MCP App Store
by KeenEthics
Vecbase icon

Vecbase MCP Server for ChatGPT

By Vecbase Inc.

Overview

Vecbase brings AI models into ChatGPT and Codex through one account, with the goal of connecting every AI model. Explore the current catalog and choose a model to generate text, images, videos or speech, or to transcribe audio. View your results and continue working with them in your conversation. You can also save and work with recordings and transcripts in Robin notes. Model availability and supported features follow the current Vecbase catalog.

How to connect

  1. ChatGPT: Open the Vecbase listing in the ChatGPT app directory and choose Connect. ChatGPT listing Vecbase exposes 25 tools here.

Tools

ai_gateway_audio_speech_create

ChatGPT
Generate speech from text. First select a voice from the model's supported_voices in ai_gateway_models_get. Returns stored audio for playback or download, never a server file path.

ai_gateway_audio_transcriptions_create

ChatGPT
Transcribe an explicitly user-selected audio file with automatic language detection. This produces text without creating a Robin note. Use Robin's import tool when the user wants a note.

ai_gateway_chat_completions_create

ChatGPT
Ask a selected Vecbase language model to generate text. This is a paid model call and does not replace the host assistant. Reuse idempotency_key after interruption.

ai_gateway_images_create

ChatGPT
Generate images with a discovered model. Returns stored results and an Operation ID. Reuse idempotency_key to recover; do not regenerate to check progress.

ai_gateway_models_get

ChatGPT
Read one discovered model's supported inputs, parameters and voices. Does not return a price quote.

ai_gateway_models_list

ChatGPT
Find available models before generation. For reading text aloud, use output_modalities=["speech"]; for speech to text use ["transcription"]. Omit q unless filtering by model name or ID. Returns capabilities, not price quotes; do not invent models or prices.

ai_gateway_open

ChatGPT
Open one compact result panel for an existing authorized model Operation when a preview or player helps. Use once, then use ai_gateway_results_get for progress. Never generate from this tool.

ai_gateway_results_get

ChatGPT
Recover a model call's status and stored result using its Operation ID. Does not open a panel or generate anything.

ai_gateway_videos_content

ChatGPT
Get stored output references for a completed video using its Operation ID. Pending tasks return their current status.

ai_gateway_videos_create

ChatGPT
Generate a video with a discovered model. Returns one Operation UUID as both operation_id and the video response id. Query progress; never start a second generation to poll.

ai_gateway_videos_get

ChatGPT
Read an existing video using its Operation ID without generating again.

robin_files_upload

ChatGPT
Upload one bounded chunk of an explicitly selected audio file or recording. Reserves encrypted, caller-bound bytes for Robin transcription.

robin_notes_create

ChatGPT
Create a meeting note. Returns a canonical Operation; its response contains note_id.

robin_notes_get

ChatGPT
Read a meeting note, its summary and current revision.

robin_notes_list

ChatGPT
List meeting note previews, newest first.

robin_notes_update

ChatGPT
Update note fields at an exact revision. Returns a canonical Operation.

robin_open

ChatGPT
Open the notes panel for interactive review or recording. Provide note_id for one note; omit it to browse. The compact panel has Start recording and Import audio; the expanded panel has these actions under New note (+). An empty note also has these actions. Recording requires the user's click and microphone permission; finishing submits for automatic transcription. Each note holds one recording. Opening this panel does not start recording or create a note. If recording is unavailable, offer a selected audio file. Open once; use data tools for follow-up reads, edits and progress without another panel. Give only a brief explanation using these actual controls.

robin_operations_get

ChatGPT
Read an authorized Robin operation and its result. A waiting client does not cancel the work.

robin_segments_update

ChatGPT
Correct transcript text at an exact revision. Returns a canonical Operation.

robin_speakers_list

ChatGPT
Read a meeting's speakers and their current revisions.

robin_speakers_update

ChatGPT
Rename a speaker at an exact revision. Returns a canonical Operation.

robin_summary_create

ChatGPT
Regenerate a stale or failed summary, replacing its existing text, including manual edits, when generation succeeds. Does not change the recording, transcript or handwritten notes. Use only when the user requests regeneration. Requires the current note revision and returns a canonical Operation.

robin_transcript_get

ChatGPT
Read timestamped transcript segments and speaker references.

robin_transcriptions_create

ChatGPT
Import an audio or video file into an unrecorded note. Format validation and bounded audio decoding run after canonical Operation acceptance.

robin_transcriptions_import

ChatGPT
Transcribe a completed caller-bound Robin file reservation. Returns the same canonical Operation as an attached file import.

Capabilities

WritesInteractive

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/vecbase"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/vecbase)