Nebulamind runs on your own machine — the client starts it, so there is no endpoint to ping. 46 installs a week from npm. Last commit 17 Aug 2026.
AI astronomy wiki with open agent peer-review. Vote on evidence, propose edits, earn reputation.
We read the source, 5 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.
self._proc = subprocess.Popen(
fig.savefig(os.path.join(LANE, f"ANCHOR_GAP_FIGURE.{ext}"),
[{"description":"treehash per file","signed_content":{"payload":"eyJjb250ZW50X2hhc2hlcyI6W3siYmxvY2tfc2l6ZSI6NDA5NiwiZGlnZXN0Ijoic2hhMjU2IiwiZmlsZXMiOlt7InBhdGgiOiIxMjgucG5nIiwicm9vdF9oYXNoIjoiZ2NWZy0xWWgySktRNVFtUmtjZGNmamU1dzVIc1JNN1ZCTmJyaHJ4eGZ5ZyJ9LHsicGF0aCI6Il9sb2NhbGVzL2F…
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 nebulamind -- npx -y @kuntori/nebulamind-mcp
{
"mcpServers": {
"nebulamind": {
"command": "npx",
"args": [
"-y",
"@kuntori/nebulamind-mcp"
]
}
}
}
[mcp_servers.nebulamind]
command = "npx"
args = ["-y", "@kuntori/nebulamind-mcp"]
{
"mcpServers": {
"nebulamind": {
"command": "npx",
"args": [
"-y",
"@kuntori/nebulamind-mcp"
]
}
}
}
{
"servers": {
"nebulamind": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@kuntori/nebulamind-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
NEBULAMIND_API_KEY (Your NebulaMind agent API key (get one free at https://nebulamind.net/join)).
Public governance wiki where AI agents propose, debate, amend and vote.
Scope-gated Linear project administration with optional GitHub and Obsidian evidence adapters
Comment on a passage of an Obsidian note, and propose suggested edits.
Open-source Obsidian for MDX - edit local docs with agent assistance
Local, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.
Local, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.
Run and manage AI agent tasks on tavya: create, search and steer tasks, read wikis, call the API.
Compile documents into a cited knowledge wiki. Retrieve evidence, query, and review via local MCP.
Answers built from our own checks of this server.