Content Tools
sefaria.org
This server provides access to the Sefaria library of Jewish texts, allowing retrieval of text, metadata, and connections between texts.
ENDPOINT 1
https://sefaria-mcp.shimonkolodny.workers.dev/mcp
MCP server metadata
- Name
- Sefaria
- Version
- 1.0.0
Known tools 9
get_indexReturns metadata for a specific text, such as section names and categories
Inferred read-onlyget_tocReturns the table of contents for all texts in the library, grouped by category
Inferred read-onlyget_topicsReturns a list of JSON objects containing metadata for topics in the database
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.sefaria]
url = "https://sefaria-mcp.shimonkolodny.workers.dev/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"sefaria": {
"type": "http",
"url": "https://sefaria-mcp.shimonkolodny.workers.dev/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: sefaria
Remote MCP URL: https://sefaria-mcp.shimonkolodny.workers.dev/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"sefaria": {
"url": "https://sefaria-mcp.shimonkolodny.workers.dev/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"sefaria": {
"type": "http",
"url": "https://sefaria-mcp.shimonkolodny.workers.dev/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "sefaria",
"transport": "streamable-http",
"url": "https://sefaria-mcp.shimonkolodny.workers.dev/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Loading Trust v2 evidence…
Checking the associated registrable domain. The BuiltWith key remains server-side.
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.