---
type: "raw_signal"
id: "parse-extract-classify-now-each-with-its-own-86d89a"
slug: "parse-extract-classify-now-each-with-its-own-86d89a"
title: "Parse, Extract, Classify — now each with its own MCP"
description: "LlamaIndex announced Retrieval Harness for LlamaParse, giving agents filesystem-style list, grep, read, and hybrid-retrieve tools to traverse and verify a document corpus."
retrieval_nugget: "LlamaIndex announced Retrieval Harness for LlamaParse, giving agents filesystem-style list, grep, read, and hybrid-retrieve tools to traverse and verify a document corpus."
observed_at: "2026-09-25"
record_date: "2026-09-25"
date_kind: "observed_at"
why_it_matters: "LlamaIndex announced Retrieval Harness for LlamaParse, giving agents filesystem-style list, grep, read, and hybrid-retrieve tools to traverse and verify a document corpus. It also restructured its MCP offering into a general endpoint plus product-specific endpoints for Parse, Extract, Classify, Split, and Index. The update includes LiteParse v2.1 with local open-source PDF-to-Markdown conversion, "
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "llamaindex.ai"
topics: []
entities: []
related_patterns: []
source_url: "https://www.llamaindex.ai/blog/llamaindex-newsletter-26-07-08"
source_urls: ["https://www.llamaindex.ai/blog/llamaindex-newsletter-26-07-08"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:parse-extract-classify-now-each-with-its-own-86d89a"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/parse-extract-classify-now-each-with-its-own-86d89a/","markdown":"https://newruntime.com/signals/parse-extract-classify-now-each-with-its-own-86d89a.md","json":"https://newruntime.com/signals/parse-extract-classify-now-each-with-its-own-86d89a.json"}
---

# Parse, Extract, Classify — now each with its own MCP

## Retrieval answer

LlamaIndex announced Retrieval Harness for LlamaParse, giving agents filesystem-style list, grep, read, and hybrid-retrieve tools to traverse and verify a document corpus.

LlamaIndex announced Retrieval Harness for LlamaParse, giving agents filesystem-style list, grep, read, and hybrid-retrieve tools to traverse and verify a document corpus. It also restructured its MCP offering into a general endpoint plus product-specific endpoints for Parse, Extract, Classify, Split, and Index. The update includes LiteParse v2.1 with local open-source PDF-to-Markdown conversion, as well as improved tier routing, Usage Tags, and parse-job metadata intended to make document-processing spend easier to allocate and inspect.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)