Fetch vs Crw
A side-by-side look at the Fetch and Crw 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 Crw for search & data extraction as a local process. 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
create_entities, create_relations, add_observations.
Choose Crw when
- You need dedicated capabilities in the Search & Data Extraction domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: OAuth 2.0.
- You have the keys it needs:
CRW_API_KEY. - You want tools like
crw_scrape, crw_crawl, crw_check_crawl_status.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Search & Data Extraction | Search & Data Extraction |
| Quality signal | 90/100 · Excellent | 72/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | OAuth 2.0 |
| Pricing | Free | Freemium |
| Required env vars | None listed | CRW_API_KEY |
| Verified owner | Verified | Community listing |
| GitHub stars | 91,147 | 1,134 |
| Directory activity | 4 views 0 installs 0 upvotes | 4 views 0 installs 0 upvotes |
| Tools | 9 | 8 |
| Full listing | View Fetch | View Crw |
Tools & capabilities
Fetch tools 9
create_entitiesCreate multiple new entities in the knowledge graphcreate_relationsCreate multiple new relations between entities in the knowledge graph. Relations should be in active voiceadd_observationsAdd new observations to existing entities in the knowledge graphdelete_entitiesDelete multiple entities and their associated relations from the knowledge graphdelete_observationsDelete specific observations from entities in the knowledge graphdelete_relationsDelete multiple relations from the knowledge graphread_graphRead the entire knowledge graphsearch_nodesSearch for nodes in the knowledge graph based on a queryopen_nodesOpen specific nodes in the knowledge graph by their names
Crw tools 8
crw_scrapeScrape one URL to markdown, HTML, or links.crw_crawlStart an async site crawl; returns a job id to poll with crw_check_crawl_status.crw_check_crawl_statusPoll an async crawl job and retrieve its pages.crw_mapDiscover URLs on a site via sitemap and/or a short crawl. Returns a URL list only, no page content.crw_extractExtract structured JSON from URLs via a prompt and/or JSON schema. Async job — poll crw_check_extract_status with the returned id. Needs an LLM.crw_check_extract_statusPoll an extract job; returns status and, when complete, a per-URL results array.crw_cancel_extractRequest cancellation of an extract job. Returns the canonical status; cancelling remains non-terminal until the claimed URL settles.crw_parse_fileParse a local PDF (base64 in contentBase64) to markdown. No OCR: scanned PDFs return empty markdown with a warning.
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": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-memory"
]
}
}
}
Crw
{
"mcpServers": {
"us-crw": {
"command": "npx",
"args": [
"-y",
"crw-mcp@latest"
],
"env": {
"CRW_API_KEY": "YOUR_CRW_API_KEY_HERE"
}
}
}
}
Frequently asked questions
Fetch is categorized under Search & Data Extraction and uses a local stdio subprocess. Crw belongs to Search & Data Extraction and uses a local stdio subprocess. Pick Fetch for search & data extraction work and Crw 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.
Fetch is listed as free. Auth: no auth required. Crw is listed as freemium — a free tier with paid plans. Auth: oauth 2.0. 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 us-crw 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 90/100 (Excellent) with 4 views, 0 installs and 91,147 GitHub stars. Crw has 72/100 (Great) with 4 views, 0 installs and 1,134 GitHub stars.