ossfind runs on your own machine — the client starts it, so there is no endpoint to ping. 74 installs a week from npm.
Safety-ranked open-source component discovery for agents across six package ecosystems.
The linked repository no longer exists on GitHub — it was deleted or made private.
We have not read this server's code yet, 54 d ago · rules 3dff92dd89df
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
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 ossfind -- npx -y ossfind
{
"mcpServers": {
"ossfind": {
"command": "npx",
"args": [
"-y",
"ossfind"
]
}
}
}
[mcp_servers.ossfind]
command = "npx"
args = ["-y", "ossfind"]
{
"mcpServers": {
"ossfind": {
"command": "npx",
"args": [
"-y",
"ossfind"
]
}
}
}
{
"servers": {
"ossfind": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"ossfind"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
GITHUB_TOKEN (Optional. Raises the GitHub repository-search rate limit; discovery works without it), LIBRARY_IO_API_KEY (Optional libraries.io key, used as the PyPI discovery fallback when no local index has been built. Without it, and without an index, PyPI search reports itself unavailable rather than returning nothing), OSSFIND_FIXTURES (Set to 1 to run fully offline against frozen supplier responses, for evaluation without network access).
Deterministic UI policy, discovery and audits for coding agents across seven ecosystems.
Product discovery for AI agents: ranked products and bundles from the open merchant web.
A package manager for Agent Skills — discover, vet, and pin them across Claude Code and Codex.
Open-source marketing system, designed for coding agents.
Help AI agents find and evaluate mature packages across 6 ecosystems instead of reinventing them.
Agent tools for discovery, payment safety, data extraction, and DeFi.
Open-source computer use for macOS agents.
Discovery for the agent ecosystem: findable businesses, tools, knowledge, agent spaces, skills.
Answers built from our own checks of this server.