A side-by-side look at the Scrivener MCP and 💯 YouTube Transcript + YouTube Search MCP for AI Agents MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Scrivener MCP for knowledge & memory work as a local process; choose for search & data extraction as a local process. You can also run both side by side in one block.
mcpServersRows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Knowledge & Memory | Search & Data Extraction |
| Quality signal | 61/100 · Good | 41/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | Not declared |
| Pricing | Free | Freemium |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 67 | 11 |
| Directory activity | 18 views 12 installs 6 upvotes | 3 views 0 installs 0 upvotes |
| Tools | Not listed | Not listed |
| Full listing | View Scrivener MCP | View 💯 YouTube Transcript + YouTube Search MCP for AI Agents |
No tool names declared yet. Check the project README from the listing page.
No tool names declared yet. Check the project README from the listing page.
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.
{
"mcpServers": {
"writerslogic-scrivener-mcp": {
"command": "npx",
"args": [
"-y",
"scrivener-setup"
]
}
}
}
{
"mcpServers": {
"youtube-transcript-youtube-search-mcp-for-ai-agents": {
"command": "npx",
"args": [
"-y",
"ajv-cli@5"
]
}
}
}