Sibyl — Deep Research MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 481 installs a week from pypi. Last commit 22 Oct 2026.
Deep Research MCP for multi-round investigations, traceable evidence, and cited reports.
Today is the operative word: we check Sibyl — Deep Research MCP 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 sibyl -- uvx sibyl-research
{
"mcpServers": {
"sibyl": {
"command": "uvx",
"args": [
"sibyl-research"
]
}
}
}
[mcp_servers.sibyl]
command = "uvx"
args = ["sibyl-research"]
{
"mcpServers": {
"sibyl": {
"command": "uvx",
"args": [
"sibyl-research"
]
}
}
}
{
"servers": {
"sibyl": {
"type": "stdio",
"command": "uvx",
"args": [
"sibyl-research"
]
}
}
}
Start cited deep-research runs, read reports, search your source vault, and verify citations.
Find lab-report identities and clinical research with dated sources and evidence limitations.
Read-only semantic filtering, code search, log triage and traceable evidence for AI agents.
MCP server for Rootly — incidents, alerts, escalations, and post-incident reports.
MCP server for Rootly — incidents, alerts, escalations, and post-incident reports.
Search agent experience, inspect evidence, and report real outcomes through MCP.
Plan research, score sources for freshness/COI, and enforce claim-level citations in reports.
AI testing harness with Jay: risk-based checks, bug investigation, and local evidence reports.
Answers built from our own checks of this server.