AgentsSAFE
One .agents source of truth to sync MCP servers, skills, and instructions across Codex, Claude Code, Gemini CLI, Cursor, Copilot, and Antigravity.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
agents
One config to rule them all.Practical standard layer for multi-LLM development.
Quick Start · Integrations · Commands · Plugins · FAQ
The Problem
Instructions converged on AGENTS.md and skills converged on SKILL.md. MCP server configuration did not. Every tool keeps its own file, in its own format, in its own place:
024d27681b42OBSERVED · 2026-10-12Connect
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 cli --env API_TOKEN=${API_TOKEN} --env CONTEXT7_API_KEY=${CONTEXT7_API_KEY} -- npx -y @agents-dev/[email protected]{
"mcpServers": {
"cli": {
"command": "npx",
"args": [
"-y",
"@agents-dev/[email protected]"
],
"env": {
"API_TOKEN": "${API_TOKEN}",
"CONTEXT7_API_KEY": "${CONTEXT7_API_KEY}"
}
}
}
}Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
search | read | Search things |
second | read | Second |
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 | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (3 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (9)
const SECRET = 'sk-live-committed-secret-0123456789'
const hash = createHash('sha1').update(path.resolve(projectRoot)).digest('hex').slice(0, 12)const secretFile = path.join(outside, 'id_rsa')
await writeFile(path.join(outside, 'id_rsa'), 'PRIVATE-KEY-CONTENT\n', 'utf8')
await symlink(path.join(outside, 'id_rsa'), path.join(shared, 'leak.txt'))
const TEMPLATE_ROOT = path.resolve(__dirname, '../../templates/agents')
const pkg = require('../../package.json') as { version?: unknown }return `http://127.0.0.1:${String(address.port)}/mcp`@clack/prompts, @iarna/toml, commander, jsonc-parser, picocolors, yaml, @types/node, @typescript-eslint/eslint-plugin
Gates applied: no_behavioural_pass.
024d27681b42full audit observations/trust-audit/mcp-server/amtiyo__agents.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 |
|---|---|---|---|---|---|
| 2026-10-12 | 024d27681b42 | SAFE | B | 89 | first audit |
Questions
What is the @agents-dev/cli MCP server?
One .agents source of truth to sync MCP servers, skills, and instructions across Codex, Claude Code, Gemini CLI, Cursor, Copilot, and Antigravity.
What tools does @agents-dev/cli expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is @agents-dev/cli 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 @agents-dev/cli need?
It reads API_TOKEN and CONTEXT7_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 @agents-dev/cli run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as @agents-dev/cli at 0.9.1.
How current is this page?
The grade is for one exact copy of the source (024d27681b42), read on 2026-10-12. The repository is watched and re-audited when it changes.