llamaparse-mcp

llamaparse-mcp is a skill for Claude Code from run-llama/llamaparse-agent-plugins. It costs 18 tokens per session (1,230 once invoked), scanned A, original, MIT.

Instructions for using LlamaParse MCP tools to upload, parse, classify, and split documents. MCP is a standard connection that lets an AI assistant call external tools.

In plain words
What is it for?
Use it when processing local files or files shared by URL through LlamaParse MCP.
Why use it?
It explains the required upload steps, account authentication, and regional server choice before document operations can work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the llamaparse-mcp-eu plugin — 2 skills, 1 MCP server shipped together

Good fit Use it when processing local files or files shared by URL through LlamaParse MCP.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/run-llama/llamaparse-agent-plugins/llamaparse-mcp
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add run-llama/llamaparse-agent-plugins --skill llamaparse-mcp
Clone the repo
git clone --depth 1 https://github.com/run-llama/llamaparse-agent-plugins

Made for: Claude Code.

Or install llamaparse-mcp-eu, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for llamaparse-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/run-llama/llamaparse-agent-plugins/llamaparse-mcp/github.svg)](https://agentmods.dev/skills/run-llama/llamaparse-agent-plugins/llamaparse-mcp)
Your own site
<a href="https://agentmods.dev/skills/run-llama/llamaparse-agent-plugins/llamaparse-mcp"><img src="https://agentmods.dev/badge/skills/run-llama/llamaparse-agent-plugins/llamaparse-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for llamaparse-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/run-llama/llamaparse-agent-plugins/llamaparse-mcp"><img src="https://agentmods.dev/badge/skills/run-llama/llamaparse-agent-plugins/llamaparse-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,230 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00018 $0.01230
Opus 5 $0.00009 $0.00615
Sonnet 5 $0.00004 $0.00246
Haiku 4.5 $0.00002 $0.00123

Measured 9d ago against content hash 0133e9171dc6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

llamaparse-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/llamaparse-mcp-eu/skills/llamaparse-mcp/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LlamaParse MCP — Usage Guide

Authentication

All tools require a valid session. If a tool call returns an authentication error, ask the user to re-authenticate before retrying. Do not retry automatically without prompting the user.

The server runs as two regional deployments — https://mcp.llamaindex.ai/mcp for accounts on cloud.llamaindex.ai, and https://mcp.eu.llamaindex.ai/mcp for accounts on cloud.eu.llamaindex.ai. Region follows the user's LlamaCloud account, so it is not something to switch mid-session. This plugin is pinned to the Europe endpoint; a token issued for North America is rejected with a 401 naming the other endpoint, and because the URL is fixed in the plugin manifest the fix is to install the llamaparse-mcp plugin instead — tell the user that rather than retrying.

Uploading a File

Every operation (parse, classify, split) requires a fileId obtained by uploading first. There are two upload paths — choose based on where the file lives:

  • File accessible via URL — use uploadFileByUrl. Pass the direct download URL and a descriptive file name. This is the preferred path when the user shares a link.
  • Local or binary file — call getUploadUrl first to obtain a pre-signed upload URL and token, then POST the file to the returned endpoint. The token is valid for 10 minutes; complete the upload before it expires.

For getUploadUrl, always set purpose to match the intended downstream operation ('parse', 'classify', 'split', etc.) so the server can apply the right storage policy.

Choosing What to Do with a File

Once you have a fileId, pick the tool that matches the user's goal:

Goal Tool
Extract text or markdown content parseFile
Determine which category a document belongs to classifyFile
Break a multi-section document into labeled segments splitFile

These are independent — you can run any combination on the same fileId.

Parsing

Use parseFile to extract readable content. Choose the tier based on document complexity:

Read the full file on GitHub · 87 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 87 lines · 18 tokens per session scan A 0133e9171dc6

Subscribe to this mod's changes

llamaparse-mcp is a skill published in the GitHub repository run-llama/llamaparse-agent-plugins (3 stars, last pushed 25d ago), licensed MIT. It adds 18 tokens to every session and 1,230 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

wiki

Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.

SethGammon/Citadel · 56 tokens

doctor

Read-only docflow diagnosis: scans docs, config, changelog, and links, then recommends init, adopt, or repair. Use when asked "check docs setup", "should I set up docflow", "why is docflow not working", or "doctor".

MedAdemBHA/docflow · 56 tokens

validate

Run the profile-aware DocFlow documentation readiness gate. Always blocks broken links, stale maps, and missing headings; applies native naming and section rules strictly to new scaffolds while treating established adopted structures as cleanup guidance.

MedAdemBHA/docflow · 44 tokens

repair

Safe maintenance for an existing docflow setup. Regenerates INDEX.md, installs or refreshes recognized DocFlow-managed helper scripts, runs link checks, and reports placeholder/validation issues. Use when docflow exists, after adding or renaming docs, or when doctor recommends repair.

MedAdemBHA/docflow · 58 tokens

read-text

Extract structured text, numbers, labels, and codes from images and evaluate by character or field accuracy. TRIGGER when: user asks to read/scan a serial, part/date/lot number, label, license plate, meter, gauge, barcode, QR code, invoice, document, form field, or other image text. SKIP when: user asks to tally/count…

Borda/vision-delivery · 143 tokens

preserve-security-evidence

Preserve security evidence before analysis, containment, or remediation changes it. Use for artifacts, volatile host state, vulnerability validation, records, logs, screenshots, commands, hashes, timelines, and reproducible handoffs.

gaelic-ghost/socket · 49 tokens