Extract raw text content from a document. Supports PDF (pdf-parse), Word/DOCX (mammoth), images via OCR (tesseract.js), Excel/CSV (xlsx), and plain text. Accepts a remote URL, a local file path, or base64-encoded bytes. Returns the extracted text plus character and word counts.
Accepts URL/endpoint input (url); Accepts file system path (file_path)
Part of the Docpulse MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call extract_document to retrieve information from Docpulse without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though extract_document only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
extract_document:
rules:
- action: allowSee the full Docpulse policy for all 4 tools.
Agents calling read-class tools like extract_document have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
Extract raw text content from a document. Supports PDF (pdf-parse), Word/DOCX (mammoth), images via OCR (tesseract.js), Excel/CSV (xlsx), and plain text. Accepts a remote URL, a local file path, or base64-encoded bytes. Returns the extracted text plus character and word counts.. It is categorised as a Read tool in the Docpulse MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for extract_document. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Docpulse MCP server.
extract_document 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 extract_document rule in your Intercept 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 Intercept policy for extract_document. 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.
extract_document is provided by the Docpulse MCP server (nicholasemccormick/docpulse-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.