Skip to content
StealthStack logo

StealthStack MCP server

Which MCP servers are StealthStack'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 2026-10-23

← Back to StealthStack

Whose server it is
  • Registry nameai.stealthstack/discoveryverified in the MCP registry

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

When we asked itchecked 2026-10-23
  • Stateanswerschecked 2026-10-23
  • Tools3
  • Server calls itselfstealthstack-discovery
  • Server version0.2.0
  • Protocol version2025-06-18

On 2026-10-23 the server answered initialize and tools/list without a sign-in. First answer in 314 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 5 of the 7 days it takes to judge reliability.

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: 5, the first on 2026-10-24
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 5 so far
  • Answeredmeasuring5 of the 7 daily checks it takes to print a share
  • Median first answer437 ms
  • Space in an agent's context≈ 1,053 tokensthe definitions of all its tools (3), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results3 of 3 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • not sure · Browse agent tools by business category
  • not sure · Verify a tool's publisher domain before connecting
  • not sure · Search the tool index from Claude Code over MCP

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 offers3 tools · read 2026-10-23
  • search_resources

    Search the StealthStack ARD index for agentic resources (agents, MCP servers, skills, catalogs) discovered across the open web. Free-text query over name/description/tags, ranked by the index's relevance score (best match first)…

  • list_resources

    Browse the StealthStack ARD index — agentic resources (agents, MCP servers, skills, catalogs) discovered across the open web. Optionally filter by kind, domain, trust, or accepted payment protocol (paid=x402). Returns a count, a kind…

  • get_resource

    Get the full record for one discovered ARD resource by its identifier (URN), as returned by search_resources / list_resources. Includes the connect URL when the publisher provides one; otherwise the inline connection or pull details. Also…

How to connect

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

{
  "mcpServers": {
    "discovery": {
      "type": "http",
      "url": "https://stealthstack.ai/mcp?src=mcpregistry"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http stealthstack https://stealthstack.ai/mcp?src=mcpregistry

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://stealthstack.ai/mcp?src=mcpregistry as a custom connector in the settings.

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.