AtomicViz Diagrams MCP server
com.atomicviz/diagramsatomicviz.comstreamable-httpv1.2.0Scanned
Interactive diagrams you can collapse, regroup and focus: architecture, dependencies, org charts
1 tool: 1 change things.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here changes things. Govern it.
- 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 AtomicViz Diagrams MCP server can do
The AtomicViz Diagrams MCP server is published by atomicviz.com, a domain the MCP Registry verified. It has 1 tool. It can create or change data (1 tool: create_diagram), but cannot delete data. None of its tools only reads.
None of its tools reads private data, brings in text other people write, or sends data out.
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 21, 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.
1 tool
Changes things 1Claude Code: ask
create_diagramCreates an interactive diagram in the conversation from nodes and edges you supply.1 finding
Why it is in this group
- The name "create_diagram" says "create": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
The server marks "create_diagram" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "create_diagram" says "create": a word for a change.
Description, as the server wrote it Creates an interactive diagram in the conversation from nodes and edges you supply. Use it when the user asks to draw, diagram, map or visualize how the parts of something relate: system architecture, services and the calls between them, data models, dependency trees, workflows, organizations, knowledge maps. Not for charts of numeric data. In the diagram the user can collapse and expand boxes, regroup at each level of nesting, focus on an item and what connects to it, show clusters and cycles, and search, hide and export. The server checks the diagram and stores nothing. STRUCTURE: every node has a unique 'id'. A node with no 'parent' is drawn as a box of its own; a node WITH a 'parent' is drawn as a ROW inside its parent's box (an endpoint inside a service, a column inside a table) and the parent can be collapsed. 'group' (top-level nodes only) draws a labelled boundary around nodes, nested with '/': 'AWS/VPC' puts the node in a VPC box inside an AWS box. If you use groups, give EVERY top-level node a group: the views that draw groups as closed or stacked boxes are offered only when no node is left out. Edges run between any two nodes, rows included; give an edge a short 'label' only when the relation is not obvious ('HTTPS', 'publishes'). Optional per node: 'description' (shown on hover; add one only where the label is not enough), 'link' (an https URL, opened on double-click), 'color', 'kind': 'field' for an attribute-style row, 'collapsed': true to start folded. Optional per edge: 'color', 'style' ('dashed' for async or optional, 'dotted' for weak). Keep it legible: prefer grouping and nesting over hundreds of top-level boxes; use color for a category, not decoration.
Annotations the server declares
- title: Create an interactive diagram
- readOnlyHint: true
- destructiveHint: false
- 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 private-data or untrusted-input or outbound.
- Reads private data0
- 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 21, 2026, 19:18 UTC, unchanged since Nov 21, 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
- 1
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://atomicviz.com/mcp: tools/list returned 1 tool to an anonymous client, including create_diagram (write)
Findings
Matches of fixed checks, with the text they matched.
- Warncreate_diagram
The server marks "create_diagram" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
What this check looks forMatched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"openWorldHint":false}; The name "create_diagram" says "create": a word for a change.
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 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http diagrams https://atomicviz.com/mcpclaude mcp add --transport http diagrams https://atomicviz.com/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": [],
"ask": [
"mcp__diagrams__create_diagram"
],
"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 diagrams. Review it before you use it.
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/com.atomicviz/diagrams/verify?hash=6c9a4f037abbaee4ec9fe65efebb781e36e5615766136ddeaaf5834d554a2865" | jq -e '.changed == false'Pinned hash 6c9a4f037abb, from Nov 21, 2026, 05:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.atomicviz/diagrams/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.atomicviz/diagrams)Source: MCP Registry · repository. Synced Nov 21, 2026, 05:17 UTC.
AtomicViz Diagrams MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the AtomicViz Diagrams MCP server safe?
- No scan can promise that. What its definitions show: 1 tool, 1 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the AtomicViz Diagrams MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the AtomicViz Diagrams 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 AtomicViz Diagrams MCP server have?
- 1 tool: 1 write. create_diagram.
Does the AtomicViz Diagrams MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the AtomicViz Diagrams MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the AtomicViz Diagrams MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 21, 2026.