Vynix MCP server
in.vynix/vynix-mcpvynix.instreamable-httpv0.1.4Scanned
Give AI coding agents access to your Vynix visual feedback, bug reports, and AI diagnosis.
17 tools: 6 change things and 11 only read.
- Reads private data · 2
- Reads text others write · 6
- Can send data out · 2
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
6 tools here change things. Govern them.
- 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 Vynix MCP server can do
The Vynix MCP server is published by vynix.in, a domain the MCP Registry verified. It has 17 tools. It can create or change data (6 tools: generate_prompt, update_annotation_status, add_comment, diagnose_annotation and 2 more), but cannot delete data. 11 tools only read.
2 tools read private data (list_comments and get_annotation_analysis); 6 tools bring in text other people can write (list_comments, list_annotation_issues, list_project_issues and 3 more); 2 tools can send data out of your system (add_comment and create_github_issue). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way 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 11, 2026, version 0.1.4.
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.
17 tools
Changes things 6Claude Code: ask
add_commentAdd a comment to an annotation’s thread, e.g.Can send data outNo findings
Why it is in this group
- The name "add_comment" says "add": a word for a change.
What it can reach
- outboundThe name "add_comment" says "add" and "comment": it writes something other people read.
Description, as the server wrote it Add a comment to an annotation’s thread, e.g. to record what you changed. Notifies the team.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: false
create_github_issueCreate a GitHub issue from an annotation.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "create_github_issue" says "create": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- outboundThe name "create_github_issue" says "create" and "issue": it writes something other people read.
Description, as the server wrote it Create a GitHub issue from an annotation. Uses the project’s configured repo and assignee unless overridden. Embeds the generated AI prompt in the issue body.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
diagnose_annotationRun the AI Diagnosis Engine on an annotation: it analyses the captured page, element, DOM, and runtime errors to produce ranked root causes, a confidence score, a suggested fix, an…Reads text others writeNo findings
Why it is in this group
- The description's first verb is "run": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Run the AI Diagnosis Engine on an annotation: it analyses the captured page, element, DOM, and runtime errors to produce ranked root causes, a confidence score, a suggested fix, and the likely source files. Calls an AI provider (uses tokens / may cost money) and stores the result. Requires AI + diagnosis enabled by the workspace admin and a key set.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
generate_promptRender a ready-to-paste coding prompt for an annotation, formatted for a target assistant.1 finding
Why it is in this group
- The name "generate_prompt" says "generate": 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 "generate_prompt" 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 "generate_prompt" says "generate": a word for a change.
Description, as the server wrote it Render a ready-to-paste coding prompt for an annotation, formatted for a target assistant. A deterministic template (no AI spend); for a deeper analysis use diagnose_annotation.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
update_annotation_statusUpdate an annotation’s status, e.g.No findings
Why it is in this group
- The name "update_annotation_status" says "update": a word for a change.
Description, as the server wrote it Update an annotation’s status, e.g. to mark it in_progress or completed.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
Only reads 11Show 11 read-only tools
get_activityRecent activity feed for a project (status changes, comments, issues, members).Reads text others writeNo findings
Why it is in this group
- The name "get_activity" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "comment": it reads comments, which other people can write.
Description, as the server wrote it Recent activity feed for a project (status changes, comments, issues, members).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_annotationFetch one annotation with its full captured context: page, target element (selector, XPath, styles), surrounding DOM, and runtime diagnostics (console + network).No findings
Why it is in this group
- The name "get_annotation" says "get": a word for reading.
Description, as the server wrote it Fetch one annotation with its full captured context: page, target element (selector, XPath, styles), surrounding DOM, and runtime diagnostics (console + network).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_annotation_analysisRead the latest stored AI diagnosis for an annotation (root causes, confidence, suggested fix, and likely source files).Reads private dataNo findings
Why it is in this group
- The name "get_annotation_analysis" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "file": it reads files.
Description, as the server wrote it Read the latest stored AI diagnosis for an annotation (root causes, confidence, suggested fix, and likely source files). Returns null when none has been generated yet; run diagnose_annotation to create one.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_annotation_screenshotsReturn the region screenshots attached to an annotation as viewable images, so you can see exactly what the reporter pointed at.No findings
Why it is in this group
- The name "get_annotation_screenshots" says "get": a word for reading.
Description, as the server wrote it Return the region screenshots attached to an annotation as viewable images, so you can see exactly what the reporter pointed at.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
get_metricsOverview of your projects: KPI counts, status breakdown, a daily time series, and recent activity.No findings
Why it is in this group
- The name "get_metrics" says "get": a word for reading.
Description, as the server wrote it Overview of your projects: KPI counts, status breakdown, a daily time series, and recent activity.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_annotation_issuesList the tracker (GitHub) issues opened from an annotation, with each issue’s live state.Reads text others writeNo findings
Why it is in this group
- The name "list_annotation_issues" says "list": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe name "list_annotation_issues" says "list" and "issue": it reads issues, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "issue": it reads issues, which other people can write.
Description, as the server wrote it List the tracker (GitHub) issues opened from an annotation, with each issue’s live state. Set refresh to reconcile against GitHub (open/closed + any linked pull request).
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: true
list_annotationsList a project’s annotations, optionally filtered by status, type, or priority.No findings
Why it is in this group
- The name "list_annotations" says "list": a word for reading.
Description, as the server wrote it List a project’s annotations, optionally filtered by status, type, or priority. Start here with status "open" to see what needs fixing.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_commentsRead the discussion thread on an annotation.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "list_comments" says "list": a word for reading.
What it can reach
- private-dataThe description's first sentence says "read" and "thread": it reads messages.
- untrusted-inputThe name "list_comments" says "list" and "comment": it reads comments, which other people can write.
- untrusted-inputThe description's first sentence says "read" and "discussion": it reads comments, which other people can write.
Description, as the server wrote it Read the discussion thread on an annotation.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_membersList a project’s team members, including role and status.No findings
Why it is in this group
- The name "list_members" says "list": a word for reading.
Description, as the server wrote it List a project’s team members, including role and status.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_project_issuesList every tracker issue across a project, with an open/closed/agent summary.Reads text others writeNo findings
Why it is in this group
- The name "list_project_issues" says "list": a word for reading.
What it can reach
- untrusted-inputThe name "list_project_issues" says "list" and "issue": it reads issues, which other people can write.
- untrusted-inputThe description's first sentence says "list" and "issue": it reads issues, which other people can write.
Description, as the server wrote it List every tracker issue across a project, with an open/closed/agent summary.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- openWorldHint: false
list_projectsList the Vynix projects you own.No findings
Why it is in this group
- The name "list_projects" says "list": a word for reading.
Description, as the server wrote it List the Vynix projects you own.
Annotations the server declares
- 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.
24 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 2 outbound tools breaks every one.
- Reads private data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write6
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__vynix__add_comment",
"mcp__vynix__create_github_issue"
]
}
}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, 18:55 UTC, unchanged since Oct 22, 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
- 6
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://mcp.vynix.in/.well-known/oauth-protected-resource
- Authorization servers
- https://mcp.vynix.in
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 6 tools that change things (6 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.vynix.in/mcp: tools/list returned 17 tools to an anonymous client, including generate_prompt (write), update_annotation_status (write), add_comment (write), diagnose_annotation (write), create_github_issue (write) and 1 more
Findings
Matches of fixed checks, with the text they matched.
- Warngenerate_prompt
The server marks "generate_prompt" 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 "generate_prompt" says "generate": 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 0.1.4. Values in angle brackets are yours to fill in.
claude mcp add --transport http vynix https://mcp.vynix.in/mcpclaude mcp add --transport http vynix https://mcp.vynix.in/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__vynix__list_projects",
"mcp__vynix__list_annotations",
"mcp__vynix__get_annotation",
"mcp__vynix__list_comments",
"mcp__vynix__get_annotation_analysis",
"mcp__vynix__get_annotation_screenshots",
"mcp__vynix__list_annotation_issues",
"mcp__vynix__list_project_issues",
"mcp__vynix__get_metrics",
"mcp__vynix__list_members",
"mcp__vynix__get_activity"
],
"ask": [
"mcp__vynix__generate_prompt",
"mcp__vynix__update_annotation_status",
"mcp__vynix__add_comment",
"mcp__vynix__diagnose_annotation",
"mcp__vynix__create_github_issue",
"mcp__vynix__create_share_link"
],
"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 vynix. Review it before you use it.
Capability tags behind 8 rules
- mcp__vynix__list_comments private-data, untrusted-input
- mcp__vynix__get_annotation_analysis private-data
- mcp__vynix__list_annotation_issues untrusted-input
- mcp__vynix__list_project_issues untrusted-input
- mcp__vynix__get_activity untrusted-input
- mcp__vynix__add_comment outbound
- mcp__vynix__diagnose_annotation untrusted-input
- mcp__vynix__create_github_issue untrusted-input, outbound
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/in.vynix/vynix-mcp/verify?hash=4f7f3dfb8fa51437f697d7864e1eb932aad2775c0375646ba38ad06036a482c8" | jq -e '.changed == false'Pinned hash 4f7f3dfb8fa5, from Nov 11, 2026, 14:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/in.vynix/vynix-mcp/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/in.vynix/vynix-mcp)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:13 UTC.
Vynix MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Vynix MCP server safe?
- No scan can promise that. What its definitions show: 17 tools, 6 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 Vynix MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Vynix 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 Vynix MCP server have?
- 17 tools: 6 write, 11 read. generate_prompt, update_annotation_status, add_comment, diagnose_annotation, create_github_issue, create_share_link, list_projects, list_annotations and 9 more.
Does the Vynix MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Vynix MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): add_comment and create_github_issue.
Has the Vynix MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 11, 2026.