epicsagas/alcove
by Various
Alcove is an MCP server that gives AI coding agents on-demand access to your private project docs — BM25 + vector hybrid search for precision retrieval, tree-sitter code indexing s
MCP
epicsagas/alcove
Added 1 June 2026
Overview
Alcove is an MCP server that gives AI coding agents on-demand access to private project documentation. It combines BM25 and vector hybrid search for precise retrieval and uses tree-sitter to index codebase structure. Policy enforcement helps maintain documentation consistency.
Best for
Best for
Teams using MCP-based AI agents who need secure, structured access to private project documentation
Use cases
- Retrieving relevant project docs for AI agents during code generation or review
- Indexing private codebases so agents understand project structure and naming conventions
- Enforcing documentation policies across shared project repositories
How to use
Tools exposed
brewcurlpowershellcargo
Tested with
Claude Code, Codex CLI, Antigravity (Gemini CLI)
Notes
Alcove is an MCP server that gives AI coding agents on-demand access to private project documentation. It combines BM25 and vector hybrid search for precise retrieval and uses tree-sitter to index codebase structure. Policy enforcement helps maintain documentation consistency.
9 stars on GitHub. Last updated 2026-06-01. Licensed Apache-2.0.
Use cases
- Retrieving relevant project docs for AI agents during code generation or review
- Indexing private codebases so agents understand project structure and naming conventions
- Enforcing documentation policies across shared project repositories
Pros
- Hybrid BM25+vector search improves retrieval accuracy over pure keyword or vector methods
- Tree-sitter indexing enables agents to interpret code structure rather than just strings
- Policy enforcement helps keep documentation aligned with project standards
Cons
- Very early-stage project with only 9 stars, indicating limited community and support
- Requires an MCP-compatible AI agent ecosystem to function
- Setup and maintenance may demand familiarity with Rust tooling
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Hybrid BM25+vector search improves retrieval accuracy over pure keyword or vector methods
- Tree-sitter indexing enables agents to interpret code structure rather than just strings
- Policy enforcement helps keep documentation aligned with project standards
Cons
- Very early-stage project with only 9 stars, indicating limited community and support
- Requires an MCP-compatible AI agent ecosystem to function
- Setup and maintenance may demand familiarity with Rust tooling
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.