Abe runs on your own machine — the client starts it, so there is no endpoint to ping. 1 008 installs a week from pypi. Last commit 13 Oct 2026.
Free, local check before an AI agent acts: your rules return ACT, BLOCK or ESCALATE.
What the code does
We read the source, 2 d ago · rules ccca72095570
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
return yaml.load(text, Loader=_Loader) # noqa: S506 - custom SafeLoader subclass
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
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 abe -- uvx abe-ai{
"mcpServers": {
"abe": {
"args": [
"abe-ai"
],
"command": "uvx"
}
}
}[mcp_servers.abe]
command = "uvx"
args = ["abe-ai"]{
"mcpServers": {
"abe": {
"args": [
"abe-ai"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"abe": {
"args": [
"abe-ai"
],
"command": "uvx"
}
}
}This one needs environment variables set before it will start:
ABE_POLICY (Absolute path to your abe-policy.yaml (create one with: uvx abe-ai init)), ABE_RESOLVER (Set to flow to send escalations to Flow (needs FLOW_API_KEY). Default: none, nothing leaves your machine.), FLOW_API_KEY (Flow Resolver key (fjp_live_...), only with ABE_RESOLVER=flow. https://fjp.flowinfo.co/credits).
The author declared them in the registry entry; get the values from the project itself.
Alternatives to Abe
same job, measured the same wayCheck an email before your AI agent sends it: allow, review or block with reasons.
Check whether a real-world fact can be verified before an agent acts on it. Free, no auth.
AI trading journal: your agent logs trades from chart screenshots and checks your own rules.
Check an agent action against its operator's mandate before acting: permit, deny or escalate.
Check text for leaked credentials before an agent writes or commits it. Runs locally.
Check SQL against your Vericto rules before it runs: blocks destructive or risky statements.
Tanilo checks the premise before an AI agent acts.
Check a lending rate before your agent borrows. Bitcoin-backed dollar rates from contracts. No key.
Abe — questions
Answers built from our own checks of this server.