Skip to main content
Glama
Sign In

PumpGTM

by com.pumpgtm.mcp
OverviewDiscussionsAdmin
This connector has been deprecated

Duplicate listing. The official PumpGTM connector is https://glama.ai/mcp/connectors/com.pumpgtm/mcp (same server, https://mcp.pumpgtm.com/mcp).

Content audit results

get_content_audit
Read-onlyIdempotent

Returns audit (the latest content audit's progress, or null), pageCount and pages, lowest score first (up to 50): score 0 to 100, the tracked questions each page answers, a short summary and the most important fixes. Read-only and free.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_content_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
workspaceIdNoA teammate's workspace you may manage: an active workspace ID from list_team_workspaces. Omit for your own workspace. Supply on every call for a teammate.

Output Schema

NameRequiredDescriptionDefault
auditYesThe latest audit's progress; null when none has run.
pagesYesAudited pages, lowest score first (up to 50).
pageCountYesPages audited in total.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "audit": {
+      "anyOf": [
+        {
+          "additionalProperties": {},
+          "properties": {
+            "auditId": {
+              "description": "The audit's id.",
+              "type": "string"
+            },
+            "failure": {
+              "anyOf": [
+                {
+                  "additionalProperties": {},
+                  "properties": {
+                    "code": {
+                      "description": "A stable reason code, such as no_pages_found or audit_failed.",
+                      "type": "string"
+                    },
+                    "message": {
+                      "description": "The reason in plain words to pass on, with what to do next.",
+                      "type": "string"
+                    }
+                  },
+                  "required": [
+                    "code",
+                    "message"
+                  ],
+                  "type": "object"
+                },
+                {
+                  "type": "null"
+                }
+              ],
+              "description": "Why a failed audit stopped, in words to pass on; null otherwise."
+            },
+            "finishedAt": {
+              "description": "When it finished; null while running.",
+              "type": [
+                "string",
+                "null"
+              ]
+            },
+            "pagesAudited": {
+              "description": "Pages read and scored so far.",
+              "type": "number"
+            },
+            "pagesFound": {
+              "description": "Pages found to audit.",
+              "type": "number"
+            },
+            "source": {
+              "description": "site or github.",
+              "type": "string"
+            },
+            "startedAt": {
+              "description": "When the audit started.",
+              "type": "string"
+            },
+            "status": {
+              "description": "running, completed or failed.",
+              "type": "string"
+            },
+            "target": {
+              "description": "The website URL or repository (owner/name/folder) audited.",
+              "type": "string"
+            }
+          },
+          "required": [
+            "auditId",
+            "source",
+            "target",
+            "status",
+            "pagesFound",
+            "pagesAudited",
+            "startedAt",
+            "finishedAt",
+            "failure"
+          ],
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "The latest audit's progress; null when none has run."
+    },
+    "pageCount": {
+      "description": "Pages audited in total.",
+      "type": "number"
+    },
+    "pages": {
+      "description": "Audited pages, lowest score first (up to 50).",
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "answersQuestions": {
+            "description": "Tracked questions the page answers.",
+            "items": {
+              "additionalProperties": {},
+              "properties": {
+                "questionId": {
+                  "description": "The tracked question.",
+                  "type": "string"
+                },
+                "text": {
+                  "description": "Its text.",
+                  "type": "string"
+                }
+              },
+              "required": [
+                "questionId",
+                "text"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "auditedAt": {
+            "description": "When the page was audited (ISO time).",
+            "type": "string"
+          },
+          "fixes": {
+            "description": "Up to 6 fixes in plain words, most important first.",
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "locator": {
+            "description": "The page URL or repository file path.",
+            "type": "string"
+          },
+          "pageId": {
+            "description": "The audited page's id.",
+            "type": "string"
+          },
+          "score": {
+            "description": "How easily AI engines can answer from it and cite it, 0 to 100.",
+            "type": "number"
+          },
+          "source": {
+            "description": "site or github.",
+            "type": "string"
+          },
+          "summary": {
+            "description": "A short summary of the page.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "title": {
+            "description": "The page title; null when it has none.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "url": {
+            "description": "The page URL; null for repository files, which use locator.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "wordCount": {
+            "description": "Words on the page.",
+            "type": "number"
+          }
+        },
+        "required": [
+          "pageId",
+          "source",
+          "title",
+          "url",
+          "locator",
+          "score",
+          "wordCount",
+          "summary",
+          "answersQuestions",
+          "fixes",
+          "auditedAt"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "audit",
+    "pageCount",
+    "pages"
+  ],
+  "type": "object"
+}
  2. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the trailing "Read-only and free" adds nothing. What the description does add is genuinely useful behavior: results are ordered lowest score first, capped at 50 pages, and audit is null when no audit exists — details no structured field conveys. It stops short of saying whether a partially-complete audit returns partial pages.

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?

It is a single front-loaded sentence that leads with the return payload and folds in the ordering, limit and score range. The heavy nested parentheticals make it read as a run-on, and "Read-only and free" duplicates the annotations rather than earning its place.

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?

With an output schema present and full annotation coverage, the description need not restate return values, yet the summary of fields and the 50-item cap make the shape scannable up front. The main gap is the missing link to start_content_audit, which an agent needs to know when the audit field will be null.

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?

There is a single optional parameter and schema coverage is 100%; the schema description already explains that workspaceId must be an active workspace from list_team_workspaces, omitted for your own workspace. The tool description adds nothing about this parameter, so the baseline 3 applies.

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 uses a specific verb ("Returns") tied to a named resource ("audit") and enumerates the payload (audit progress, pageCount, pages, score, questions, summary, fixes). It implicitly distinguishes itself from the sibling start_content_audit by framing the audit as something that already exists ("the latest content audit's progress, or null"), but it never names or contrasts that sibling explicitly.

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?

Usage is only implied: the "or null" fallback hints that an audit must already exist (presumably from start_content_audit) before this call is meaningful. There is no explicit when-to-use, when-not-to-use, or statement about polling vs one-shot retrieval of an in-progress audit.

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

All PumpGTM toolsInspect
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