AgentArmorHQ
Sign in

UltraRAG

MCP server · GitHub · ★ 5.7k · graded 2026-10-21Source linked

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

No outside reports on file

UltraRAG can access your files and send document content through AI models, so restrict it to specific safe folders and monitor what data it indexes.

Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for UltraRAG helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionNo shell command runner notedLOW
  • Network reachConnects to outside service APINOTED
  • CredentialsNo API token requiredLOW
  • Package sourceGitHub (OpenBMB/UltraRAG)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/OpenBMB/UltraRAG ↗

All setup options ↓

Check this skillWatch it in my stackCompareREADME badgeView project

Everything known

We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.

0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30

Popularity grade: B (from public signals such as stars and downloads, not a code review). Graded 2026-10-21.

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.

Check a specific version →

About UltraRAG

UltraRAG is a framework that helps developers build retrieval-augmented generation (RAG) systems with less coding. RAG systems retrieve relevant documents or data, then use AI to generate answers based on what was retrieved. It appears designed to make complex RAG pipelines easier to set up and customize.

Who it’s for

Software developers and AI engineers who want to build RAG applications without writing everything from scratch. Teams that need flexible pipelines for searching documents and generating AI responses based on retrieved content.

Alternatives

  • LlamaIndex: Popular open-source RAG framework with similar goals.
  • LangChain: Widely-used framework for building retrieval and generation chains.
  • Haystack: Retrieval and QA framework by DeepSet, focused on document search.

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README. The GitHub repository should have installation instructions for setting it up as an MCP server or connector.

Why this grade

BB — Some risk signals

Signal-based grade (4/7 points): very widely starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

41/100
GitHub stars
5.7k
Listing last refreshed
2026-10-30

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Risks to watch for

  • File and data access: Can read files from your system to build retrieval indexes; could expose sensitive documents if not restricted to intended folders.
  • Prompt injection via documents: If someone adds malicious text to indexed documents, it could trick the AI into unexpected behavior when those documents are retrieved.
  • Model interaction: Sends queries and retrieved content to language models; very large or sensitive documents could end up in model processing.
  • Configuration mistakes: Incorrect setup could index the wrong directories or expose unintended data sources.
  • Third-party dependencies: Uses other packages that may have their own vulnerabilities; keep dependencies updated.

How to lower the risk

Least-privilege permissions

  • Only let it read specific folders you intend to index, never your entire system.
  • Use a dedicated service account with minimal access rights.

Network isolation

  • Run it on an internal network or isolated environment if possible.
  • Be cautious if it makes external API calls; verify where data is sent.

Monitoring

  • Log which files and folders are being indexed.
  • Track what documents are being retrieved in response to queries.

Red flags to watch for

  • Unexpected file access outside your configured folders.
  • Large amounts of sensitive data being indexed without your approval.
  • Changes to configuration or indexed sources you didn't make.

Questions

How do I install UltraRAG?

UltraRAG does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/OpenBMB/UltraRAG.

Are there security reports about UltraRAG?

No reports found for this package in our research (last checked 2026-10-30). UltraRAG currently holds Grade B (Some risk signals) based on public adoption and transparency signals. Key risk areas to watch include file and data access, prompt injection via documents, model interaction.

Is UltraRAG actively maintained?

UltraRAG has 5.7k GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/OpenBMB/UltraRAG before pinning it in production.

What are alternatives to UltraRAG?

Notable alternatives to UltraRAG include LlamaIndex (Popular open-source RAG framework with similar goals), LangChain (Widely-used framework for building retrieval and generation chains), Haystack (Retrieval and QA framework by DeepSet, focused on document search). You can also compare UltraRAG side by side with other MCP servers in the Related tools section on this page.

README badge and team notes

Maintain or use UltraRAG? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

AgentArmorHQ Risk Grade B for UltraRAG

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for UltraRAG](https://agentarmorhq.com/api/badge/openbmb-ultrarag)](https://agentarmorhq.com/skills/openbmb-ultrarag)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/openbmb-ultrarag"><img src="https://agentarmorhq.com/api/badge/openbmb-ultrarag" alt="AgentArmorHQ Risk Grade for UltraRAG" height="20" /></a>

Terminal check:

terminal
curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "openbmb-ultrarag"

Share with your security lead

Need sign-off to use UltraRAG? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: UltraRAG
- **Listing URL:** https://agentarmorhq.com/skills/openbmb-ultrarag
- **Type:** App connector
- **Risk Grade:** Grade B (Some risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 5.7k GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** No API token required
- **Package source:** GitHub (OpenBMB/UltraRAG)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/OpenBMB/UltraRAG
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
App connector
Publisher
OpenBMB
Source code
github.com/OpenBMB/UltraRAG
Est. context load
~500 tokens / turn (~3 tool schemas, 0.25% of 200k context)
Popularity
5.7k GitHub stars
Last updated
2026-10-30
Last graded
2026-10-21

Community

Discussions for UltraRAG

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for UltraRAG helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude