Connect 8 clients · secrets stay placeholders JSON (mcpServers) Claude Code Codex OpenCode Cursor VS Code Gemini CLI Goose
{
"mcpServers": {
"agentlock": {
"type": "http",
"url": "https://app.agentlock.net/api/mcp",
"headers": {
"Authorization": "Bearer ${AGENTLOCK_TOKEN}"
}
}
}
}claude mcp add --transport http agentlock https://app.agentlock.net/api/mcp --header "Authorization: Bearer ${AGENTLOCK_TOKEN}"[mcp_servers.agentlock]
url = "https://app.agentlock.net/api/mcp"
bearer_token_env_var = "AGENTLOCK_TOKEN"
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"agentlock": {
"type": "remote",
"url": "https://app.agentlock.net/api/mcp",
"enabled": true,
"headers": {
"Authorization": "Bearer {env:AGENTLOCK_TOKEN}"
}
}
}
}{
"mcpServers": {
"agentlock": {
"type": "http",
"url": "https://app.agentlock.net/api/mcp",
"headers": {
"Authorization": "Bearer ${AGENTLOCK_TOKEN}"
}
}
},
"deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=agentlock&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBwLmFnZW50bG9jay5uZXQvYXBpL21jcCIsImhlYWRlcnMiOnsiQXV0aG9yaXphdGlvbiI6IkJlYXJlciAke0FHRU5UTE9DS19UT0tFTn0ifX0%3D"
}{
"servers": {
"agentlock": {
"type": "http",
"url": "https://app.agentlock.net/api/mcp",
"headers": {
"Authorization": "Bearer ${AGENTLOCK_TOKEN}"
}
}
}
}{
"mcpServers": {
"agentlock": {
"httpUrl": "https://app.agentlock.net/api/mcp",
"headers": {
"Authorization": "Bearer ${AGENTLOCK_TOKEN}"
}
}
}
}extensions:
"agentlock":
enabled: true
name: "agentlock"
type: streamable_http
uri: "https://app.agentlock.net/api/mcp"
headers:
"Authorization": "Bearer ${AGENTLOCK_TOKEN}"
timeout: 300
Placeholders to fill from your own secret store: ${AGENTLOCK_TOKEN}. The registry never accepts secret values.
Quality – / 100 not scored Not scored: fewer than three checks apply, usually because no remote answered a credential-free probe or the server is a local package.
protocol n/a · weight 25
n/a protocol.modern, protocol.stateless, protocol.transport, protocol.list_ttlno remote answered a protocol handshake (not probed yet, unreachable, or local-only)
authorization n/a · weight 15
n/a auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a auth.secret_in_urlno templated URL
tool hygiene n/a · weight 30
n/a tools.descriptions, tools.description_length, tools.schemas, tools.annotations, tools.directory_hints, tools.token_cost, tools.api_dumptool list unknown (behind auth, not probed, or empty)
dependencies n/a · weight 15
Tool list unknown · checked 2026-10-19 10:20 UTC
Tool changes No tool definition changes recorded. A server's first observation is its baseline; later probes record what changes.
Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.
Trust 87 / 100 +repository +namespace-matches-repo +reachable +uptime-100% ~updated-143d-ago
Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.
Tools (0) No tools observed. Tools appear once a credential-free probe can list them.
Schemas: list_tools .
Official server.json {
"name": "io.github.Olum289/agentlock",
"$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
"remotes": [
{
"url": "https://app.agentlock.net/api/mcp",
"type": "streamable-http",
"headers": [
{
"name": "Authorization",
"isSecret": true,
"isRequired": true,
"description": "AgentLock API token as a Bearer credential (format: 'Bearer <token>'); create one in the dashboard."
}
]
}
],
"version": "0.2.0",
"repository": {
"url": "https://github.com/Olum289/agentlock",
"source": "github"
},
"description": "Security gateway for AI agents: policy, approval, and audited execution, no secrets shared."
}