Keel runs on your own machine — the client starts it, so there is no endpoint to ping. 2 102 installs a week from pypi. Last commit 30 Oct 2026.
Per-tenant bitemporal context graph built from domain events, shared by agents via five tools.
We read the source, 1 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.
этот файл ставится пользователю, но в репозитории его нет
document.querySelectorAll("[data-i18n]").forEach(n => { if (d[n.dataset.i18n] != null) n.innerHTML = d[n.dataset.i18n]; });
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 keel -- uvx keel-context
{
"mcpServers": {
"keel": {
"command": "uvx",
"args": [
"keel-context"
]
}
}
}
[mcp_servers.keel]
command = "uvx"
args = ["keel-context"]
{
"mcpServers": {
"keel": {
"command": "uvx",
"args": [
"keel-context"
]
}
}
}
{
"servers": {
"keel": {
"type": "stdio",
"command": "uvx",
"args": [
"keel-context"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
KEEL_DB (A SQLite file or a mysql:// URL; in memory when unset), KEEL_AGENT (The agent id, when the cartridge declares agents).
Temporal engineering context for agents via MCP.
Shared knowledge graph, skills, and tool discovery for AI agents through the Model Context Protocol.
Graph-native memory for AI agents: a knowledge graph built from conversation, via MCP.
Append-only event log for cross-agent context/memory sharing via 3 MCP tools.
Persistent context for AI agents built fromlearned vectors with certainty scores.
Encrypted mail, shared memory, and persistent context for AI agents.
Local personal memory for agents as MCP tools — remember, recall, search, context, graph traversal.
Shared product-knowledge graph for AI agent fleets — vault tools + agent self-signup over MCP.
Answers built from our own checks of this server.