Skip to content

UND Assay MCP server

Which MCP servers are UND Assay's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-31

← Back to UND Assay

Whose server it is
  • Registry namecom.undassay/und-assayverified in the MCP registry

The registry name sits under undassay.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-31
  • Stateanswerschecked 2026-10-31
  • Tools8
  • Server calls itselfund-assay
  • Server version0.12.0
  • Protocol version2025-06-18

On 2026-10-31 the server answered initialize and tools/list without a sign-in. First answer in 157 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: check who publishes an MCP server before installing it; compare what changed between a tool's published versions; spot look-alike names impersonating real tools.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • For "check who publishes an MCP server before installing it", the likely first call is check_before_install.
  • For "compare what changed between a tool's published versions", the likely first call is get_changes.
  • For "spot look-alike names impersonating real tools", the likely first call is resolve_identifier.
  • Parameters are untyped or undescribed in 6 of 8 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-10-31
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer129 ms
  • Space in an agent's context≈ 893 tokensthe definitions of all its tools (8), which an agent carries on every turn
  • Tool definitionsB · 88 of 100
  • Typed results0 of 8 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 6 of 8

What an agent can do with it

  • can do · check who publishes an MCP server before installing it
  • can do · compare what changed between a tool's published versions
  • can do · spot look-alike names impersonating real tools

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers8 tools · read 2026-10-31
  • check_before_install

    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. No warnings is…

  • get_setup

    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…

  • resolve_identifier

    Resolve an MCP server name, catalog id or GitHub repository URL 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.

  • search_tools

    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…

  • get_tool

    Every assertion for a tool with its state (VERIFIED, CLAIMED, CONTRADICTED, STALE, UNKNOWN), reason, check and evidence records.

  • get_publisher

    How a publisher is identified across ecosystems (MCP namespace, domain, GitHub, packages) and the state of each link.

  • get_changes

    Metadata changes between consecutive published versions: new network hosts, replaced or added artifact sources, newly requested credentials.

  • get_evidence

    A single assertion of a tool (by field name) with the evidence records behind it: URL, fetch time, SHA-256.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "und-assay": {
      "type": "http",
      "url": "https://undassay.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http undassay https://undassay.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://undassay.com/mcp as a custom connector in the settings.

OpenAPI spec

10 paths, read 2026-10-31. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.