Atlas / MCP servers / nestdevlab / agentwheel

agentwheelCAUTION

mcp/nestdevlab/agentwheel

Skills, rules, and instructions across every AI agent. One source, every agent.

Verdict
CAUTION
Grade
B
Trust score
87 /100
Exposed tools
5 5r · 0w · 0d
Transport
streamable-http
License
MIT
Stars
9
01

Overview

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

agentwheel

One source. Every agent.

Weave skills, rules, instructions, commands, subagents, MCP, hooks, settings, and plugins across every AI agent you use, from any source, reconciled into each runtime with your private tweaks intact.

Why agentwheel?

Your AI agents are multiplying. OpenClaw, Claude Code, Codex CLI, Copilot, Hermes — and the next harness your team adopts. Each one wants its own skills, rules, instructions, commands, subagents, MCP servers, hooks, and settings, in its own layout.

agentwheel makes that one declared state. Add packages to .agentwheel/config.json, preview the runtime changes, then install the declared state into each target. Updates move tracking sources forward explicitly; installs make the current declaration true.

npm i -g agentwheel
agentwheel init
agentwheel add github:your-org/agent-pack --adapter codex --local --mode tracking
agentwheel plan
agentwheel install

No lock-in. No central gatekeeper. Packages live in plain git repos or local folders, customizations live in your workspace, and runtimes stay generated output.

Install Methods

CLI install

npm i -g agentwheel
agentwheel init

Prefer pnpm? pnpm add -g agentwheel works too.

AI agent handoff

Give an agent install.md when you want it to install Agentwheel, verify the CLI, install the companion skill, and show the right catalogue flow for your runtime.

curl -fsSL https://raw.githubusercontent.com/NestDevLab/agentwheel/main/install.md

Companion skills

The management skill keeps Agentwheel commands and safety rules inside the runtime you are using. Install the discovery skill separately when you also want proactive, non-installing suggestions:

agentwheel doctor --adapter codex --local
agentwheel install 
Read from source at commit 5b3208b48757OBSERVED · 2026-10-12
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 agentwheel --env AGENTWHEEL_AUTH_CONFIG=${AGENTWHEEL_AUTH_CONFIG} -- npx -y [email protected]
claude-desktop
{
  "mcpServers": {
    "agentwheel": {
      "command": "npx",
      "args": [
        "-y",
        "[email protected]"
      ],
      "env": {
        "AGENTWHEEL_AUTH_CONFIG": "${AGENTWHEEL_AUTH_CONFIG}"
      }
    }
  }
}
03

Exposed tools (5)

5 read · 0 write · 0 destructive.

ToolRiskDescription
ai-agentreadBuild a conversational agent
code-reviewreadA
inboxreadC
self-improvereadCapture corrections for future sessions
self-improving-agentreadContinuously evolve from experience
04

Trust audit

CAUTIONgrade B · trust 87/100 Install with care. The audit found things worth knowing before you trust its output.

LayerWhat it checksResult
L0Provenance & inventoryPASS
L1Static analysis of the codeFAIL
L2Instruction surface (what it tells the agent)PASS
L3Class-specific surfacePASS
L4Behavioural (sandbox)SKIPPED

What the source does

Filesystem
declared (6 observation(s))
Network
declared (4 observation(s))
Shell
none-observed
Dependencies
not all pinned
Secrets in source
none-found

Findings (16)

HIGHFilesystem / path · fs.credential_store · CWE-22, CWE-59
src/cli/index.ts:4895
identityFile: "~/.ssh/id_ed25519",
Why it matters. touches a credential store
LOWInventory / provenance · inv.hidden_file · CWE-1104
docs/.nojekyll
.nojekyll
Why it matters. hidden member outside the usual dotfiles
Fix. review its purpose
LOWFilesystem / path · fs.credential_store · CWE-22, CWE-59
test/runtime-target.test.ts:440
identityFile: ".ssh/id_ed25519",
Why it matters. touches a credential store
LOWFilesystem / path · fs.credential_store · CWE-22, CWE-59
test/runtime-target.test.ts:453
identityFile: join(project, ".ssh/id_ed25519"),
Why it matters. touches a credential store
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/targets/plugins/claude.ts:2
import type { Artifact } from "../../model/artifact.js";
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/targets/plugins/codex.ts:2
import type { Artifact } from "../../model/artifact.js";
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/targets/plugins/common.ts:4
import { pathExists } from "../../utils/fs.js";
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/targets/plugins/copilot.ts:2
import type { Artifact } from "../../model/artifact.js";
LOWFilesystem / path · fs.traversal · CWE-22, CWE-59
src/targets/plugins/hermes.ts:2
import type { Artifact } from "../../model/artifact.js";
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
test/openclaw-adapter.test.ts:274
process.env.ODOO_SERVICE_MCP_URL = "http://192.168.1.107:3201/mcp";
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
test/openclaw-adapter.test.ts:308
url: "http://192.168.1.107:3201/mcp",
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
test/openclaw-adapter.test.ts:339
expect(refreshed.mcp.servers["odoo-service"].url).toBe("http://192.168.1.107:3201/mcp");
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
test/openclaw-adapter.test.ts:366
url: "http://192.168.1.107:3201/mcp",
LOWNetwork egress · net.raw_ip · CWE-200, CWE-319
test/openclaw-adapter.test.ts:377
url: "http://192.168.1.107:3201/mcp",
LOWObfuscation / stealth · obf.zero_width · CWE-506, CWE-94
test/skill-frontmatter-validation.test.ts:48
const artifact = await skillArtifact(`${validFrontmatter}`);
LOWSupply chain · supply.unpinned · CWE-829, CWE-1357
package.json
mermaid
Why it matters. 1 dependency range(s) float
Fix. pin exact versions or ship a lockfile

Gates applied: no_behavioural_pass.

Audited 2026-10-12 · audit v0.4.1 · source sha 5b3208b48757full audit observations/trust-audit/mcp-server/nestdevlab__agentwheel.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
2026-10-125b3208b48757CAUTIONB87first audit
06

Questions

What is the agentwheel MCP server?

Skills, rules, and instructions across every AI agent. One source, every agent.

What tools does agentwheel expose?

5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.

Is agentwheel safe to connect to an agent?

With care. The audit graded it B (87/100) and found 16 things worth knowing before you trust this server, listed below with the exact line each was found on.

What credentials does agentwheel need?

It reads AGENTWHEEL_AUTH_CONFIG 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 agentwheel run?

It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as agentwheel at 0.20.20.

How current is this page?

The grade is for one exact copy of the source (5b3208b48757), read on 2026-10-12. The repository is watched and re-audited when it changes.

Advertisement