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.
npx skills add run-llama/llamaparse-agent-plugins --skill llamaparse-mcpgit clone --depth 1 https://github.com/run-llama/llamaparse-agent-pluginsWrote 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.
[](https://agentmods.dev/skills/run-llama/llamaparse-agent-plugins/llamaparse-mcp)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
getUploadUrlfirst 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:
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.
- 9d ago First seen · 87 lines · 18 tokens per session scan A 0133e9171dc6
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.
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.
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".
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.
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.
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…
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.