protogrid

Check an MCP server URL

check_server

Idempotent

Probe a remote MCP server URL once, credential-free and without calling its tools, and get its quality checks and its readiness for the Claude and OpenAI directories. Pass url to start a check (waits up to 25 s for the result), or id to read one. Quota: a few checks per hour anonymously, more with an API key.

Input Schema

TableJSON Schema

Name	Required	Description
`id`	No	A check id returned earlier, to read its result
`url`	No	The server's streamable HTTP or SSE URL, e.g. https://mcp.example.com/mcp. Never include credentials.
`wait`	No	Seconds to wait for the result (default 25)

Output Schema

TableJSON Schema

Name	Required	Description
`id`	Yes	Pass as id to read the result later
`url`	Yes
`page`	Yes	Shareable result page
`error`	No
`result`	No	Present when status is done
`server`	Yes	The catalog server listing this URL, if any
`status`	Yes
`disclaimer`	Yes
`finished_at`	Yes
`next_actions`	Yes	Follow-up calls: action is the tool, arguments are ready to pass ({placeholders} are yours to fill)
`requested_at`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 28, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "disclaimer": {
+      "type": "string"
+    },
+    "error": {
+      "type": "string"
+    },
+    "finished_at": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "id": {
+      "description": "Pass as id to read the result later",
+      "type": "string"
+    },
+    "next_actions": {
+      "description": "Follow-up calls: action is the tool, arguments are ready to pass ({placeholders} are yours to fill)",
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "action": {
+            "type": "string"
+          },
+          "arguments": {
+            "additionalProperties": {},
+            "propertyNames": {
+              "type": "string"
+            },
+            "type": "object"
+          }
+        },
+        "required": [
+          "action"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "page": {
+      "description": "Shareable result page",
+      "type": "string"
+    },
+    "requested_at": {
+      "type": "string"
+    },
+    "result": {
+      "additionalProperties": {},
+      "description": "Present when status is done",
+      "properties": {
+        "probe": {
+          "additionalProperties": {},
+          "properties": {},
+          "type": "object"
+        },
+        "quality": {
+          "additionalProperties": {},
+          "properties": {
+            "label": {
+              "type": "string"
+            },
+            "score": {
+              "type": [
+                "number",
+                "null"
+              ]
+            }
+          },
+          "required": [
+            "score",
+            "label"
+          ],
+          "type": "object"
+        },
+        "readiness": {
+          "description": "Claude and OpenAI directory requirements, one per directory; items are pass, warn, fail, unknown, manual or na",
+          "items": {
+            "additionalProperties": {},
+            "properties": {},
+            "type": "object"
+          },
+          "type": "array"
+        }
+      },
+      "required": [
+        "probe",
+        "quality",
+        "readiness"
+      ],
+      "type": "object"
+    },
+    "server": {
+      "description": "The catalog server listing this URL, if any",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "status": {
+      "enum": [
+        "queued",
+        "running",
+        "done",
+        "failed"
+      ],
+      "type": "string"
+    },
+    "url": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "id",
+    "status",
+    "url",
+    "requested_at",
+    "finished_at",
+    "server",
+    "page",
+    "disclaimer",
+    "next_actions"
+  ],
+  "type": "object"
+}

AddedSep 25, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Adds context the annotations do not carry: credential-free operation, no tool invocation, a 25 s wait ceiling, and an explicit quota ('a few checks per hour anonymously, more with an API key'). Rate-limit disclosure is exactly the kind of behavioral detail the annotations leave open.

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?

Three dense sentences, front-loaded with what the tool does, then how to invoke each mode, then the quota constraint. No filler and nothing an agent must read twice.

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?

For a three-parameter read/probe tool with an output schema and full annotation coverage, the description closes the remaining gaps: invocation modes, latency budget, and quota. Nothing needed to call it correctly is missing.

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 the baseline is 3, but the description adds the url-vs-id mode choice and the wait behavior that the schema only states as a default. It reinforces rather than merely repeats the parameter meaning.

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 ('Probe a remote MCP server URL once') plus the concrete deliverable ('quality checks and its readiness for the Claude and OpenAI directories'). The qualifier 'credential-free and without calling its tools' separates it from siblings like list_tools and get_server without needing their schemas.

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

Usage Guidelines4/5

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

Gives an explicit branch: pass `url` to start a check or `id` to read an existing one. It does not, however, say when to reach for check_server rather than the sibling get_server/get_connection, so the guidance is clear but not fully exclusive.

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

All protogrid tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?