INBOXAXE
Welcome to the Era of RI

Give your AI a memory it cannot lose, a fleet it can command, and a gate it cannot bypass.

Three MCP servers that plug into Claude Desktop, Claude Code, Cursor and Codex in one line. Free to run, forever. The v2 line is what teams pay for when they run it every day.

Free, open source, no telemetry

ArkHive

Tamper-evident local memory. Your AI writes what it did and reads it back next session; every record is hash-chained, so a silent rewrite fails verification.

pip install arkhive-mcp

Tools: birth · remember · recall · verify · govern

GitHub · PyPI · Smithery

Algernon

Fan a goal out to cheap parallel workers on your own key, or on a free local Ollama it detects automatically. The expensive mind stops doing the grunt work.

pip install algernon-mcp

Tools: algernon_doctor · plan · dispatch · orchestrate

GitHub · PyPI

Sentarion

Governed orchestration: every dispatch passes a fail-closed two-chamber gate first and is logged to both memory chains. Composes the two above.

pip install sentarion-mcp

Tools: govern · orchestrate_and_record · dispatch_with_dependencies · worktree · …

GitHub · PyPI · Smithery

Claude Code / Cursor config

{ "mcpServers": {
    "sentarion": { "command": "sentarion", "env": { "ANTHROPIC_API_KEY": "sk-ant-..." } },
    "arkhive":   { "command": "arkhive-mcp" },
    "algernon":  { "command": "algernon-mcp" }
} }

No key? Leave it out. Algernon and Sentarion use your local Ollama when one is running. Hosted, no install: https://arkhive.dondatabrain.com/mcp and https://arkhive.dondatabrain.com/sentarion/mcp.

v2 — the paid upgrade for people who run this daily

Everything in the free line stays free. v2 is what you lose if you stop paying: real capability, not a lock.

You need to…Free 0.xv2
Start a session already knowing what happenedpage through recallcontext_pack: one call, fits your token budget
Find the record about the nginx deploy from last monthlast N rows onlyfull-text search, actor/kind/tag/time filters, paging
Keep client A's memory away from client Bone global chainspaces per project/tenant; hosted keys pinned to a space
Prove nothing was altered, fastre-hash everythingincremental + Ed25519-signed verify that names the bad block
Stop the agent before it emails a customer listonly flags you remembered to declareinferred risk flags (PII, credentials, money, irreversible, outbound, bulk) + stored policies + REVIEW verdict
Run 40 sub-tasks without the tool call dyingdies at ~120 sprogress notifications + background jobs
Cap spend and never pay twicebudget_usd, token caps, result cache, retries
Feed task B the output of task Aordering only{{id}} data flow between tasks
Prove what the fleet actually didgoal string loggedsigned manifest: prompt/result hashes, usage, cost
Review a diff adversarially before mergingmulti-agent review: finders per dimension, skeptics refute
Let the fleet edit code safelyworktree create/removesandbox: create · diff · apply_patch · commit

Get a free 14-day v2 trial key

No card. We email nothing automatically; the key appears right here. We do keep your address so a human can follow up.

Pricing

Pro — includes MCP v2

$177/mo

The full InboxAxe governed AI marketing platform plus v2 license keys for your team (3 seats). Nothing sends without your yes.

$27 for your first 15 days, then $177/mo from day 15, automatically. Cancel anytime before, one click.

Start — $27 for 15 days

Agency

$777/mo

Multi-client, multi-seat. v2 team keys (10 seats), hosted tenant spaces per client.

Subscribe

Enterprise

$2,500+

Hand-delivered install and pilot on your own server, unlimited v2, your own hosted endpoint.

Contact us

Already a Pro or Agency customer? Sign in → Settings → MCP to mint your v2 key.