Payram

Diagnose a PayRam server

payram_doctor

Read-onlyIdempotent

Read-only diagnosis of a PayRam server by its public URL — works from the hosted MCP without credentials: reachability, health, TLS certificate, installed vs latest version, worker states. Optionally validates an API key without creating anything. Returns ranked likely causes and exact fixes for the first failing stage. Run this first when anything PayRam-related fails.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`apiKey`	No	Optional project API key to validate (never creates anything). Passing it puts the key in this conversation; prefer running payram_ops_playbook "connect" locally.
`baseUrl`	No	Public address of the PayRam server, same origin as the dashboard: https://pay.example.com, or just pay.example.com or an IP (https is tried first, then http). No :8080, no path. Required on the hosted MCP.

Output Schema

TableJSON Schema

Name	Required	Description
`baseUrl`	Yes
`healthy`	Yes
`version`	Yes
`findings`	Yes
`nextCall`	Yes	The single most useful tool call to make next
`warnings`	Yes
`nextSteps`	Yes
`setupStage`	Yes	Pass as payram_setup_plan stage once the server answers PayRam health; null when not reachable
`failedStage`	Yes	First failing stage, null when healthy
`likelyCauses`	Yes	Ranked causes for the first failing stage
`latestVersion`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedOct 11, 2026

changedInput schema / properties / baseUrl / description

Previous value: -"Public URL of the PayRam server, same origin as the dashboard (e.g. https://pay.example.com). No :8080. Required on the hosted MCP."New value: +"Public address of the PayRam server, same origin as the dashboard: https://pay.example.com, or just pay.example.com or an IP (https is tried first, then http). No :8080, no path. Required on the hosted MCP."

addedOutput schema / properties / nextCall

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "arguments": {
+          "additionalProperties": {},
+          "propertyNames": {
+            "type": "string"
+          },
+          "type": "object"
+        },
+        "tool": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "tool",
+        "arguments"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "The single most useful tool call to make next"
+}

addedOutput schema / properties / setupStage

Added value: +{
+  "anyOf": [
+    {
+      "const": "installed",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "Pass as payram_setup_plan stage once the server answers PayRam health; null when not reachable"
+}

changedOutput schema / required

Previous value: -[
-  "baseUrl",
-  "healthy",
-  "failedStage",
-  "version",
-  "latestVersion",
-  "findings",
-  "warnings",
-  "likelyCauses",
-  "nextSteps"
-]New value: +[
+  "baseUrl",
+  "healthy",
+  "failedStage",
+  "version",
+  "latestVersion",
+  "findings",
+  "warnings",
+  "likelyCauses",
+  "nextSteps",
+  "setupStage",
+  "nextCall"
+]

Changed15 schema fields changedOct 8, 2026

changedInput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

removedInput schema / additionalProperties
```
Removed value: -false
```

changedInput schema / properties / apiKey / description

Previous value: -"Merchant API key (per-project). Defaults to PAYRAM_API_KEY. Obtain headlessly: ./setup_payram_agents.sh ensure-api-key"New value: +"Optional project API key to validate (never creates anything). Passing it puts the key in this conversation; prefer running payram_ops_playbook \"connect\" locally."

changedInput schema / properties / baseUrl / description

Previous value: -"PayRam server base URL. Defaults to PAYRAM_BASE_URL. The installer publishes on port 80 (http://localhost), not :8080."New value: +"Public URL of the PayRam server, same origin as the dashboard (e.g. https://pay.example.com). No :8080. Required on the hosted MCP."

removedInput schema / properties / baseUrl / format
```
Removed value: -"uri"
```

changedOutput schema / $schema

Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"

addedOutput schema / properties / baseUrl

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

removedOutput schema / properties / failedStage / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

changedOutput schema / properties / failedStage / description

Previous value: -"First failing stage: reachability | api-key | jwt | readiness; null when healthy"New value: +"First failing stage, null when healthy"

addedOutput schema / properties / failedStage / type
```
Added value: +[
+  "string",
+  "null"
+]
```

addedOutput schema / properties / latestVersion

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / properties / likelyCauses / items / properties / likelihood / description

Previous value: -"Rough probability, e.g. \"80%\""New value: +"Rough probability, e.g. \"60%\""

addedOutput schema / properties / version

Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / warnings

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

changedOutput schema / required

Previous value: -[
-  "healthy",
-  "failedStage",
-  "findings",
-  "likelyCauses",
-  "nextSteps"
-]New value: +[
+  "baseUrl",
+  "healthy",
+  "failedStage",
+  "version",
+  "latestVersion",
+  "findings",
+  "warnings",
+  "likelyCauses",
+  "nextSteps"
+]

AddedJun 11, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower. The description nevertheless adds real context: it works without credentials, the API-key check 'never creates anything', and it returns 'ranked likely causes and exact fixes for the first failing stage'. This goes meaningfully beyond the annotations, though it does not touch rate limits or auth requirements for the version/worker checks.

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

Conciseness4/5

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

Four dense sentences that each carry distinct information: purpose+scope, capability list, API-key handling, return value, and an entry-point directive. Front-loaded with the core purpose, though the most actionable usage instruction ('run this first') sits at the tail where it is slightly less prominent.

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?

An output schema exists, so return values need not be fully explained, yet the description still summarizes them (ranked causes and fixes). Both optional params are schema-documented, annotations carry the safety profile, and the hosted-vs-local credential distinction is covered. Nothing an agent needs to invoke this correctly is missing.

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

Parameters3/5

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

Schema description coverage is 100%, and the schema itself documents both baseUrl (origin format, https-then-http fallback, no :8080/path) and apiKey including the security caveat about the key landing in the conversation. The description only restates 'by its public URL' and 'validates an API key', so baseline 3 is appropriate.

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?

Specific verb+resource ('Read-only diagnosis of a PayRam server') plus an explicit enumeration of what it inspects: reachability, health, TLS certificate, installed vs latest version, worker states. The closing directive 'Run this first when anything PayRam-related fails' positions it against siblings like payram_troubleshoot and test_payram_connection, so an agent can select it without opening any 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 an explicit trigger ('Run this first when anything PayRam-related fails') and names the alternative path for the sensitive case — prefer payram_ops_playbook "connect" locally rather than passing an API key here. The hosted-MCP-without-credentials condition is stated up front, leaving little to inference.

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

All Payram 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?