AI & Machine Learning
agentmystro.com
Provides deterministic classification and advisory routing for prompts to optimize AI model selection.
ENDPOINT 1
https://agentmystro.com/mcp
MCP server metadata
- Name
- agent-mystro
- Version
- 0.1.0
Agent Mystro classifies a prompt into a task type and reports which model has earned that kind of work, learned from blind picks. mystro_classify and mystro_route make no provider call and cost nothing to run. Every tools/call requires an Agent Mystro API key: Authorization: Bearer mk_live_...
Known tools 3
mystro_classifyClassify a prompt into Agent Mystro's task taxonomy with the same deterministic weighted-signal scorer that backs every /v1/chat/completions call.
Inferred read-onlymystro_modelsAgent Mystro's current routing table: every task type it classifies, whether each one is backed by a blind-tested battery or flagged unmeasured, the population prior strength per model rung (arm), and which arms are servable today.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.agent-mystro]
url = "https://agentmystro.com/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"agent-mystro": {
"type": "http",
"url": "https://agentmystro.com/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: agent-mystro
Remote MCP URL: https://agentmystro.com/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"agent-mystro": {
"url": "https://agentmystro.com/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"agent-mystro": {
"type": "http",
"url": "https://agentmystro.com/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "agent-mystro",
"transport": "streamable-http",
"url": "https://agentmystro.com/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for agentmystro.com was fetched 2026-09-06T23:54:37.338Z.
agentmystro.com is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.