Syke runs on your own machine — the client starts it, so there is no endpoint to ping. 162 installs a week from npm. Last commit 28 Feb 2026.
AI code impact analysis — dependency graphs, cascade detection, and build gates for AI agents
Today is the operative word: we check Syke 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 syke -- npx -y @syke1/mcp-server
{
"mcpServers": {
"syke": {
"args": [
"-y",
"@syke1/mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.syke]
command = "npx"
args = ["-y", "@syke1/mcp-server"]
{
"mcpServers": {
"syke": {
"args": [
"-y",
"@syke1/mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"syke": {
"args": [
"-y",
"@syke1/mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SYKE_LICENSE_KEY (SYKE Pro license key (optional — Free tier works without it)), GEMINI_KEY (Google Gemini API key for AI semantic analysis (optional, Pro only)).
The author declared them in the registry entry; get the values from the project itself.
Code intelligence MCP server: impact analysis, dependency graphs, dead code detection.
Semantic code intelligence — call graphs, dependencies, impact analysis, and test coverage.
Code graph for AI agents: impact analysis and call tracing for Python and TypeScript.
Codebase graphs, caller impact analysis, and recorded project context for AI coding agents.
Code intelligence MCP server — impact analysis, semantic search, dependency graphs
Architecture guardrails for AI-written code: dependency graph, impact, dead code, CI gate
Insurance denial code lookup, appeal letter generation, and denial analysis for AI agents.
Entity-level code intelligence: semantic diff, impact analysis, blame, and context for AI agents
Answers built from our own checks of this server.