OpenGrok MCP Server runs on your own machine — the client starts it, so there is no endpoint to ping. 362 installs a week from npm. Last commit 16 Sep 2026.
MCP server bridging OpenGrok search engine with AI for instant context across massive codebases.
We read the source, 22 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.
const filePath = path.join(memoryBank.bankDir, filename);
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 opengrok-mcp-server -- npx -y opengrok-mcp-server
{
"mcpServers": {
"opengrok-mcp-server": {
"args": [
"-y",
"opengrok-mcp-server"
],
"command": "npx"
}
}
}
[mcp_servers.opengrok-mcp-server]
command = "npx"
args = ["-y", "opengrok-mcp-server"]
{
"mcpServers": {
"opengrok-mcp-server": {
"args": [
"-y",
"opengrok-mcp-server"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"opengrok-mcp-server": {
"args": [
"-y",
"opengrok-mcp-server"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
OPENGROK_BASE_URL (OpenGrok server base URL (e.g. https://opengrok.example.com/source/)), OPENGROK_USERNAME (OpenGrok authentication username. Leave unset for anonymous access.), OPENGROK_PASSWORD (OpenGrok authentication password. Prefer storing via OS keychain using 'npx opengrok-mcp-server setup'.), OPENGROK_VERIFY_SSL (Verify TLS certificates. Set to false for self-signed or internal CA certs.), OPENGROK_CODE_MODE (Enable Code Mode: 2-tool sandbox interface with env.opengrok.* JavaScript API. Reduces AI token usage by ~90%.), OPENGROK_ENABLE_MEMORY_TOOLS (Register the 3 memory tools in Code Mode (memory status, read, update). Off = api + execute only.), OPENGROK_DEFAULT_PROJECT (Default project to scope all searches. Can be overridden per call.), OPENGROK_CONTEXT_BUDGET (Response size tier controlling token usage.), OPENGROK_API_VERSION (OpenGrok REST API version. Use v2 for call graph features (requires OpenGrok 1.12+).), HTTP_PROXY (HTTP/HTTPS proxy URL for all OpenGrok API requests (e.g. http://proxy.company.com:8080). Also set as HTTPS_PROXY.), OPENGROK_RESPONSE_FORMAT_OVERRIDE (Force a specific response format for all tools. Leave unset for per-tool auto-selection (recommended).), OPENGROK_MEMORY_BANK_DIR (Directory where the AI stores investigation notes (active-task.md, investigation-log.md). Defaults to ~/.config/opengrok-mcp/memory-bank/ or workspace-relative when set by the VS Code extension.), OPENGROK_LOCAL_COMPILE_DB_PATHS (Comma-separated paths to compile_commands.json for C/C++ compiler flag and include-path extraction. Leave unset for automatic workspace discovery.), OPENGROK_ENABLE_ELICITATION (Interactive AI Prompts — the AI pauses to ask questions during investigations (project selection, file disambiguation). Requires Claude Code v2.1.76+ or a client that supports MCP Elicitation.), OPENGROK_ENABLE_SAMPLING (AI Sampling — allow the server to request LLM completions for error explanations and summaries. Off by default to avoid consuming premium requests (e.g. GitHub Copilot).), OPENGROK_SAMPLING_MODEL (Model preference for MCP Sampling (used for error explanation and query reformulation).), OPENGROK_ENABLE_FILES_API (Files API Cache — avoids re-uploading unchanged investigation notes. Requires Files API support in the MCP client.), OPENGROK_ENABLE_OBSERVATION_MASKER (Observation Masker — prepend compact history summaries to opengrok_execute results after N turns. Disabled by default; has no benefit for clients that retain full context (Claude Code, Cursor).), OPENGROK_OBSERVATION_MASKER_TURNS (Number of most-recent opengrok_execute results to keep as full text before masking older ones. Default: 10.), OPENGROK_SAMPLING_MAX_TOKENS (Maximum tokens for AI sampling responses (error explanation, query reformulation). Range: 64–4096.), OPENGROK_AUDIT_LOG_FILE (Path to write structured audit events (CSV/JSON). Appends tool invocations, elicitation events, and errors. Leave unset to disable.), OPENGROK_RATELIMIT_RPM (Maximum requests per minute to the OpenGrok server. Default: 60.), OPENGROK_PER_TOOL_RATELIMIT (Per-tool rate limits in requests per minute, as comma-separated tool:rpm pairs (e.g. opengrok_execute:15,opengrok_search_code:30). Overrides OPENGROK_RATELIMIT_RPM for specific tools.), OPENGROK_TIMEOUT (HTTP request timeout in seconds for OpenGrok API calls. Increase for slow servers. Default: 30.), OPENGROK_DEFAULT_MAX_RESULTS (Default maximum number of results returned per search query. Default: 25.), OPENGROK_PASSWORD_FILE (Path to a file containing the OpenGrok password (file-mounted secret for containers). Takes precedence over the OS keychain when OPENGROK_PASSWORD is unset.), OPENGROK_MAX_RESPONSE_BYTES (Hard cap on response payload size in bytes. Overrides the context-budget default. Non-positive values are ignored.), OPENGROK_SEARCH_AND_READ_CAP (Cap for the search_and_read compound tool in bytes. Overrides the context-budget default (2–8 KB depending on tier). Non-positive values are ignored.), OPENGROK_STRICT_SSRF (When true, reject OPENGROK_BASE_URL values pointing at private/loopback IPs at startup. Default: false (warn only; per-request guards still apply).), OPENGROK_JWT_ISSUER (Expected JWT issuer (iss claim) for HTTP transport OAuth. When set, JWTs from other issuers are rejected.), OPENGROK_GRAMMAR_DIR (Directory containing tree-sitter WASM grammars. Overrides the bundled grammar lookup.).
The author declared them in the registry entry; get the values from the project itself.
MCP server for SearXNG aggregator — web search across multiple engines via Model Context Protocol
Model Context Protocol server for Google Gemini AI with chat, research, and grounding
Open-source MCP server for AI agents: web search, content extraction, and library docs.
Official SerpApi MCP server for Google, Bing, and other search engines.
MCP server for Styx — intelligent AI routing across OpenAI, Anthropic, Google, and Mistral.
Public MCP server for the LLM Search Engine
FastMCP server for Tavily search API with web search and content extraction
AI assistant with RAG, web search, filesystem and memory. MCP sub-agent for Claude Code.
Answers built from our own checks of this server.