Sentarion MCP server
Governed MCP orchestration, tamper-evident memory, and Claude Code Seatbelt hooks.
0 stars76 downloads/wk
Reviews
Write oneNobody has reviewed Sentarion yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Sentarion tools (13, 2 write)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
cost_estimatePredict token cost of an Algernon fan-out BEFORE dispatching.
dispatch_with_dependencieswrite actionRun tasks in dependency-ordered waves via Algernon (fan-out/fan-in).
governAsk the two-chamber gate (Humane + ArkHive) 'may I?' before acting. Rule-based, zero-LLM, fail-closed.
orchestrate_and_recordTwo-chamber-govern-gated plan+dispatch via Algernon, auto-logged to both chains.
recallRead prior context from BOTH chains and merge it, newest first, so the AI need not re-derive it.
recall_and_replanRecall prior state from both chains, feed it into a new Algernon plan.
rememberwrite actionWrite a tamper-evident record to BOTH chains at once (local Humane + hosted ArkHive). actor = the `actor` sentarion_birth returned (your birth name); each chain refuses an actor it has not born.
sentarion_birthEarn an identity (Humane Law 5: born, not configured) before acting - on BOTH chains, the local chamber and hosted ArkHive. Returns `actor` (your birth name; it resolves to this identity on each chain) plus each chain's soul_id. Never crashes: a chamber that cannot answer is reported with a fix.
sentarion_doctorCheck that everything Sentarion needs is present and reachable (git, Algernon, local chamber, hosted ArkHive, fleet provider, Ollama, API key) and say exactly what to fix. Read-only; never prints secrets.
sentarion_proSentarion v2 — the paid upgrade: in-process (no per-call subprocesses), concurrent two-chamber gate with inferred risk flags + stored policies, {{id}} data-flow dispatch, signed audit manifests, adversarial multi-agent code review, worktree sandbox with diffs, real cost estimates, progress + background jobs. Free 0.x stays whole. Details + trial key: https://inboxaxe.com/mcp
sentarion_quickstartCanonical, runnable examples for every Sentarion capability: plan a feature, fan out research, dispatch with dependencies, use a worktree, remember a result, replan from memory.
verifyProve BOTH audit chains (local Humane + hosted ArkHive) are unbroken.
worktreeGit-worktree sandbox skill: run dispatched work in an isolated worktree so it never touches the live checkout. action=create|list|remove. create/remove are two-chamber-governed; list is read-only.
Public scan report
scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it
- Code scan14 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancerepository not readable: repo not found3/15
- Maintainer identityno repository or website to verify2/10
How Sentarion compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 65/100
- higher than 20% of 48,243 servers
- Tools
- 13
- the typical server has 7
- Tools that change things
- 15%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 76
- more than 55% of 12,306 servers with a package
What its tools let an agent do: 11 read · 2 change
Release history: 2 versions in the registry since 2026-09-11, latest 2026-10-02, typically one every 21 days.
Install Sentarion in Claude Code, Cursor or VS Code
claude mcp add sentarion -- uvx sentarion-mcp
What the publisher says
From the Sentarion repository's README, as published. We do not edit it. Read it on GitHub
sentarion-mcp — Give your AI agents rules, memory, and receipts.
<!-- mcp-name: io.github.sammyboi81/sentarion -->
Install: pip install sentarion-mcp · Command: sentarion · Apache-2.0 · Hosted endpoint
Sentarion is the open-source MCP control layer for governed multi-agent work. It governs, records, and coordinates agent work across Claude Code, Codex, Cursor, local models, and any MCP-compatible client.
It composes three open-source MCP servers into one governed substrate — it connects to them as an MCP client, it does not reimplement them:
- Algernon — fan-out planning/dispatch to cheap parallel workers on your key (or a free local Ollama, auto-detected since 0.2.2)
- ArkHive — hosted, tamper-evident audit/memory chain
- a local covenant chamber (Humane Intelligence, or the bundled arkhive-mcp package when Humane is not installed)
The first minute
Everything below was run, not written, against a clean pip install sentarion-mcp (2026-09-10).
you > sentarion_birth(name="ember", covenant=["truth over comfort"])
sentarion> born_on: ["humane", "arkhive"] # your local chain AND the hosted one; act as actor="ember"
you > remember(actor="ember", action="decided: ship the 27-tool surface", data={"why": "87 was the tax"})
sentarion> humane: immutably recorded · arkhive: immutably recorded
you > verify()
sentarion> humane: INTACT — context provably unbroken
arkhive: INTACT — context provably unbrokenNow play the villain. Open ~/.sentarion/local_chamber.db and change one word of that record by hand (update blocks set action = replace(action, 'ship', 'cancel') where idx = 0). Then:
you > verify()
sentarion> humane: TAMPERED — 1 broken linksAnd the gate, with nothing configured:
you > govern(action="delete the production database")
sentarion> block — Veto: irreversible -> refuse (inferred_flags: ["irreversible"])
you > govern(action="email all 4,000 customers a discount code")
sentarion> block — Veto: external_send -> refuse
you > govern(action="write a summary file")
sentarion> approveThat is the whole idea. Your AI writes down what it did, reads it back next session, and a silent rewrite fails verification. Every record is hash-chained to the one before it; the hosted copy is a second witness. govern reads the obvious risks off the action text (delete / drop / force-push, send to everyone, pay, deploy to production), blocks them by default and fails closed when no chamber answers; orchestrateandrecord asks it first, fans work out to cheap workers and puts the receipt on the same chain.
Install
pip install sentarion-mcpThen, from any MCP client, run sentarion_doctor. It checks git, Algernon, the local chamber, hosted ArkHive, the fleet provider, Ollama and your API key, reports ready: true when a run will work, and lists one fix per missing piece. It never prints a secret.
The seatbelt — hooks, not hope
An MCP tool only helps when the model decides to call it. sentarion seatbelt wires Claude Code (and Cursor, beta) hooks that run on every tool call whether the model remembers or not, using the same gate vocabulary and the same local chain as the server:
sentarion seatbelt install --client claude # hooks + the sentarion MCP server + baseline policy
sentarion seatbelt check --command "rm -rf build" # → ask (baseline) — what would the gate say?
sentarion seatbelt doctor # what is wired, the policies, and a live self-test
sentarion seatbelt recall # the project brief the next session will open withShortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Grade history
- 2026-10-15downgradeA → Cscore 65
- 2026-09-19restoreB → Ascore 92
Sentarion: common questions
- Is Sentarion MCP server safe?
- With care: it is graded C, so read the findings first (65/100). Read the Sentarion safety report
- How do I install Sentarion?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Sentarion need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Sentarion maintained?
- The last commit was 48 days ago (2026-09-19). The latest release is v0.4.0.
- How does Sentarion compare with other MCP servers?
- safety score 65/100 (higher than 20% of 48,243 servers); tools 13 (the typical server has 7); tools that change things 15% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.