Vayl runs on your own machine — the client starts it, so there is no endpoint to ping. 1 525 installs a week from pypi. Last commit 22 Oct 2026.
Reconciling memory for AI agents: a changed fact retires the old value, with history and approval.
We read the source, 2 d ago · rules 995398eba69f
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.
code = subprocess.call([sys.executable, os.path.abspath(__file__), "--once"])
outputs = {SPEC_OUT: render(spec), **{os.path.join(PAGES_DIR, k): v for k, v in pages.items()}}
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 vayl -- uvx vayl-mcp
{
"mcpServers": {
"vayl": {
"command": "uvx",
"args": [
"vayl-mcp"
]
}
}
}
[mcp_servers.vayl]
command = "uvx"
args = ["vayl-mcp"]
{
"mcpServers": {
"vayl": {
"command": "uvx",
"args": [
"vayl-mcp"
]
}
}
}
{
"servers": {
"vayl": {
"type": "stdio",
"command": "uvx",
"args": [
"vayl-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
OPENAI_API_KEY (OpenAI key for extraction and embeddings. Leave unset to use a local Ollama model), VAYL_DB (Absolute path of the SQLite memory database).
Memory for AI agents: facts a person approved, each with a link, and answers that cite them.
Personal memory for AI agents from a vault on your Mac, with per-agent scopes and approvals
Certified SEC EDGAR fact memory for AI agents with zero hallucination and filing provenance.
Living technical memory for AI agents: recall approved project context, record what was learned.
Bitemporal memory for AI agents with point-in-time recall and tamper-evident audit history.
Sandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history
Project memory and a control plane for AI coding agents.
Project management for coding agents: record the approved plan, work the tasks, ask, hand off.
Answers built from our own checks of this server.