AgentAtlas MCP server
io.github.zachhhhh/agentatlaszachhhhhstreamable-httpv1.2.0Scanned
Sourced setup answers, MCP config for 15 clients and trending agent repos.
6 tools: 6 only read.
- Reads private data · 3
- Reads text others write · 1
- Can send data out · 0
- No findings
Sign-in required, no OAuth metadata. Remote posture
Anlyon alternative
Run the operations that matter as governed actions.
Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.
Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.
Import an OpenAPI spec →What the AgentAtlas MCP server can do
The AgentAtlas MCP server is published by the GitHub account zachhhhh. It has 6 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
3 tools read private data (get_guide, get_setup_config and get_trending); 1 tool brings in text other people can write (get_trending).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Last scanned Nov 6, 2026, version 1.2.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
6 tools
Only reads 6Show 6 read-only tools
get_guideGet a full sourced setup guide (settings, commands, config files) by slug, as Markdown with source links.Reads private dataNo findings
Why it is in this group
- The name "get_guide" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "file": it reads files.
Description, as the server wrote it Get a full sourced setup guide (settings, commands, config files) by slug, as Markdown with source links.
Annotations the server declares
- readOnlyHint: true
get_mcp_serverGet install commands for Claude Code, Codex, Gemini CLI, Cursor and VS Code, plus tools and auth details, for an official MCP server by slug.No findings
Why it is in this group
- The name "get_mcp_server" says "get": a word for reading.
Description, as the server wrote it Get install commands for Claude Code, Codex, Gemini CLI, Cursor and VS Code, plus tools and auth details, for an official MCP server by slug.
Annotations the server declares
- readOnlyHint: true
get_pricingGet coding agent plans and prices copied from vendor pricing pages.No findings
Why it is in this group
- The name "get_pricing" says "get": a word for reading.
Description, as the server wrote it Get coding agent plans and prices copied from vendor pricing pages. Optional harness slug, e.g. 'cursor' or 'claude-code'.
Annotations the server declares
- readOnlyHint: true
get_setup_configGet ready-to-write MCP config for one client and one or more official MCP servers, with the file path to write it to.Reads private dataNo findings
Why it is in this group
- The name "get_setup_config" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "get" and "file": it reads files.
Description, as the server wrote it Get ready-to-write MCP config for one client and one or more official MCP servers, with the file path to write it to. Clients: claude-code, claude-code-cli, cursor, vs-code, codex, gemini-cli, antigravity, copilot-cli, claude-desktop, opencode, cline, kiro, zed, devin-desktop, amp. Use search_atlas (type mcp_server) to find server slugs.
Annotations the server declares
- readOnlyHint: true
get_trendingWhat is trending in AI agents: fastest-rising new agent and MCP repos on GitHub, stars gained by tracked agent projects, most-discussed agent posts on Hacker News, and verified acc…Reads private dataReads text others writeNo findings
Why it is in this group
- The name "get_trending" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "repo": it reads repositories.
- untrusted-inputThe description's first sentence says "post": it reads posts, which other people can write.
Description, as the server wrote it What is trending in AI agents: fastest-rising new agent and MCP repos on GitHub, stars gained by tracked agent projects, most-discussed agent posts on Hacker News, and verified accounts to follow.
Annotations the server declares
- readOnlyHint: true
search_atlasSearch AgentAtlas, the verified map of the AI agent stack: setup guides for coding agents (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more), official MCP servers, plugin s…No findings
Why it is in this group
- The name "search_atlas" says "search": a word for reading.
Description, as the server wrote it Search AgentAtlas, the verified map of the AI agent stack: setup guides for coding agents (Claude Code, Codex, Cursor, Gemini CLI, Copilot and more), official MCP servers, plugin systems, eval frameworks, agent benchmarks and protocols. Every entry is sourced from vendor docs.
Annotations the server declares
- readOnlyHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data3
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 19:13 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 405
- tools/list served without credentials
- no
- Tools that change things, listed without credentials
- 0
- Protocol version
- not observed
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
The probe stopped: initialize answered HTTP 405.
Posture changes
- Nov 20, 2026
- HTTP status of an anonymous initialize: 402 to 405
- Nov 13, 2026
- HTTP status of an anonymous initialize: 200 to 402
- tools/list served without credentials: yes to no
- Protocol version: 2025-06-18 to none
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. HTTP status of an anonymous initialize: 402 -> 405.View diff
- HTTP status of an anonymous initialize: 402 to 405
PostureRemote posture changed. HTTP status of an anonymous initialize: 200 -> 402; tools/list served without credentials: yes -> no; Protocol version: 2025-06-18 -> none.View diff
- HTTP status of an anonymous initialize: 200 to 402
- tools/list served without credentials: yes to no
- Protocol version: 2025-06-18 to none
Install
Pinned to version 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http agentatlas https://agentatlas.dev/api/mcpclaude mcp add --transport http agentatlas https://agentatlas.dev/api/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__agentatlas__search_atlas",
"mcp__agentatlas__get_guide",
"mcp__agentatlas__get_mcp_server",
"mcp__agentatlas__get_pricing",
"mcp__agentatlas__get_setup_config",
"mcp__agentatlas__get_trending"
],
"ask": [],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as agentatlas. Review it before you use it.
Capability tags behind 3 rules
- mcp__agentatlas__get_guide private-data
- mcp__agentatlas__get_setup_config private-data
- mcp__agentatlas__get_trending private-data, untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.zachhhhh/agentatlas/verify?hash=3b42dd3a292a9427de815d03f38dc6670082982596ac2590728c7e4655cb4cdf" | jq -e '.changed == false'Pinned hash 3b42dd3a292a, from Nov 6, 2026, 17:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.zachhhhh/agentatlas/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.zachhhhh/agentatlas)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:52 UTC.
AgentAtlas MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AgentAtlas MCP server safe?
- No scan can promise that. What its definitions show: 6 tools, all of which only read, and 0 findings from fixed checks. Read-only tools can still pass private data to a model.
Can the AgentAtlas MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AgentAtlas MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the AgentAtlas MCP server have?
- 6 tools: 6 read. search_atlas, get_guide, get_mcp_server, get_pricing, get_setup_config and get_trending.
Does the AgentAtlas MCP server need sign-in or OAuth?
- Its remote endpoint did not answer the last anonymous look.
Does the AgentAtlas MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the AgentAtlas MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 6, 2026.