--- title: "Reducto" description: "The agentic document platform for parsing, extraction, splitting, classification, and editing." canonical: "https://reducto.ai/" last-updated: "2026-08-21" --- # Reducto Reducto is the complete agentic document platform for parsing, extracting, splitting, classifying, and editing documents at enterprise scale. It combines custom models with frontier models for accurate, citation-ready outputs across 30+ file types, including complex tables, charts, handwriting, scans, and spreadsheets. Get started free with 15,000 credits at https://studio.reducto.ai/. ## Products - [Parse](https://reducto.ai/parse): Turn PDFs, scans, spreadsheets, and slides into structured, citation-ready JSON. - [Split](https://reducto.ai/split): Segment documents into meaningful sections and repeating sub-documents. - [Extract](https://reducto.ai/extract): Return typed JSON with citations and bounding boxes. - [Classify](https://reducto.ai/classify): Route documents using plain-language taxonomies. - [Edit](https://reducto.ai/edit): Turn extracted data back into finished PDF and DOCX files. - [Studio](https://reducto.ai/studio): Build, test, and deploy document pipelines without code. ## Developer Tools - [Agent skill](https://reducto.ai/SKILL.md): Setup instructions for AI agents, including API usage, CLI, and MCP. - [Agent skills discovery](https://reducto.ai/.well-known/agent-skills/index.json): Machine-readable index of available agent skills. - [Agent card](https://reducto.ai/.well-known/agent-card.json): Machine-readable agent card for Reducto's MCP and REST API interface. - [Agent discovery](https://reducto.ai/.well-known/agents.json): Discovery metadata linking Reducto's agent card, skill, and MCP endpoint. - [MCP discovery](https://reducto.ai/.well-known/mcp.json): Machine-readable MCP endpoint, authentication, and server-card metadata. - [Web MCP discovery](https://reducto.ai/.well-known/webmcp.json): Machine-readable Web MCP endpoint and server-card metadata. - [MCP server cards](https://reducto.ai/.well-known/mcp/server-cards.json): Index of Reducto's hosted MCP server cards. - [MCP server](https://docs.reducto.ai/mcp-server): Connect AI agents through the hosted server or `uvx mcp-server-reducto`. - [CLI](https://docs.reducto.ai/cli): Parse, extract, split, classify, and edit from the terminal with `pip install reducto-cli`. - [API documentation](https://docs.reducto.ai): Quickstarts, API reference, and SDKs for Python and Node. - [OpenAPI specification](https://reducto.ai/openapi.json): OpenAPI 3.1 schema for the Reducto API. - [Developers](https://reducto.ai/developers.md): Markdown implementation guide for API, SDK, CLI, and MCP users. ## Setup for agents ```text Step 1: Set up Reducto Read https://reducto.ai/SKILL.md and follow its setup instructions: get a Reducto API key configured and verify credentials against the API before proceeding. For a new user with no saved key, use the direct HTTP signup in https://reducto.ai/auth.md (no CLI). Ask for the email, request the code, then ask for code, first/last name, explicit terms agreement, and the first document together. Keep the signup token private; on 202 or a lost response repeat the same verification request after Retry-After. Save the returned key securely as REDUCTO_API_KEY without printing it. After successful signup, tell the human: no password was set; the signup code only verified their email. They can sign into Studio using a magic link via “Email me a sign-in link”. Setting a password is optional via “Set a password” on the login screen. Show error.message and error.field (when present) in the agent's terminal. For 400 invalid_input, ask for the corrected fields and retry; if error.restart_required is true, request a new code after correcting the fields and respecting the resend cooldown. Otherwise, preserve any already accepted verification request. For 403 signup_restricted, show the email-policy reason and ask for a different email. Only 409 studio_required requires Studio. For studio_required, stop automated signup and show error.message with studio_url. The human continues in Studio to sign in, finish setup, or select Join or Request access for a listed organization. Never infer consent. Process the supplied first document once the key is ready before asking about further setup. Step 2: Ask the user Would you like to: a) Start a fresh project b) Integrate into an existing project c) Process local files from the terminal (no project) d) Add Reducto as MCP tools in this agent or another MCP client Step 3: Set up the chosen path If the answer to Step 2 is (a) - Fresh project: Ask the user which language they prefer (Python or TypeScript). Scaffold a minimal project and install the SDK (pip install reductoai or npm install reductoai). Wire up REDUCTO_API_KEY: the SDKs read it from the process environment, not from .env files — if you use a .env file, load it explicitly (python-dotenv in Python, node --env-file=.env or dotenv in Node). Write a first script from the SKILL.md quickstart: upload a document, parse it, print the result. If the answer to Step 2 is (b) - Existing project: Read the user's codebase to understand: - Language and framework - Package manager (npm, pnpm, pip, uv, poetry, go modules, etc.) - Project structure and file conventions - How environment variables are managed (.env, config files, secrets, etc.) Ask the user what they want Reducto to do in their project (parse documents to markdown, extract fields to JSON with a schema, classify, split, or fill forms). Based on the project's language, read the relevant Reducto SDK README: Python: https://raw.githubusercontent.com/reductoai/reducto-python-sdk/main/README.md TypeScript: https://raw.githubusercontent.com/reductoai/reducto-node-sdk/main/README.md Go: https://raw.githubusercontent.com/reductoai/reducto-go-sdk/main/README.md - Install the Reducto SDK and any required dependencies. - Write the integration code, matching the project's existing conventions. If the answer to Step 2 is (c) - Terminal only: Install the CLI: pip install reducto-cli (requires Python 3.11+; on older Pythons use uv tool install reducto-cli). If it's already installed, update it: pip install --upgrade reducto-cli, or uv tool upgrade reducto-cli if it was installed with uv. The CLI reads REDUCTO_API_KEY from the environment; run reducto login only if the env var isn't set. Then run reducto parse or reducto extract -s schema.json. If the answer to Step 2 is (d) - MCP tools: Follow the SKILL.md "MCP Server" section. Use the local server (uvx mcp-server-reducto, requires Python 3.11+ and uvx) when documents are local files; use the hosted server (https://mcp.reducto.ai/mcp with an Authorization: Bearer header) when documents are at public URLs. For Claude Code: claude mcp add -s user reducto -- uvx mcp-server-reducto. The local server reads REDUCTO_API_KEY from the environment. Restart the MCP client and confirm the Reducto tools (parse_document, extract_data, upload_file, ...) appear, then verify by calling parse_document on a sample document. Step 4: Verify Confirm credentials: curl -s "https://platform.reducto.ai/jobs?limit=1" -H "Authorization: Bearer $REDUCTO_API_KEY" returns a jobs array. Run a first parse on a real document and confirm the response contains job_id, result, and usage. Share the response's studio_link with the user so they can inspect the output against the source document. If something fails, diagnose the issue and fix it. Common issues: - 401 "Provide an access token" means REDUCTO_API_KEY is empty in this shell; 401 "Invalid access token" means the key is wrong; 403 with an HTML page means no Authorization header was sent - reducto command not found: requires Python 3.11+, or install with uv tool install reducto-cli - Empty chunks on large documents: result.type == "url" - fetch result.url for the content ``` ## More - [Agent skill](https://reducto.ai/SKILL.md) - [LLM documentation index](https://reducto.ai/llms.txt) - [Full homepage overview](https://reducto.ai/llms-full.txt) - [Developers](https://reducto.ai/developers.md): Build document workflows with the Reducto API, SDKs, CLI, and MCP server. - [Pricing](https://reducto.ai/pricing.md): Per-product Standard pricing and custom Growth and Enterprise plans for the Reducto platform. - [About](https://reducto.ai/about.md): Learn about Reducto, the agentic document platform for AI teams. - [Contact](https://reducto.ai/contact.md): Contact Reducto sales, support, and solutions teams about the document platform. - [Authentication](https://reducto.ai/auth.md): How agents discover, obtain, use, and revoke Reducto API credentials. - [MCP capabilities catalog](https://reducto.ai/.well-known/ai-catalog.json)