Server data from the Official MCP Registry
Governed multi-agent orchestration: fan-out dispatch, safety gates, tamper-evident memory.
About
Governed multi-agent orchestration: fan-out dispatch, safety gates, tamper-evident memory.
Security Report
Sentarion is a well-architected composite MCP server that delegates core functionality to three upstream services (Algernon, ArkHive, Humane) rather than reimplementing them. The codebase demonstrates solid security patterns including a fail-closed two-chamber governance gate, proper subprocess handling in worktree.py, and careful credential management. However, several moderate-severity issues warrant attention: environment variable exposure risks, incomplete error handling, and potential availability concerns when upstream services fail. Supply chain analysis found 5 known vulnerabilities in dependencies (0 critical, 5 high severity). Package verification found 1 issue.
7 files analyzed · 15 issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
How to Install
Add this to your MCP configuration file:
{
"mcpServers": {
"io-github-sammyboi81-sentarion": {
"args": [
"sentarion-mcp"
],
"command": "uvx"
}
}
}Documentation
View on GitHubFrom the project's GitHub README.
sentarion-mcp (v0.1.0)
Composite MCP server wrapping Algernon (fan-out orchestration) and ArkHive (governed audit/memory). Connects to both as an MCP client — does not reimplement either.
What's real right now
cost_estimate— pre-dispatch cost prediction, grounded in Algernon's own published benchmark numbers.dispatch_with_dependencies— fan-out/fan-in wave ordering on top of Algernon's independent-taskalgernon_dispatch.orchestrate_and_record— plan+dispatch, auto-logged to ArkHive'sremember.recall_and_replan— pulls ArkHiverecallhistory into a new Algernon plan.
Governance — real, wired, fail-closed
govern_stub.py now carries the REAL ArkHive govern client (verified against
the live GovernanceBlock engine, 2026-08-18):
- wire in:
{action, flags: [...], rules: [{trigger, action}]} - wire out:
{vetoed: bool, reason, engine: "zero-LLM rule gate", auditable: true} - verdicts are binary (no "pending" state exists in the engine)
- fail-closed: if ArkHive is unreachable, dispatch is blocked — an absent governor never silently approves
- a blocked
orchestrate_and_recordreturns the decision and skips dispatch
Not yet built (deferred, per the earlier feature list)
- Durable/crash-resistant execution via
mcp-agent(Temporal-backed) — listed as a dependency in pyproject.toml but not yet wired into server.py. - Phase-gate state machine (queue→work→review→terminal) inside ArkHive's
govern— depends on #1 above.
Install (once ready)
pip install -e .
Run
sentarion
Support this project 💛
Sentarion, Algernon, and ArkHive are free, open source, and built on our own hardware. If they save you tokens or time:
- Donate: https://dondatabrain.com (Stripe link on the page)
- Go Pro: hosted endpoints, priority support, and the InboxAxe business suite → https://inboxaxe.com
Hosted endpoint
Skip the local install — connect any MCP client to:
https://arkhive.dondatabrain.com/sentarion/mcp
Reviews
No reviews yet
Be the first to review this server!
More Developer Tools MCP Servers
Git
Freeby Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
Fetch
Freeby Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
MCP Marketplace
Freeby mcp-marketplace · Developer Tools
Search and install MCP servers from inside your AI client.
MarkItDown
Freeby Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption