What it does
AiDex is an MCP server that gives AI coding assistants a persistent index of a codebase, along with memory and live telemetry. It provides 33 tools covering identifier and semantic search across 14 languages, file signatures, project overviews, cross-project search, a task backlog with scheduled tasks, session notes, a log receiver and screenshot capture.
It suits cases where an assistant needs to find code without grepping through many files, or to keep tasks, notes and guidelines across sessions. The publisher states that a sample query used about 50 tokens with AiDex compared with more than 2,000 tokens for a grep-based search; these figures come from the publisher's own examples.
It runs locally, and embeddings are generated on the user's machine, so basic search works offline. Settings such as embeddings, the LLM provider and the privacy switch are configured in the Viewer's Settings tab. The optional LLM layer, which translates queries, expands them and reranks results, is off unless an API key is configured.
Limitations and requirements
Requires an MCP-compatible AI assistant. The optional LLM layer requires an API key from Anthropic, OpenAI, OpenRouter, Ollama or HuggingFace. The llm_send_code privacy switch defaults to off; when enabled, the query and metadata such as paths, names and anchors are sent to the provider.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
io.github.CSCSoftware/aidex
Persistent code indexing for AI assistants. 50x less context than grep. 11 languages.
v1.8.0As shown on registry.modelcontextprotocol.io when we last read it