AgentArmorHQ
Sign in

MCP

MCP server · GitHub · ★ 897 · graded 2026-10-23Source linked

Official Jina AI Remote MCP Server

No outside reports on file

This tool sends your data and queries to Jina's remote servers; secure your API keys carefully, validate all scraped content, and monitor API usage for abuse.

Based on public adoption and transparency signals as of Oct 23, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for MCP helpful?

What it can access

  • Local filesNo local folder access notedLOW
  • Command executionNo shell command runner notedLOW
  • Network reachLocal or standard API callsLOW
  • CredentialsRequires API key or tokenREVIEW
  • Package sourceGitHub (jina-ai/MCP)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/jina-ai/MCP ↗

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: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-23.

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 MCP

This MCP server connects Claude (an AI assistant) to Jina AI's remote services, likely for web scraping, data extraction, or document processing. It acts as a bridge that lets Claude send requests to Jina's cloud tools and get results back.

Who it’s for

Developers building Claude applications that need web content extraction or document analysis features. Teams using Jina AI's services who want to integrate them into Claude workflows.

Alternatives

  • Puppeteer or Playwright MCP servers: Local browser automation for web scraping without third-party servers.
  • Custom MCP servers: Build your own connector to in-house document extraction tools you control.
  • Anthropic's built-in tools: Claude's native file and web interaction features for basic use cases.

Setup

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

Follow the project's README for installation and configuration instructions. Typically MCP servers are added to Claude Desktop by editing a configuration file with the server's connection details.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

32/100
GitHub stars
897
Listing last refreshed
2026-10-29

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

Risks to watch for

  • API key exposure: Requires Jina AI credentials to work; if leaked, attackers can use your account and billing. Ensure keys are stored in environment variables, never in code.
  • Remote code through web content: Jina fetches and processes web pages; attackers could craft malicious pages with hidden prompts to manipulate Claude's responses.
  • Data sent to third party: All requests flow through Jina's servers; sensitive documents or queries are shared with their infrastructure.
  • Unvalidated external data: Results from web scraping may contain misleading information, malware links, or fake data designed to trick the AI.
  • Rate limits and DoS: Attackers could abuse the connection to exhaust API quotas or cause service disruptions, increasing your costs.

How to lower the risk

Least-privilege permissions

  • Use separate API keys for different applications, never share keys across projects.
  • Restrict Jina API key permissions to only needed scopes if their service supports it.

Network isolation

  • Store API keys only in environment variables or secure vaults, never hardcode them.
  • Monitor what URLs and domains Claude attempts to process through this connector.

Monitoring

  • Set up billing alerts on your Jina AI account to catch unexpected usage spikes.
  • Log all requests this server makes; review them regularly for unusual patterns.

Red flags to watch for

  • Unexpected charges or API quota consumption you didn't authorize.
  • Claude starting to visit websites or domains you didn't ask it to fetch.

Questions

How do I install MCP?

MCP does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/jina-ai/MCP.

Are there security reports about MCP?

No reports found for this package in our research (last checked 2026-10-30). MCP currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include api key exposure, remote code through web content, data sent to third party.

Is MCP actively maintained?

MCP has 897 GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/jina-ai/MCP before pinning it in production.

What are alternatives to MCP?

Notable alternatives to MCP include Puppeteer or Playwright MCP servers (Local browser automation for web scraping without third-party servers), Custom MCP servers (Build your own connector to in-house document extraction tools you control), Anthropic's built-in tools (Claude's native file and web interaction features for basic use cases). You can also compare MCP side by side with other MCP servers in the Related tools section on this page.

README badge and team notes

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

AgentArmorHQ Risk Grade C for MCP

GitHub README Markdown:

markdown
[![AgentArmorHQ Risk Grade for MCP](https://agentarmorhq.com/api/badge/jina-ai-mcp)](https://agentarmorhq.com/skills/jina-ai-mcp)

HTML embed:

html
<a href="https://agentarmorhq.com/skills/jina-ai-mcp"><img src="https://agentarmorhq.com/api/badge/jina-ai-mcp" alt="AgentArmorHQ Risk Grade for MCP" height="20" /></a>

Terminal check:

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

Share with your security lead

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

### AgentArmorHQ Security Review Memo: MCP
- **Listing URL:** https://agentarmorhq.com/skills/jina-ai-mcp
- **Type:** App connector
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 897 GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Local or standard API calls
- **Credentials:** Requires API key or token
- **Package source:** GitHub (jina-ai/MCP)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/jina-ai/MCP
- **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 23, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type
App connector
Publisher
jina-ai
Source code
github.com/jina-ai/MCP
Est. context load
~500 tokens / turn (~3 tool schemas, 0.25% of 200k context)
Popularity
897 GitHub stars
Last updated
2026-10-29
Last graded
2026-10-23

Community

Discussions for MCP

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 MCP 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