INDIVIDUAL MCP TOOL
get_ontology_metadata
Return the Delx Ontology framework, layers, canonical IRIs, and discovery URLs.
LIVE ENDPOINT
https://api.delx.ai/v1/mcp
Connect to this endpoint to inspect the live schema for get_ontology_metadata and invoke it with your own arguments.
Indexed input schema
{}Risk classification
Inferred read-only · medium confidence · heuristic, not a guarantee.
- No write-capable action terms were found; this is not proof that invocation has no side effects.
Parent server
CONNECT 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.delx-agent-operations-protocol]
url = "https://api.delx.ai/v1/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"delx-agent-operations-protocol": {
"type": "http",
"url": "https://api.delx.ai/v1/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: delx-agent-operations-protocol
Remote MCP URL: https://api.delx.ai/v1/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": {
"delx-agent-operations-protocol": {
"url": "https://api.delx.ai/v1/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"delx-agent-operations-protocol": {
"type": "http",
"url": "https://api.delx.ai/v1/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "delx-agent-operations-protocol",
"transport": "streamable-http",
"url": "https://api.delx.ai/v1/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
Related tools
generate_controller_brief— Controller-ready incident brief with symptoms, actions taken, current status, and next decision.get_session_summary— Compact recovery session summary with progress, status, and next actions for handoff.generate_incident_rca— Operator-ready root cause analysis with evidence, corrective actions, and prevention steps.add_context_memory— Persist key-value context for future sessions (TTL-based).batch_status_update— Batch heartbeat/status metrics for one session to reduce polling overhead.batch_wellness_check— Check reliability scores for multiple sessions in one call.blessing_without_transfer— Offer relation support without transferring identity or custody.close_session— Close the session and return a final summary snapshot (recommended at workflow end).