Context Atlas MCP server
io.github.levin-staudt/contextatlaslevin-staudtstreamable-httpv1.0.0Scanned
Find llms.txt, docs, MCP servers, skills and CLIs for a tech stack, for coding agents.
3 tools: 3 only read.
- Reads private data · 1
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
Decide which of this server's tools your agent can use.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Context Atlas MCP server can do
The Context Atlas MCP server is published by the GitHub account levin-staudt. It has 3 tools. Every one of them only reads: going by their definitions, none of them creates, changes, sends or deletes anything.
1 tool reads private data (get_topic).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 8, 2026, version 1.0.0.
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.
3 tools
Only reads 3Show 3 read-only tools
get_topicAll sources (llms.txt, docs, MCP servers, skills, rules), detection signals and the role of one tool, by id such as `vercel`, `nextjs` or `drizzle`.Reads private dataNo findings
Why it is in this group
- The name "get_topic" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "doc": it reads documents.
Description, as the server wrote it All sources (llms.txt, docs, MCP servers, skills, rules), detection signals and the role of one tool, by id such as `vercel`, `nextjs` or `drizzle`.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
list_topicsEvery tool in the catalog with its id, name, role and region, without sources.No findings
Why it is in this group
- The name "list_topics" says "list": a word for reading.
Description, as the server wrote it Every tool in the catalog with its id, name, role and region, without sources. Use it to find candidates per role, then get_topic and their llms.txt sources to compare them.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
searchFull-text search over tools (topics) and their sources.No findings
Why it is in this group
- The name "search" says "search": a word for reading.
Description, as the server wrote it Full-text search over tools (topics) and their sources. Matches names, roles, regions, detection signals (files, dependencies, env vars), source titles and URLs. Every word must match, as a prefix.
Annotations the server declares
- readOnlyHint: true
- openWorldHint: false
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 untrusted-input or outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- 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 15, 2026, 13:22 UTC, unchanged since Oct 24, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 0
- Protocol version
- 2025-06-18
- 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
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.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http contextatlas https://contextatlas.dev/mcpclaude mcp add --transport http contextatlas https://contextatlas.dev/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__contextatlas__search",
"mcp__contextatlas__get_topic",
"mcp__contextatlas__list_topics"
],
"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 contextatlas. Review it before you use it.
Capability tags behind 1 rule
- mcp__contextatlas__get_topic private-data
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.levin-staudt/contextatlas/verify?hash=5842ff4d15de11f35acd0e2ce03725d241c4cdba01b170ad43ddc26e3449197d" | jq -e '.changed == false'Pinned hash 5842ff4d15de, from Nov 8, 2026, 22:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.levin-staudt/contextatlas/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.levin-staudt/contextatlas)Source: MCP Registry · repository. Synced Oct 23, 2026, 22:17 UTC.
Context Atlas MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Context Atlas MCP server safe?
- No scan can promise that. What its definitions show: 3 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 Context Atlas MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Context Atlas 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 Context Atlas MCP server have?
- 3 tools: 3 read. search, get_topic and list_topics.
Does the Context Atlas MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Context Atlas MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Context Atlas MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 8, 2026.