ModelsAtlas
Explore
Atlas / MCP servers / xuanwo / Opendal

OpendalSAFE

mcp/xuanwo/opendal
MCP server by xuanwo · Audited 2026-10-08
⚑ Report / re-scanSource ↗

Model Context Protocol Server for Apache OpenDALTM

Verdict
SAFE
Grade
B
Trust score
89 /100
Exposed tools
3 3r · 0w · 0d
Transport
—
License
Apache-2.0
Stars
35
01

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

A Model Context Protocol (MCP) server implementation that provides access to various storage services via Apache OpenDALTM.

[](https://pypi.org/project/mcp-server-opendal/) [](https://pypi.org/project/mcp-server-opendal/) [](https://github.com/Xuanwo/mcp-server-opendal/actions/workflows/test.yml)

Features

  • Seamless access to multiple storage services including S3, Azure Blob Storage, Google Cloud Storage, and more
  • List files and directories from storage services
  • Read file contents with automatic text/binary detection
  • Environment variable based configuration

Installation

pip install mcp-server-opendal

Usage with Claude Desktop

Add the following to claude_desktop_config.json:

{
"mcpServers": {
"opendal": {
"command": "uvx",
"args": [
"mcp-server-opendal"
],
"env": {
"YOUR_ENV_VAR": "YOUR_ENV_VALUE"
}
}
}
}

It requires uv to be installed on your machine. Check the official documentation for installation guides.

Environment variables

Configure storage services by setting environment variables. Each service requires a prefix and specific configuration options.

For example, to configure an S3 service with alias "mys3":

OPENDAL_MYS3_TYPE=s3
OPENDAL_MYS3_BUCKET=mybucket
OPENDAL_MYS3_REGION=us-east-1
OPENDAL_MYS3_ENDPOINT=http://localhost:9000
OPENDAL_MYS3_ACCESS_KEY_ID=myaccesskey
OPENDAL_MYS3_SECRET_ACCESS_KEY=mysecretkey

Then you can use tool like read and list with mys3://path/to/file.

mcp-server-opendal will also load from .env.

Development

Read from source at commit 430b757540fdOBSERVED · 2026-10-08
02
Connect
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-code
claude mcp add mcp-server-opendal --env OPENAI_API_KEY=${OPENAI_API_KEY} -- uvx mcp-server-opendal
claude-desktop
{
  "mcpServers": {
    "mcp-server-opendal": {
      "command": "uvx",
      "args": [
        "mcp-server-opendal"
      ],
      "env": {
        "OPENAI_API_KEY": "${OPENAI_API_KEY}"
      }
    }
  }
}
03
Exposed tools (3)
3 read · 0 write · 0 destructive.
ToolRiskDescription
get_inforead
listread
readread
04
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.
LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codePASS
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED
What the source does
Filesystem
none-observed
Network
none-observed
Shell
none-observed
Dependencies
pinned
Secrets in source
none-found
Findings (2)
LOWObfuscation / stealth · obf.decode_call · CWE-506, CWE-94
tests/test_integration_fs.py:118
decoded = base64.b64decode(result["content"])
INFOPrompt injection · prompt.credential_read · CWE-94, CWE-1427
README.md:60
`mcp-server-opendal` will also load from `.env`.
Why it matters. asks the agent to read credentials
Gates applied: no_behavioural_pass.
Audited 2026-10-08 · audit v0.4.1 · source sha 430b757540fdfull audit observations/trust-audit/mcp-server/xuanwo__opendal.json · Report an issue / request a re-scan
05
Audit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
DateSourceVerdictGradeScoreChange
2026-10-08430b757540fdSAFEB89first audit
06
Questions
What is the Opendal MCP server?
Model Context Protocol Server for Apache OpenDALTM
What tools does Opendal 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 Opendal 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 Opendal need?
It reads OPENAI_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 current is this page?
The grade is for one exact copy of the source (430b757540fd), read on 2026-10-08. The repository is watched and re-audited when it changes.
Advertisement