Palanit Core runs on your own machine — the client starts it, so there is no endpoint to ping. 729 installs a week from pypi. Last commit 21 Oct 2026.
Scan MCP servers and agent tool manifests for poisoning, exfiltration, secrets and supply-chain risk
Today is the operative word: we check Palanit Core every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 palanit-core -- uvx palanit-core
{
"mcpServers": {
"palanit-core": {
"command": "uvx",
"args": [
"palanit-core"
]
}
}
}
[mcp_servers.palanit-core]
command = "uvx"
args = ["palanit-core"]
{
"mcpServers": {
"palanit-core": {
"command": "uvx",
"args": [
"palanit-core"
]
}
}
}
{
"servers": {
"palanit-core": {
"type": "stdio",
"command": "uvx",
"args": [
"palanit-core"
]
}
}
}
Scans MCP servers for tool poisoning, prompt injection and supply chain risks.
Audit MCP servers for tool poisoning, rug pulls and supply-chain risk (OWASP MCP Top 10).
Security scanner for MCP servers - detects tool poisoning and injection
Multi-layer security scanner for MCP servers and agent skills (injection, exfiltration)
package-lock.json for MCP trust: catch MCP rug-pulls, tool poisoning, and leaked secrets.
Security tools for AI agents: scan MCP servers, validate HDP delegation chains, audit releases.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Scan MCP tool definitions for poisoning, look up server history, count tool-list tokens. Free.
Answers built from our own checks of this server.