AXIOM runs on your own machine — the client starts it, so there is no endpoint to ping. 570 installs a week from npm. Last commit 21 Sep 2026.
Transactional write gate for coding agents: plan, canonical manifest, checks, two-phase apply.
We read the source, 12 h ago · rules 3dff92dd89df
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.
const child = spawn(
return new Uint8Array(await readFile(path.join(contentDir, rel)));
"expr": "manifest.name == 'xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx…
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
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.
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 axiom -- npx -y @codai/axiom-mcp
{
"mcpServers": {
"axiom": {
"args": [
"-y",
"@codai/axiom-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.axiom]
command = "npx"
args = ["-y", "@codai/axiom-mcp"]
{
"mcpServers": {
"axiom": {
"args": [
"-y",
"@codai/axiom-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"axiom": {
"args": [
"-y",
"@codai/axiom-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
AXIOM_SIGNING_KEY (Optional Ed25519 private key (base64 PKCS#8 or raw seed) used by axiom_sign; never stored under a root.).
The author declared them in the registry entry; get the values from the project itself.
Local-first biological memory for coding agents: recall, consolidation, and pre-action Guard checks.
Local mandate gate and proof trail for AI agents that take consequential actions.
Mechanical write gates, evidence receipts, and adversarial review for AI coding agents.
LSP-backed IDE intelligence plus concurrency-safe, transactional edits for AI coding agents.
Medical-billing tools for AI agents: prior-auth checks, denial decoding, claim triage, appeals.
The API-change deploy gate for AI coding agents. Read-only breaking-change detection.
Preventive human-approval write-gate for AI agents: writes commit only after a human approves.
Merge gates and safety checks for AI coding agents via MCP.
Answers built from our own checks of this server.