UND Assay MCP server
com.undassay/und-assayundassay.comstreamable-httpv0.13.0Scanned
Evidence on MCP servers before you install: publisher, source, provenance, advisories, changes.
8 tools: 1 change things and 7 only read.
- Reads private data · 2
- Reads text others write · 3
- Can send data out · 0
- 2 findings
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 UND Assay MCP server can do
The UND Assay MCP server is published by undassay.com, a domain the MCP Registry verified. It has 8 tools. It can create or change data (1 tool: check_before_install), but cannot delete data. 7 tools only read.
2 tools read private data (resolve_identifier and get_changes); 3 tools bring in text other people can write (get_setup, resolve_identifier and get_evidence).
The fixed checks matched 2 findings (annotation-conflict and credentials-mention). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 15, 2026, version 0.13.0.
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.
8 tools
Changes things 1Claude Code: ask
check_before_installEvidence summary for an MCP server before you install or connect it: publisher identity level, provenance, known vulnerabilities, install scripts, maintenance, open warnings, check…1 finding
Why it is in this group
- The name "check_before_install" says "install": 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 "check_before_install" 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,"idempotentHint":true,"openWorldHint":false}; The name "check_before_install" says "install": a word for a change.
Description, as the server wrote it Evidence summary for an MCP server before you install or connect it: publisher identity level, provenance, known vulnerabilities, install scripts, maintenance, open warnings, checks that could not run, and recent changes. Pass installed (the servers already in use) to also get tool names this server shares with them, which an AI could call by mistake. No warnings is NOT a safety guarantee.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Check a tool before installing it
Only reads 7Show 7 read-only tools
get_changesMetadata changes between consecutive published versions: new network hosts, replaced or added artifact sources, newly requested credentials.Reads private data1 finding
Why it is in this group
- The name "get_changes" says "get": a word for reading.
What it can reach
- private-dataThe description's first sentence says "credential": it reads secrets.
Findings
- Info
The description mentions "credentials".
What this check looks forMatched text
description: "...added artifact sources, newly requested credentials."
Description, as the server wrote it Metadata changes between consecutive published versions: new network hosts, replaced or added artifact sources, newly requested credentials.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: What changed between versions
get_evidenceA single assertion of a tool (by field name) with the evidence records behind it: URL, fetch time, SHA-256.Reads text others writeNo findings
Why it is in this group
- The name "get_evidence" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it A single assertion of a tool (by field name) with the evidence records behind it: URL, fetch time, SHA-256.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: One assertion with its evidence
get_publisherHow a publisher is identified across ecosystems (MCP namespace, domain, GitHub, packages) and the state of each link.No findings
Why it is in this group
- The name "get_publisher" says "get": a word for reading.
Description, as the server wrote it How a publisher is identified across ecosystems (MCP namespace, domain, GitHub, packages) and the state of each link.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Publisher identity
get_setupOne stable answer (schema_version 1) for connecting an MCP server: its validated remote URL and transport, packages, copy-paste setup for Claude Code and JSON configs, warnings by …Reads text others writeNo findings
Why it is in this group
- The name "get_setup" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
Description, as the server wrote it One stable answer (schema_version 1) for connecting an MCP server: its validated remote URL and transport, packages, copy-paste setup for Claude Code and JSON configs, warnings by severity, checks that could not run, and contradicted claims. auth is null until Assay has checked the sign-in metadata of the server. Never a safety rating.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: How to connect a tool
get_toolEvery assertion for a tool with its state (VERIFIED, CLAIMED, CONTRADICTED, STALE, UNKNOWN), reason, check and evidence records.No findings
Why it is in this group
- The name "get_tool" says "get": a word for reading.
Description, as the server wrote it Every assertion for a tool with its state (VERIFIED, CLAIMED, CONTRADICTED, STALE, UNKNOWN), reason, check and evidence records.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Full evidence for a tool
resolve_identifierResolve an MCP server name, catalog id, GitHub repository URL, or what a config file names (an npm or PyPI package, a container image, a hosted https address) to the real registry …Reads private dataReads text others writeNo findings
Why it is in this group
- The name "resolve_identifier" says "resolve": a word for reading.
What it can reach
- private-dataThe description's first sentence says "resolve" and "repository": it reads repositories.
- untrusted-inputThe description's first sentence says "resolve" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it Resolve an MCP server name, catalog id, GitHub repository URL, or what a config file names (an npm or PyPI package, a container image, a hosted https address) to the real registry entry. If there is no exact match, returns the closest real names so look-alikes and invented names can be caught. No account needed.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Does this tool really exist?
search_toolsSearch cataloged MCP servers by keywords.No findings
Why it is in this group
- The name "search_tools" says "search": a word for reading.
Description, as the server wrote it Search cataloged MCP servers by keywords. Returns classification (verified_publisher = the publisher proved control of a domain or verified GitHub org, NOT that a company named in the tool made it / community / not_analyzed), identity level and warning counts.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- title: Search tools
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 data2
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- 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, 13:21 UTC, unchanged since Oct 31, 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
- https://undassay.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://undassay.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- yes
- 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://undassay.com/mcp: tools/list returned 8 tools to an anonymous client, including check_before_install (write)
Findings
Matches of fixed checks, with the text they matched.
The server marks "check_before_install" 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,"idempotentHint":true,"openWorldHint":false}; The name "check_before_install" says "install": a word for a change.
- Infoget_changes
The description mentions "credentials".
What this check looks forMatched text
description: "...added artifact sources, newly requested credentials."
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools3 changed.~3 changedView diff
- Changed:check_before_installChanges thingsdescriptioninputSchema
- Changed:get_setupOnly readsinputSchema
- Changed:resolve_identifierOnly readsdescriptioninputSchema
Install
Pinned to version 0.13.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http und-assay https://undassay.com/mcpclaude mcp add --transport http und-assay https://undassay.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": [
"mcp__und-assay__get_setup",
"mcp__und-assay__resolve_identifier",
"mcp__und-assay__search_tools",
"mcp__und-assay__get_tool",
"mcp__und-assay__get_publisher",
"mcp__und-assay__get_changes",
"mcp__und-assay__get_evidence"
],
"ask": [
"mcp__und-assay__check_before_install"
],
"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 und-assay. Review it before you use it.
Capability tags behind 4 rules
- mcp__und-assay__get_setup untrusted-input
- mcp__und-assay__resolve_identifier private-data, untrusted-input
- mcp__und-assay__get_changes private-data
- mcp__und-assay__get_evidence 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/com.undassay/und-assay/verify?hash=0d4b6604d47145f598502878d1d12b65c65e34841fae069a53614a4793cbdfa9" | jq -e '.changed == false'Pinned hash 0d4b6604d471, from Nov 15, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.undassay/und-assay/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.undassay/und-assay)Source: MCP Registry. Synced Nov 2, 2026, 04:17 UTC.
UND Assay MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the UND Assay MCP server safe?
- No scan can promise that. What its definitions show: 8 tools, 1 of which can change, send or delete something, and 2 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the UND Assay MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the UND Assay 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 UND Assay MCP server have?
- 8 tools: 1 write, 7 read. check_before_install, get_setup, resolve_identifier, search_tools, get_tool, get_publisher, get_changes and get_evidence.
Does the UND Assay MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the UND Assay MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the UND Assay MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.