & machine learning capabilities via the streamable-http transport.
HOW TO USE
Select your AI client above to get the install command. This MCP server uses the streamable-http transport.
What tools does it provide?
The otterscore server extends your AI assistant with ai & machine learning capabilities. Once installed, your AI can use its tools automatically.
