arr-mcpBLOCK
Arr related MCP and A2A / AG-UI Agent
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
CLI or API | MCP | Agent
Version: 2.1.0
Documentation — Installation, deployment, usage across the API, CLI, MCP, and A2A agent interfaces, and guidance for provisioning the Arr Suite services are maintained in the official documentation.
Table of Contents
- Overview
- Key Features
- Installation
- CLI or API
- MCP
- Dynamic Tool Selection & Visibility
- Agent
-
0330bcbdc0c2OBSERVED · 2026-10-11Connect
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.
claude mcp add arr-mcp -- uvx arr-mcp
{
"mcpServers": {
"arr-mcp": {
"command": "uvx",
"args": [
"arr-mcp"
]
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
arr_ingest_library | read | Ingest the live *arr library into epistemic-graph as typed nodes. |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- declared (6 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (11)
| **Prompt Injection Defense** | ✅ Built-in | 25+ pattern scanner + jailbreak taxonomy (CONCEPT:AU-OS.config.secrets-authentication) |
module = importlib.import_module(module_path)
A2A_URL = os.environ.get("A2A_URL", "http://127.0.0.1:9016/a2a/").bumpversion.cfg
.codespellignore
.pre-commit-config.yaml
.vulture_ignore
mod = importlib.import_module(pkg_name)
mod = importlib.import_module(pkg_name)
mod = importlib.import_module(pkg_name)
tree-sitter, requests, urllib3, pydantic
Gates applied: instruction_override, no_behavioural_pass.
0330bcbdc0c2full audit observations/trust-audit/mcp-server/knuckles-team__arr-mcp.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 |
|---|---|---|---|---|---|
| 2026-10-11 | 0330bcbdc0c2 | BLOCK | D | 69 | first audit |
Questions
What is the arr-mcp MCP server?
Arr related MCP and A2A / AG-UI Agent
What tools does arr-mcp expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is arr-mcp safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.
What credentials does arr-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does arr-mcp run?
It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on PyPI as arr-mcp.
How current is this page?
The grade is for one exact copy of the source (0330bcbdc0c2), read on 2026-10-11. The repository is watched and re-audited when it changes.