Search / co.promptguard/security
PromptGuard
L0· runs locallyScan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
v1.1.2 · active · repository · descriptor JSON · versions
Search / co.promptguard/security
L0· runs locallyScan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client
v1.1.2 · active · repository · descriptor JSON · versions
{
"mcpServers": {
"security": {
"command": "npx",
"args": [
"-y",
"@promptguard/[email protected]"
],
"env": {
"PROMPTGUARD_API_KEY": "${PROMPTGUARD_API_KEY}"
}
}
}
}claude mcp add security -e "PROMPTGUARD_API_KEY=${PROMPTGUARD_API_KEY}" -- npx -y @promptguard/[email protected][mcp_servers.security]
command = "npx"
args = ["-y", "@promptguard/[email protected]"]
env = { "PROMPTGUARD_API_KEY" = "${PROMPTGUARD_API_KEY}" }
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"security": {
"type": "local",
"command": [
"npx",
"-y",
"@promptguard/[email protected]"
],
"enabled": true,
"environment": {
"PROMPTGUARD_API_KEY": "{env:PROMPTGUARD_API_KEY}"
}
}
}
}{
"mcpServers": {
"security": {
"command": "npx",
"args": [
"-y",
"@promptguard/[email protected]"
],
"env": {
"PROMPTGUARD_API_KEY": "${PROMPTGUARD_API_KEY}"
}
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=security&config=eyJjb21tYW5kIjoibnB4IiwiYXJncyI6WyIteSIsIkBwcm9tcHRndWFyZC9tY3Atc2VydmVyQDEuMS4yIl0sImVudiI6eyJQUk9NUFRHVUFSRF9BUElfS0VZIjoiJHtQUk9NUFRHVUFSRF9BUElfS0VZfSJ9fQ%3D%3D"
}{
"servers": {
"security": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@promptguard/[email protected]"
],
"env": {
"PROMPTGUARD_API_KEY": "${PROMPTGUARD_API_KEY}"
}
}
}
}{
"mcpServers": {
"security": {
"command": "npx",
"args": [
"-y",
"@promptguard/[email protected]"
],
"env": {
"PROMPTGUARD_API_KEY": "${PROMPTGUARD_API_KEY}"
}
}
}
}extensions:
"security":
enabled: true
name: "security"
type: stdio
cmd: "npx"
args:
- "-y"
- "@promptguard/[email protected]"
envs:
"PROMPTGUARD_API_KEY": "${PROMPTGUARD_API_KEY}"
timeout: 300
Placeholders to fill from your own secret store: ${PROMPTGUARD_API_KEY}. The registry never accepts secret values.
This is a local package: the command runs on your machine.
Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.
protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)auth.prm, auth.as_metadata, auth.cimdno remote uses OAuthauth.secret_in_urlno templated URLtools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)stability.changes, stability.rug_pulltool list unknowndeps.known_vulnsno known advisory in 1 resolved packagesdeps.mcp_sdk_versionthe official MCP SDK is not in the dependency graphdeps.resolvable@promptguard/[email protected] resolved: 1 packagesNo tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
+repository +dns-namespace ~liveness-unmeasured ~updated-57d-ago -unpinned-packages(1)
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
@promptguard/[email protected] npm0 dependencies, resolved · advisories checked 2026-10-19
No known advisory affects this dependency graph.
Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.
| package | registry | version | runtime | secrets |
|---|---|---|---|---|
@promptguard/mcp-server | npm | 1.1.2 | – | PROMPTGUARD_API_KEY |
docker.io/abhijoysarkar/promptguard-mcp-server:1.1.2 | oci | unpinned | – | PROMPTGUARD_API_KEY |
No tools observed. Local packages are never executed by the registry.
Schemas: list_tools.
{
"name": "co.promptguard/security",
"title": "PromptGuard",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"version": "1.1.2",
"packages": [
{
"version": "1.1.2",
"transport": {
"type": "stdio"
},
"identifier": "@promptguard/mcp-server",
"registryType": "npm",
"environmentVariables": [
{
"name": "PROMPTGUARD_API_KEY",
"format": "string",
"isSecret": true,
"description": "PromptGuard API key (starts with pg_live_)"
}
]
},
{
"transport": {
"type": "stdio"
},
"identifier": "docker.io/abhijoysarkar/promptguard-mcp-server:1.1.2",
"registryType": "oci",
"environmentVariables": [
{
"name": "PROMPTGUARD_API_KEY",
"format": "string",
"isSecret": true,
"description": "PromptGuard API key (starts with pg_live_)"
}
]
}
],
"repository": {
"url": "https://github.com/acebot712/promptguard",
"source": "github"
},
"description": "Scan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client"
}