SocialGPT

Search your content

search

Read-only

Search across your own connected-account content and return the best matches.

Each result has an id (pass it to fetch for the full item), a title, a url, and a text snippet. This is the deep-research "search" entrypoint the ChatGPT/Claude connectors call by convention; for semantic search over analyzed videos specifically use search_videos. Returns {"results": [...]}; when you have no connected accounts it returns reason="no_connected_accounts" plus a connect_url instead of results.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum number of results to return (default 10).
`query`	Yes	Free-text query matched against your connected accounts' content (captions, titles, transcripts).
`platform`	No	Optional platform filter — instagram, tiktok, or youtube (case-insensitive). Omit to span all connected platforms.

Output Schema

TableJSON Schema

Name	Required	Description
`reason`	No	Present only when results is empty — why it is empty.
`results`	Yes
`connect_url`	No	Where to connect an account; present only with reason='no_connected_accounts'.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedJul 24, 2026

removedOutput schema / additionalProperties
```
Removed value: -true
```

addedOutput schema / description

Added value: +"Output of `search`. `reason` appears only when `results` is empty:\n'no_matching_content' (accounts connected, nothing matched) or\n'no_connected_accounts' (then `connect_url` is also present)."

addedOutput schema / properties

Added value: +{
+  "connect_url": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Where to connect an account; present only with reason='no_connected_accounts'."
+  },
+  "reason": {
+    "anyOf": [
+      {
+        "enum": [
+          "no_matching_content",
+          "no_connected_accounts"
+        ],
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "default": null,
+    "description": "Present only when results is empty — why it is empty."
+  },
+  "results": {
+    "items": {
+      "properties": {
+        "id": {
+          "type": "string"
+        },
+        "metadata": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "text": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null
+        },
+        "title": {
+          "type": "string"
+        },
+        "url": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "id",
+        "title",
+        "url"
+      ],
+      "type": "object"
+    },
+    "type": "array"
+  }
+}

addedOutput schema / required
```
Added value: +[
+  "results"
+]
```

Changed3 schema fields changedJun 24, 2026

addedInput schema / properties / limit / description

Added value: +"Maximum number of results to return (default 10)."

addedInput schema / properties / platform / description

Added value: +"Optional platform filter — instagram, tiktok, or youtube (case-insensitive). Omit to span all connected platforms."

addedInput schema / properties / query / description

Added value: +"Free-text query matched against your connected accounts' content (captions, titles, transcripts)."

First observedJun 18, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the readOnlyHint annotation (true), the description details the output format (results array with id/title/url/text) and edge case when no connected accounts (returns reason and connect_url). No destructive behavior is implied.

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?

Two concise sentences: first defines the tool's primary action, second explains output and key edge case. No wasted words.

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?

Given the output schema (results array), the description adequately covers return fields and error condition. No additional details are needed for correct usage.

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%, and the description adds meaningful context: query matches captions/titles/transcripts, platform is case-insensitive, defaults are noted. It reinforces schema but does not add entirely new info.

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?

The description clearly states the tool searches across connected-account content and returns best matches. It specifies result fields (id, title, url, text snippet) and distinguishes from sibling search_videos for semantic video search.

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?

The description provides usage context: pass id to fetch for full item, and use search_videos for semantic video search. It does not explicitly state when not to use this tool, but the alternative is well-defined.

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

All SocialGPT 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.