List the commentaries and cross-references on a passage (e.g. Rashi, Targum, quoting commentaries) from Sefaria's link graph. Keyless.
AI agents call get_commentaries to retrieve information from Mcp Sefaria without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
ref | string | Yes | Textual reference, e.g. "Genesis.1.1", "Shabbat.2a". |
limit | number | — | Max results (default 25, max 100). |
category | string | — | Filter to links of this category, case-insensitive (e.g. "Commentary", "Targum"). Default "Commentary". |
Parameters from the server's own tool schema.
This tool queries and returns existing metadata (commentaries and cross-references) from the Sefaria digital library without creating, modifying, or deleting any data. It is purely informational retrieval, making it a Read operation with low severity. The blast radius of misuse is minimal—an agent could only retrieve more commentary data than intended, posing no destructive or operational risk.
From the tool's definition Tool name 'get_commentaries' and description 'List the commentaries and cross-references on a passage' indicates a retrieval/query operation.
Attacks that exploit this kind of access
List the commentaries and cross-references on a passage (e.g. Rashi, Targum, quoting commentaries) from Sefaria's link graph. Keyless. It is categorised as a Read tool in the Mcp Sefaria MCP Server, which means it retrieves data without modifying state.
get_commentaries accepts 3 parameters: ref, limit, category. Required: ref. The full parameter table on this page comes from the server's own tool schema.
Register the Mcp Sefaria MCP server in PolicyLayer and add a rule for get_commentaries: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Sefaria. Nothing to install.
get_commentaries is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_commentaries rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_commentaries. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_commentaries is provided by the Mcp Sefaria MCP server (pipeworx-io/mcp-sefaria). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →