StealthStack ARD Discovery

Browse the index by kind or source

list_resources

Read-onlyIdempotent

Browse the StealthStack index without a search query: for example every agent skill (kind=skill), everything one domain publishes (domain=...), or services that accept x402 payments (paid=x402). Returns the total, a count per kind and one page of records with connect details. For a specific need ("MCP server for Postgres") use search_resources, which ranks by relevance.

Input Schema

Name	Required	Description
`kind`	No	Optional. Only one kind: mcp (MCP server), skill (agent skill, SKILL.md), agent (A2A agent), api (HTTP / OpenAPI service), catalog or registry (lists of more resources), other. Omit to include every kind.
`paid`	No	Optional. x402 = only services that list x402 pay-per-request pricing (stablecoins). A filter, not a ranking.
`limit`	No	Optional. Number of results, 1-50 (default 25).
`trust`	No	Optional. verified = the record's URN names the same domain that hosts its catalog. It shows where the record was published, not that anyone reviewed the resource.
`domain`	No	Optional. Only resources from this source domain, e.g. "stealthstack.ai".

Output Schema

Name	Required	Description	Default
`total`	Yes
`byKind`	No
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed8 schema fields changedOct 27, 2026

changedInput schema / properties / domain / description

Previous value: -"Restrict to one publisher domain (e.g. stealthstack.ai)."New value: +"Optional. Only resources from this source domain, e.g. \"stealthstack.ai\"."

changedInput schema / properties / kind / description

Previous value: -"Restrict to one resource kind."New value: +"Optional. Only one kind: mcp (MCP server), skill (agent skill, SKILL.md), agent (A2A agent), api (HTTP / OpenAPI service), catalog or registry (lists of more resources), other. Omit to include every kind."

changedInput schema / properties / limit / description

Previous value: -"Max results (1-50)."New value: +"Optional. Number of results, 1-50 (default 25)."

changedInput schema / properties / paid / description

Previous value: -"Only services that list this payment protocol (x402: pay-per-request in stablecoins). A filter, never a ranking."New value: +"Optional. x402 = only services that list x402 pay-per-request pricing (stablecoins). A filter, not a ranking."

changedInput schema / properties / trust / description

Previous value: -"Restrict by trust status."New value: +"Optional. verified = the record's URN names the same domain that hosts its catalog. It shows where the record was published, not that anyone reviewed the resource."

addedOutput schema / properties / results / items / properties / access

Added value: +{
+  "description": "What is known about auth and pricing. requiresAuth comes from the MCP Registry entry; auth and pricing are StealthStack's automated labels (unknown values omitted).",
+  "properties": {
+    "auth": {
+      "type": "string"
+    },
+    "pricing": {
+      "type": "string"
+    },
+    "requiresAuth": {
+      "type": "boolean"
+    }
+  },
+  "type": "object"
+}

addedOutput schema / properties / results / items / properties / install

Added value: +{
+  "description": "Packages to install the server from (MCP Registry entries). `command` is a ready-to-run start command (npx / uvx / docker / cargo), present only when the package name passes a strict charset check.",
+  "items": {
+    "properties": {
+      "command": {
+        "type": "string"
+      },
+      "env": {
+        "description": "Required environment variable names the package lists (names only).",
+        "items": {
+          "type": "string"
+        },
+        "type": "array"
+      },
+      "package": {
+        "type": "string"
+      },
+      "registry": {
+        "type": "string"
+      },
+      "transport": {
+        "type": "string"
+      },
+      "version": {
+        "type": "string"
+      },
+      "versionRejected": {
+        "description": "The listed version failed validation; `command` is not pinned to it.",
+        "type": "boolean"
+      }
+    },
+    "required": [
+      "registry",
+      "package"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

addedOutput schema / properties / results / items / properties / repository

Added value: +{
+  "description": "Source repository URL (https), as listed.",
+  "type": "string"
+}

Changed2 schema fields changedOct 7, 2026

addedInput schema / properties / paid

Added value: +{
+  "description": "Only services that list this payment protocol (x402: pay-per-request in stablecoins). A filter, never a ranking.",
+  "enum": [
+    "x402"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / results / items / properties / payment

Added value: +{
+  "description": "Payment terms the service lists (x402): protocol, lowest listed price + currency, network (CAIP-2). Self-declared; never a payee address.",
+  "properties": {
+    "currency": {
+      "type": "string"
+    },
+    "network": {
+      "type": "string"
+    },
+    "price": {
+      "type": "string"
+    },
+    "protocol": {
+      "type": "string"
+    },
+    "testnet": {
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "protocol"
+  ],
+  "type": "object"
+}

First observedSep 27, 2026

TDQS

A4.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and open-world, so safety is covered. The description adds real behavioral context: the response includes a total, a per-kind count, and exactly one page of records with connect details, which tells the agent results are paginated rather than exhaustive. It stops short of naming a pagination cursor or rate limits, so it is strong but not complete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero filler: the scope and examples come first, the sibling routing comes second. Every clause carries information the agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With five optional parameters, an output schema, and full annotation coverage, the remaining risk is ambiguity about the tool's role versus search. The description closes that gap explicitly and even sketches the response shape, so nothing material is missing for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description goes beyond the enum definitions by mapping filters to intents — 'every agent skill (kind=skill)', 'everything one domain publishes (domain=...)', 'services that accept x402 payments (paid=x402)'. That gives the agent a mental model for combining filters, though it omits trust and limit.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Browse the StealthStack index') and immediately scopes it as query-less, with three concrete filter axes (kind, domain, paid). It explicitly contrasts with the sibling search_resources, so an agent can pick between them without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives both directions: use this for open-ended browsing by kind/domain/payment type, and use search_resources for a specific need like 'MCP server for Postgres' because that one ranks by relevance. The selection condition is explicit and unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All StealthStack ARD Discovery tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?