Andrea9293 MCP vs MCP Local Rag
A side-by-side look at the Andrea9293 MCP and MCP Local Rag MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Andrea9293 MCP for knowledge & memory work as a local process; choose MCP Local Rag for knowledge & memory as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Andrea9293 MCP when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
add_document, delete_document, search_documents.
Choose MCP Local Rag when
- You need dedicated capabilities in the Knowledge & Memory domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You have the keys it needs:
BASE_DIR, BASE_DIRS, IGNORE_PATHS, DB_PATH, CACHE_DIR, HF_ENDPOINT. - You want tools like
sync_start, sync_status, ingest_file.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Knowledge & Memory | Knowledge & Memory |
| Quality signal | 67/100 · Great | 69/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | No auth required |
| Pricing | Free | Free |
| Required env vars | None listed | BASE_DIRBASE_DIRSIGNORE_PATHSDB_PATHCACHE_DIRHF_ENDPOINT |
| Verified owner | Community listing | Community listing |
| GitHub stars | 344 | 416 |
| Directory activity | 4 views 0 installs 0 upvotes | 9 views 0 installs 0 upvotes |
| Tools | 11 | 9 |
| Full listing | View Andrea9293 MCP | View MCP Local Rag |
Tools & capabilities
Andrea9293 MCP tools 11
add_documentAdd a new document to the knowledge basedelete_documentDelete a document from the collectionsearch_documentsSearch for chunks within a specific document using semantic similarity. Always tell the user if result is truncated because of length. for example if you recive a message like this in the response: 'Tool response was too long and was truncated'get_documentUse this tool only when user explicitly requests it. Retrieve a specific document by ID. Always tell the user if result is truncated because of length. for example if you recive a message like this in the response: 'Tool response was too long and was truncated'list_documentsList all documents in the knowledge basesearch_all_documentsSearch for relevant chunks across ALL documents in the knowledge base using semantic similarity (hybrid: full-text + vector). Useful for cross-document search when you don't know which document contains the answer.get_context_windowReturns a window of parent content sections around a central parent_index. Use parent_index values from search results. Always tell the user if result is truncated because of length.get_ui_urlGet the URL of the web UI. use this tool when user ask you to access the web interface, when the user ask you to upload a file or when the user ask you the uploads folder path. All these function are available in the web UI.get_uploads_pathGet the absolute path to the uploads folder where you can manually place .txt and .md filesprocess_uploadsProcess all .txt and .md files in the uploads folder and create embeddings for themlist_uploads_filesList all files in the uploads folder with their details
MCP Local Rag tools 9
sync_startReconcile the index with all configured roots or one pathsync_statusPoll a running sync jobingest_fileIngest or replace one fileingest_dataIngest text, Markdown, or HTML already held by the clientquery_documentsSearch with semantic matching and keyword boostread_chunk_neighborsRead surrounding chunks from a search resultlist_filesShow supported files and their ingestion statedelete_fileDelete an indexed file or an `ingest_data` itemstatusShow index and search status
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
Andrea9293 MCP
{
"mcpServers": {
"mcp-documentation-server": {
"command": "npx",
"args": [
"-y",
"@andrea9293/mcp-documentation-server"
]
}
}
}
MCP Local Rag
{
"mcpServers": {
"shinpr-mcp-local-rag": {
"command": "npx",
"args": [
"-y",
"mcp-local-rag"
],
"env": {
"BASE_DIR": "YOUR_BASE_DIR_HERE",
"BASE_DIRS": "YOUR_BASE_DIRS_HERE",
"IGNORE_PATHS": "YOUR_IGNORE_PATHS_HERE",
"DB_PATH": "YOUR_DB_PATH_HERE",
"CACHE_DIR": "YOUR_CACHE_DIR_HERE",
"HF_ENDPOINT": "YOUR_HF_ENDPOINT_HERE"
}
}
}
}
Frequently asked questions
Andrea9293 MCP is categorized under Knowledge & Memory and uses a local stdio subprocess. MCP Local Rag belongs to Knowledge & Memory and uses a local stdio subprocess. Pick Andrea9293 MCP for knowledge & memory work and MCP Local Rag for knowledge & memory.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Andrea9293 MCP is listed as free. Auth: no auth required. MCP Local Rag is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add mcp-documentation-server and shinpr-mcp-local-rag as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Andrea9293 MCP has a quality signal of 67/100 (Great) with 4 views, 0 installs and 344 GitHub stars. MCP Local Rag has 69/100 (Great) with 9 views, 0 installs and 416 GitHub stars.