Jina AISAFE
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/server/jina-ai-mcp) [](https://smithery.ai/server/jina-ai-mcp-server)
An MCP server that provides access to Jina AI's powerful web services through Claude. This server implements three main tools:
- Web page reading and content extraction
- Web search
- Fact checking/grounding
Features
Tools
read_webpage
- Extract content from web pages in a format optimized for LLMs
- Supports multiple output formats (Default, Markdown, HTML, Text, Screenshot, Pageshot)
- Options for including links and images
- Ability to generate alt text for images
- Cache control options
search_web
- Search the web using Jina AI's search API
- Configurable number of results (default: 5)
- Support for image retention and alt text generation
- Multiple return formats (markdown, text, html)
- Returns structured results with titles, descriptions, and content
fact_check
- Fact-check statements using Jina AI's grounding engine
- Provides factuality scores and supporting evidence
- Optional deep-dive mode for more thorough analysis
- Returns references with key quotes and supportive/contradictory classification
Setup
Prerequisites
You'll need a Jina AI API key to use this server. Get one for free at https://jina.ai/
Installation
There are two ways to use this server:
Installing via Smithery
To install Jina AI for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install jina-ai-mcp-server --client claude
Option 1: NPX (Recommended)
Add this configuration to your Claude Desktop config file:
{
"mcpServers": {
"jina-aid9913a820bd0OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add jina-ai-mcp-server --env JINA_API_KEY=${JINA_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"jina-ai-mcp-server": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"JINA_API_KEY": "${JINA_API_KEY}"
}
}
}
}Exposed tools (3)
3 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
fact_check | read | Fact-check a statement using Jina AI |
read_webpage | read | Extract content from a webpage in a format optimized for LLMs |
search_web | read | Search the web using Jina AI |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (3 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
@modelcontextprotocol/sdk, mcp-evals, node-fetch, zod, zod-to-json-schema, @types/node, ts-node, typescript
The evals package loads an mcp client that then runs the index.ts file, so there is no need to rebuild between tests. You can load environment variables by prefixing the npx command. Full documentatio
Gates applied: no_behavioural_pass.
d9913a820bd0full audit observations/trust-audit/mcp-server/joebuildsstuff__jina-ai-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | d9913a820bd0 | SAFE | B | 89 | first audit |
Questions
What tools does Jina AI expose?
3 in total: 3 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Jina AI safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Jina AI need?
It reads JINA_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Jina AI run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as jina-ai-mcp-server at 1.0.4.
How current is this page?
The grade is for one exact copy of the source (d9913a820bd0), read on 2026-10-08. The repository is watched and re-audited when it changes.