superdoc_get_content

Read document content in various formats. Call this first in any workflow to understand document structure before making edits. Action "blocks" returns structured block data with nodeId, nodeType, textPreview, optional full text when includeText:true, formatting properties (fontFamily, fontSize, color, bold, underline, alignment), and ref handles for immediate use with superdoc_edit or superdoc_format. Paragraph-class blocks include tabCount, the number of U+0009 tabs in the complete text even if the 80-character preview trims or truncates them. If tabCount is positive, read includeText:true before editing; do not treat a preview space as proof that there is no tab. Its optional reviewMode selects final, original, or redline numbering metadata without filtering blocks. When you need to evaluate or rewrite existing paragraphs or clauses, prefer action "blocks" with includeText:true so you can identify the correct block and then target it by nodeId. Actions "text", "markdown", and "html" return compact strings. Actions "markdown_projection" and "html_projection" return detailed async projections with review modes, scopes, diagnostics, annotations, block maps, and optional source maps. Projection source targets use tracked coordinates and are valid only at evaluatedRevision; after any mutation, reproject before using them. Treat omitted or partially emitted annotations according to their status instead of guessing an anchor from rendered text. Action "info" returns document metadata: word count, paragraph count, page count, outline, available styles, and capability flags. The "blocks" action supports pagination via "offset" and "limit", filtering via "nodeTypes", and numbering projection via "reviewMode". Other actions ignore pagination and filtering parameters. This tool never modifies the document. Do NOT call superdoc_edit or superdoc_format without first reading blocks to get valid refs and formatting reference values. EXAMPLES: 1. {"action":"blocks"} 2. {"action":"blocks","includeText":true,"offset":0,"limit":20,"reviewMode":"final"} 3. {"action":"blocks","offset":0,"limit":20,"nodeTypes":["heading","paragraph"]} 4. {"action":"text"} 5. {"action":"info"} 6. {"action":"html_projection","reviewMode":"redline","includeSourceMap":true} 7. {"action":"markdown_projection","reviewMode":"original","scope":{"kind":"block","nodeType":"paragraph","nodeId":"paragraph-id"},"includeSourceMap":true}. It is categorised as a Read tool in the Superdoc MCP Server, which means it retrieves data without modifying state.

superdoc_get_content accepts 12 parameters: in, limit, scope, action, offset, nodeIds, nodeTypes, reviewMode, session_id, textSearch, includeText, unflattenLists. Required: action, session_id. The full parameter table on this page comes from the server's own tool schema.

Register the Superdoc MCP server in PolicyLayer and add a rule for superdoc_get_content: 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 Superdoc. Nothing to install.

superdoc_get_content 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 superdoc_get_content 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 superdoc_get_content. 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.

superdoc_get_content is provided by the Superdoc MCP server (@superdoc/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.