Sensegrep runs on your own machine — the client starts it, so there is no endpoint to ping. 176 installs a week from npm. Last commit 16 Aug 2026.
Semantic + structural code search MCP server for AI-native development.
We read the source, 19 h 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.
execSync(`"${tsc}" -p "${packagePath(name, 'tsconfig.json')}"`, {
return path.join(rootDir, 'packages', name, ...parts);
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 sensegrep -- npx -y @sensegrep/mcp
{
"mcpServers": {
"sensegrep": {
"args": [
"-y",
"@sensegrep/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.sensegrep]
command = "npx"
args = ["-y", "@sensegrep/mcp"]
{
"mcpServers": {
"sensegrep": {
"args": [
"-y",
"@sensegrep/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"sensegrep": {
"args": [
"-y",
"@sensegrep/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SENSEGREP_ROOT (Root directory to index and search. Defaults to current working directory.), SENSEGREP_PROVIDER (Embeddings provider: gemini, openai, or bedrock.), GEMINI_API_KEY (Required only when SENSEGREP_PROVIDER=gemini.).
The author declared them in the registry entry; get the values from the project itself.
AI Code Firewall — MCP Server for hallucination prevention in AI development
MCP server for code search (ripgrep + fd) with structured, token-efficient output
Semantic code graph MCP server for coding agents
Zero-LLM structural code retrieval for AI coding agents, served over MCP.
MCP server for enterprise local codebase indexing, semantic search, and code dependency graphs.
ContextStream MCP server for code context, memory, search, and AI tools.
Advanced codebase indexing and semantic search MCP server
Semantic code search and analysis from CodeAlive for AI assistants and agents.
Answers built from our own checks of this server.