okl — Observed Knowledge Ledger runs on your own machine — the client starts it, so there is no endpoint to ping. 2 634 installs a week from pypi. Last commit 8 Nov 2026.
Keeps your agent true to your rules. Keeps them true to the code. Keeps learning as you build.
What the code does
We read the source, 8 h 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.
out = subprocess.run(["git", "-C", repo_dir, *args],
server_cls = getattr(__import__(module, fromlist=[name]), name)
r = subprocess.run(args.run, shell=True, capture_output=True, text=True,
…ation tests pass in CI on Linux but fail instantly on every Mac on the team", "docker socket path on macOS, the default /var/run/docker.sock is missing", "container runtime not detected by the test library on an Apple silicon laptop", "Docker daemon unreachable from the test runn…
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 okl -- uvx observed-knowledge-ledger{
"mcpServers": {
"okl": {
"command": "uvx",
"args": [
"observed-knowledge-ledger"
]
}
}
}[mcp_servers.okl]
command = "uvx"
args = ["observed-knowledge-ledger"]{
"mcpServers": {
"okl": {
"command": "uvx",
"args": [
"observed-knowledge-ledger"
]
}
}
}{
"servers": {
"okl": {
"type": "stdio",
"command": "uvx",
"args": [
"observed-knowledge-ledger"
]
}
}
}Alternatives to okl — Observed Knowledge Ledger
same job, measured the same wayCode knowledge graph over MCP: token-budgeted context for AI coding agents.
Read-only MCP server: your agent sees all your sibling repos but structurally cannot touch them
The official Letmediff MCP server helping you review your code with an agent first workflow
Give your coding agent the right code: graph + hybrid search, packed into a token budget. Local.
Run the Grok Build CLI as MCP tools: agent runs with live progress, code review, web research.
Shared local memory for AI coding tools that stays true to your code.
A live graph of your running system, code fused with OTel runtime, that your agent queries over MCP.
Persistent code knowledge graph + 9 composite MCP tools for AI coding agents.
okl — Observed Knowledge Ledger — questions
Answers built from our own checks of this server.