An MCP server that gives AI coding agents on-demand access to private project docs with hybrid search and code indexing.
alcove is worth checking the docs before setup with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
gh repo view epicsagas/alcove --webOpen the official README and confirm the supported install method.
Add the server entry to your MCP client config.
Restart your agent and verify that the server tools appear.
Alcove is a tool that helps AI coding assistants understand your private project documentation. It uses smart search to find the right docs without loading everything into the AI's memory, so your agent stays fast and focused. It also indexes your code structure and enforces documentation rules.
Alcove is an HTTP API server designed as an MCP (Model Context Protocol) server that provides AI coding agents with on-demand access to your private project documentation. It features BM25 + vector hybrid search for precision retrieval, tree-sitter code indexing so agents understand your codebase structure, and policy enforcement for documentation consistency. The tool solves the problem of context bloat by not loading all docs into every session, instead retrieving only relevant information when needed. It supports multiple projects, global search, and validation/generation of documentation. Alcove is privacy-focused: your docs stay on your infrastructure and are never leaked to public repositories. It is built in Rust and distributed as a crate, with a CLI and API interface.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 51 days ago.
10 GitHub stars indicate community interest.
1 open issues signal maintenance load.
Apache-2.0 license detected.
Give Claude Code or Codex instant access to your private architecture docs without context bloat.
Enable AI agents to search across multiple project documentation sets with hybrid search.
Enforce documentation policies and validate consistency across your project docs.
Index your codebase with tree-sitter so agents understand code structure and symbols.
Run a local MCP server for privacy-sensitive projects where docs cannot leave your network.
Since Alcove runs locally, ensure your server is not exposed to untrusted networks to prevent unauthorized access to private docs.
The tool indexes your codebase; if you have sensitive code, ensure the index storage is secured.
10
Stars
3
Forks
1
Issues
Apache-2.0
License
Optimize markdown documentation for LLMs and RAG systems, reducing token consumption by 67-95%.
Codebase intelligence layer for AI coding agents: code health, git analytics, dead code detection, and architectural decisions via MCP.
Turn OpenAPI, MCP, Doxygen, godoc, rustdoc, and Markdown into static documentation sites you own.
An MCP server that gives AI coding agents on-demand access to private project docs with hybrid search and code indexing.
Developers using AI coding agents like Claude Code or Codex who need private doc access., Engineering teams that maintain internal documentation and want AI agents to use it., Privacy-conscious developers who cannot upload proprietary docs to public AI services.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Since Alcove runs locally, ensure your server is not exposed to untrusted networks to prevent unauthorized access to private docs. The tool indexes your codebase; if you have sensitive code, ensure the index storage is secured.
Similar or complementary options to evaluate include llm-docs-builder, repowise, sourcey.
Jun 7, 2026
2 security/trust notes recorded.
Setup difficulty is 3/5.