@proof-holdings/mcp-server

Official

Overview Schema Source Related Servers Discussions Admin

get_dns_providers

Read-only

Retrieve metadata for supported DNS providers, including required credential fields and documentation links, to configure DNS verification in Proof.

Instructions

Get metadata for all supported DNS providers, including required credential fields and documentation links.

ACCESS: needs a Proof account. Set PROOF_API_KEY and restart this server, or sign in with start_login — a session opens this tool — then call this tool again.

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description	Default
`count`	Yes	How many providers are supported. A supported provider with no metadata on record is counted here but not listed in `providers`.
`providers`	Yes	Each supported provider with metadata on record, keyed by provider id

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.7.2Nov 6, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "description": "The DNS providers credentials can be saved for",
+  "properties": {
+    "count": {
+      "description": "How many providers are supported. A supported provider with no metadata on record is counted here but not listed in `providers`.",
+      "maximum": 9007199254740991,
+      "minimum": -9007199254740991,
+      "type": "integer"
+    },
+    "providers": {
+      "additionalProperties": {
+        "additionalProperties": {},
+        "properties": {
+          "apiDocUrl": {
+            "type": "string"
+          },
+          "capabilities": {
+            "additionalProperties": {},
+            "properties": {
+              "canCreateTxt": {
+                "type": "boolean"
+              },
+              "hasOAuth": {
+                "type": "boolean"
+              },
+              "isRegistrar": {
+                "type": "boolean"
+              }
+            },
+            "required": [
+              "hasOAuth",
+              "isRegistrar",
+              "canCreateTxt"
+            ],
+            "type": "object"
+          },
+          "name": {
+            "type": "string"
+          },
+          "optionalCredentials": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "requiredCredentials": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          }
+        },
+        "required": [
+          "name",
+          "requiredCredentials",
+          "optionalCredentials",
+          "capabilities"
+        ],
+        "type": "object"
+      },
+      "description": "Each supported provider with metadata on record, keyed by provider id",
+      "properties": {},
+      "type": "object"
+    }
+  },
+  "required": [
+    "providers",
+    "count"
+  ],
+  "type": "object"
+}

First observedv1.1.0Sep 9, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations only declare readOnlyHint=true, so the description earns credit for disclosing the authentication requirement (Proof account, PROOF_API_KEY environment variable with a server restart, or a start_login session) and the fact that the tool must be re-invoked after signing in. With an output schema present, it is fair that return values are not enumerated; only the absence of any note about result volume or refresh behavior keeps this below 5.

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?

A single purpose sentence followed by a clearly labeled ACCESS block; every sentence carries information the agent needs, and the access constraint is separated visually rather than buried mid-paragraph.

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

Completeness4/5

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

For a zero-argument read tool with an output schema and readOnlyHint, the description covers purpose and the one real complication, authentication. It stops short of telling the agent what the natural next tool is (connect_dns_provider / create_dns_credential) in this very large sibling set.

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?

The tool takes zero parameters, so there is no parameter semantics to document and the baseline of 4 applies. The description correctly implies the call is unfiltered metadata retrieval.

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

Purpose4/5

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

The description gives a specific verb and resource ('Get metadata for all supported DNS providers') and even enumerates the payload fields returned (credential fields, documentation links). It never distinguishes itself from neighboring tools such as connect_dns_provider, connect_cloudflare, or create_dns_credential, so an agent must infer that this is the discovery step.

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

Usage Guidelines3/5

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

Access prerequisites are spelled out, and the description explicitly routes an unauthenticated caller to start_login, which is genuine when-to-use guidance. However, it says nothing about when to call this versus the credential-creating or provider-connecting siblings, so the sequencing guidance is only implied.

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

Deploy Server