PumpGTM MCP server

AI search topics to write about

get_ai_search_topics

Read-onlyIdempotent

Returns up to 5 pages the company could write to be named in AI answers, built from its tracked questions that don't name it and whose current answers leave it out. Questions no tracked company is named on (open) come first, then those competitors are named on least. Each topic has a suggested title, the kind of page (howto, guide, comparison or explainer) and its angle, the questions it answers, how many answers name no tracked company (unclaimed), the competitors named instead, the pages the engines cite, what they searched for and the reason; with a content audit, the company's best page that answers it (page) or that none does (noPage); and up to 3 related Hacker News discussions with points, comments and date (none rather than a weak match). Topics follow the latest answers, so they change after each check. Empty until a check has answered an unbranded question. Read-only and free: it never asks an engine anything.

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_ai_search_topics"
  }
}

Input Schema

Name	Required	Description	Default
`workspaceId`	No	A 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

Name	Required	Description
`topics`	Yes	Up to 5 pages to write, open questions first; empty until a check has answered an unbranded question.
`company`	Yes	The company being tracked; null without a company profile.
`message`	No	Only when AI search is off: how to start it.
`aiSearch`	Yes	on, or off until the first AI search step turns it on.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 10, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "aiSearch": {
+      "description": "on, or off until the first AI search step turns it on.",
+      "type": "string"
+    },
+    "company": {
+      "anyOf": [
+        {
+          "additionalProperties": {},
+          "properties": {
+            "name": {},
+            "website": {}
+          },
+          "required": [
+            "name",
+            "website"
+          ],
+          "type": "object"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "The company being tracked; null without a company profile."
+    },
+    "message": {
+      "description": "Only when AI search is off: how to start it.",
+      "type": "string"
+    },
+    "topics": {
+      "description": "Up to 5 pages to write, open questions first; empty until a check has answered an unbranded question.",
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "angle": {
+            "description": "The angle the page should take.",
+            "type": "string"
+          },
+          "cited": {
+            "description": "Pages the engines cite for these questions.",
+            "items": {},
+            "type": "array"
+          },
+          "hackerNews": {
+            "description": "Up to 3 related Hacker News discussions.",
+            "items": {
+              "additionalProperties": {},
+              "properties": {
+                "comments": {
+                  "type": "number"
+                },
+                "createdAt": {
+                  "type": "string"
+                },
+                "points": {
+                  "type": "number"
+                },
+                "title": {
+                  "type": "string"
+                },
+                "url": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "title",
+                "url",
+                "points",
+                "comments",
+                "createdAt"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "kind": {
+            "description": "Kind of page: howto, guide, comparison or explainer.",
+            "type": "string"
+          },
+          "named": {
+            "description": "Competitors named instead, with answer counts.",
+            "items": {},
+            "type": "array"
+          },
+          "noPage": {
+            "description": "True when no audited page answers these questions.",
+            "type": "boolean"
+          },
+          "page": {
+            "description": "With a content audit: the company's best page that answers it, or null."
+          },
+          "questions": {
+            "description": "Tracked questions the page answers; open when no answer names a tracked company.",
+            "items": {
+              "additionalProperties": {},
+              "properties": {
+                "open": {
+                  "type": "boolean"
+                },
+                "questionId": {
+                  "type": "string"
+                },
+                "text": {
+                  "type": "string"
+                }
+              },
+              "required": [
+                "questionId",
+                "text",
+                "open"
+              ],
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "reason": {
+            "description": "Why this topic is worth writing.",
+            "type": "string"
+          },
+          "searches": {
+            "description": "What the engines searched for.",
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "title": {
+            "description": "A suggested page title.",
+            "type": "string"
+          },
+          "unclaimed": {
+            "description": "Answers that name no tracked company.",
+            "type": "number"
+          }
+        },
+        "required": [
+          "title",
+          "kind",
+          "angle",
+          "questions",
+          "unclaimed",
+          "named",
+          "cited",
+          "searches",
+          "reason",
+          "page",
+          "noPage",
+          "hackerNews"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "aiSearch",
+    "company",
+    "topics"
+  ],
+  "type": "object"
+}

AddedNov 7, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description usefully reinforces the cost model ('free: it never asks an engine anything') plus two facts annotations cannot express: results are empty before a check has answered an unbranded question, and topics shift after each check. It stops short of describing pagination or how the 5-item cap is chosen.

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

Conciseness3/5

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

The precondition and freshness caveats are front-loaded and earn their place, but the middle of the description is one long semicolon-chained enumeration of every returned field, which duplicates the output schema and makes the text heavy to scan. It is information-dense rather than concise.

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 zero-required-parameter read tool with full annotation coverage and an output schema, this is more than sufficient: it explains ordering (open questions first, then least-named competitors), the empty state, and the fact that results track the latest answers. 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.

Parameters3/5

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

There is one optional workspaceId parameter and the schema already describes it at 100% coverage, including the 'omit for your own workspace' rule. The description adds nothing about parameters, so the baseline 3 applies — the schema, not the prose, carries this dimension.

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 concrete verb+resource ('Returns up to 5 pages the company could write to be named in AI answers') and immediately scopes it to tracked questions that don't name the company and whose answers leave it out. That is specific enough to separate it from get_ai_search_question, get_ai_search_answer and get_content_audit 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 Guidelines3/5

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

Usage is implied rather than stated: the output is for content planning, and the description notes it is 'Empty until a check has answered an unbranded question', which is a real precondition. But it never names an alternative (e.g. get_content_audit, get_ai_search_question) or says when to prefer this tool over them, so the agent must infer the routing.

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

All PumpGTM MCP server 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.