Singularis runs on your own machine — the client starts it, so there is no endpoint to ping. 581 installs a week from pypi. Last commit 18 Oct 2026.
Unlimited computation for agents. Results depend on your equipment; GPU optional.
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.
proc = subprocess.run(cmd, shell=True, input=json.dumps(job).encode(), capture_output=True)
proc = subprocess.run(cmd, shell=True, input=json.dumps(job).encode(), capture_output=True)
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 singularis -- uvx singularis-mcp
{
"mcpServers": {
"singularis": {
"command": "uvx",
"args": [
"singularis-mcp"
]
}
}
}
[mcp_servers.singularis]
command = "uvx"
args = ["singularis-mcp"]
{
"mcpServers": {
"singularis": {
"command": "uvx",
"args": [
"singularis-mcp"
]
}
}
}
{
"servers": {
"singularis": {
"type": "stdio",
"command": "uvx",
"args": [
"singularis-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
SINGULARIS_API_KEY (API key (optional: the singularis_register_key tool can obtain one)), SINGULARIS_COUNTRY (Operator country, ISO code (used when registering a key)), SINGULARIS_ENGINE_CMD (Command of the Singularis runtime on this machine (jobs run locally)), SINGULARIS_SHELL_SECRET (Shell secret (saved automatically by singularis_register_key)).
Read-only US golf course, scorecard, equipment, deal, and golf-trip data for AI agents.
Open federation for AI agents: identity, mentors, reputation and limited accession.
Deterministic computation tools for AI agents. Zero dependencies, no network, read-only.
Real-time web search for AI agents: ranked results, source URLs, and optional AI answers.
Shared, source-backed memory for AI agents on your own Postgres, with an optional document engine.
Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.
Open Identity Standard for AI Agents — DID, Agent Cards, delegation, reputation, payment & escrow
Citation-ready YouTube transcript research and optional channel intelligence for AI agents.
Answers built from our own checks of this server.