$ loading_
Search code lexically and semantically for faster AI-assisted code discovery.
This MCP tool is described as a local code search utility with no required secrets and no declared remote endpoints. Given its open-source MIT-licensed source, overall risk appears low, but its normal ability to execute locally and access repository data still warrants standard caution.
The materials explicitly state that no keys or environment variables are required, with no indication of token collection, storage, or credential exfiltration, so credential abuse surface appears limited.
No remote endpoints are declared. The description indicates code search via Zoekt and ChromaDB, but the materials do not state that data is sent to external services. Based on the available facts, there is no clear network egress red flag.
The system flags this tool as executes-code, indicating it can run local code or start related search components/processes. This is a normal MCP capability, and no excessive system privilege request beyond the stated function is evident, but it should still be run in a controlled environment.
Its core function is lexical and semantic search over codebases, so it necessarily needs access to local code/project data and may build indexes or embedding stores. This access scope is consistent with the stated purpose, and no obvious overreach is shown in the materials, but it should be limited to the intended repository scope.
Positive signals include an auditable open-source repository and MIT licensing, which materially lower risk. However, it comes from a third-party registry, has 0 stars, and an unknown maintenance status, so supply-chain maturity and ongoing maintenance signals are weak; review the source and dependencies before using it in sensitive environments.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "grepsense" yet — see the docs or source repo.
Search the current repository for all code matching the regex `Auth.*Middleware`, and return file paths, matching snippets, and surrounding context.
A list of regex matches with file locations and nearby context for quick investigation.
Find implementations in the codebase related to "API request wrappers with retry logic," even if function names differ, and rank them by relevance.
Relevant semantically similar code implementations with file paths and ranked relevance scores.
First search for code containing the keyword `timeout`, then find implementations semantically related to "request timeout handling," and summarize the modules I should inspect.
Keyword hits, semantic matches, and a summarized list of modules to inspect first.
Search codebases semantically to find relevant snippets and implementation context fast.
Search files recursively and find matches using natural language and grep options.
Search code quickly and accurately while using far fewer tokens.
Search and navigate multiple code repositories with natural language understanding.
Build semantic indexes for codebases to find relevant code with natural language queries.
Search codebases semantically and find relevant snippets with source locations.