Fetch vs Rag
A side-by-side look at the Fetch and Rag MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Fetch for search & data extraction work as a local process; choose Rag for search & data extraction. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Fetch when
- You need dedicated capabilities in the Search & Data Extraction domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
fetch.
Choose Rag when
- You need dedicated capabilities in the Search & Data Extraction domain.
- You want tools like
list_knowledge_bases, search_documents, get_document_chunk.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Search & Data Extraction | Search & Data Extraction |
| Quality signal | 80/100 · Excellent | 41/100 · Fair |
| Install command | Confirmed | Not confirmed yet |
| Transport | Local subprocess (stdio) | — |
| Auth | No auth required | Not declared |
| Pricing | Free | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Verified | Community listing |
| GitHub stars | 91,526 | 0 |
| Directory activity | 5 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | 1 | 7 |
| Full listing | View Fetch | View Rag |
Tools & capabilities
Fetch tools 1
fetchFetches a URL from the internet and extracts its contents as markdown.
Rag tools 7
list_knowledge_basesList all available KBs with status (file/chunk counts, indexing status)search_documentsHybrid BM25 + vector search with RRF. Supports `search_mode`: `auto`, `bm25`, `vectorget_document_chunkRetrieve full content of a specific chunk by IDstart_reindexQueue an indexing request. Scope merge, force/deferred flags, orchestrator auto-spawncancel_reindexRemove a pending (not-yet-started) queue entryget_index_infoIndex metadata, queue state (status/position/deferred/last_error), contextualization healthcheck_changesDry-run filesystem scan. Lightweight, no API calls
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.
Fetch
{
"mcpServers": {
"fetch": {
"command": "uvx",
"args": [
"mcp-server-fetch"
]
}
}
}
Rag
No confirmed install command for Rag yet — follow the setup steps linked from its listing page rather than a guessed package name.
Frequently asked questions
Fetch is categorized under Search & Data Extraction and uses a local stdio subprocess. Rag belongs to Search & Data Extraction and uses an install path we have not confirmed yet. Pick Fetch for search & data extraction work and Rag for search & data extraction.
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. Rag has no confirmed install command yet — follow its own setup instructions.
Fetch is listed as free. Auth: no auth required. Rag has no declared pricing — check the project's own site. 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 fetch and rag as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Fetch has a quality signal of 80/100 (Excellent) with 5 views, 0 installs and 91,526 GitHub stars. Rag has 41/100 (Fair) with 0 views, 0 installs and 0 GitHub stars.