Goro

Two scopes exist, and a client that does not ask for a narrower grant gets both:

Access tokens last an hour and the client refreshes them silently. Refresh tokens last 30 days and rotate on every use.

Building the client yourself rather than using an existing one? The OAuth flow is documented end to end in theOAuth quickstart.

That is the complete list. There is no per-tool MCP surface: the 70 catalog tools are reached throughrun_toolby slug, which is what keeps the tool list small enough for an agent to reason about.

discover_toolstakes a plain-languagequeryand an optionallimit(default 5, maximum 20). Each result carries a slug, guidance on when to use it, its price and a fillable sample input, so the agent can usually skipinspect_tool.

You do. Goro never chooses one:run_tooltakes an exact slug, so when several tools can do a job, the choice happens in the agent.

By default it is not allowed to make that choice quietly.discover_toolsreturns achoosefield telling the agent to show you the candidates with their prices and ask which you want. That matters because the prices are not close: five tools can make you an image, from $0.01 to $0.27 a call, and being charged for one you were never shown is not a good surprise.

- You named the tool."Use nano banana pro for this" is already an answer.
- Only one tool matches.Nothing to choose between, though the agent should still tell you what it is about to spend.
- You said to always use one.Tell the agent "always use X for images", "remember that", or "stop asking me", and it callsremember_tool_choice. From then ondiscover_toolsreturnsyour_preferencefor that category and the agent uses it without asking.

A preference is savedonly when you ask for one. Picking a tool for a single job is not a standing instruction, and treating it as one would mean you are never offered the cheaper option again. One saved choice per category (image, video, voice, search, social, maps, people, ecommerce). Say you want to pick again and the agent callsforget_tool_choice.

This is an instruction to the agent, not a lock. Goro can tell a client to ask you and can refuse to guess on your behalf, but it cannot reach into the client and force a prompt. A well-behaved agent follows it; treatremember_tool_choiceas the reliable control, since that one is enforced server-side.

The HTTP API and the CLI are unaffected: both already require you to name a slug, so there is nothing for anyone to pick.

run_toolblocks for up to about 25 seconds. A fast tool returns its rows in that same response. A slower one returns arun_idand an explicit instruction to pollget_rununtil the status is terminal.

wallet_balancereturns the available balance and atop_up_url, which is what an agent should surface to a human when funds run out.

One rule, and it matters more than it looks: an agent must never read a file into the conversation in order to send it. Tool arguments pass through the context window exactly like tool results do, so a 3 MB photograph sent asimage_base64is roughly a million tokens, gets truncated, and fails the run with something that reads like file corruption.

create_uploadis the way round it. It takes acontent_type, returns a short handle plus a URL to PUT the file to, and includes the exactcurlto run. The agent uploads the file with its own shell, then passes the handle asimage_handleinrun_tool. The bytes never enter the conversation, the ceiling goes from 3 MB to 10 MB, and the handle itself is about thirty characters. Do not shrink the image to make it fit: size was never the problem the upload path is solving.Uploadsdocuments the whole flow.

Tool errors carry the samecodeandmessageas the HTTP API, so one set of instructions covers both surfaces.

Everything. The MCP tools are thin wrappers over the same code paths as/v1/discover,/v1/inspect,/v1/uploads,/v1/run,/v1/runs/{id}and/v1/wallet/balance. Same catalog, same holds, same charges, same ledger.

Rows arrive in therun_toolresponse, or in theget_runpoll that finds the run finished. Polling a finished run is the supported way to collect a slow result. Results are deleted once collected, and after 24 hours regardless, so have the agent write down anything it will need later. When the result is a media link, from a voice or image tool, have it download the file too: those links expire on the same clock or on the model provider's.

Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.

Streamline your social media with Postiz. Schedule posts, analyze performance, and manage all accounts in one place

You're agent can Chain 60+ AI image and video models on one workflow canvas

Add real-time chat, voice and video calling, AI agents & moderation to your app.

Compress video, images, PDF and GIF on macOS, Windows and Linux

File conversion for AI agents: office docs to PDF, PDF to Word, document interchange, and audio/video transcodes via the hushvert hosted API.

PostPlanify Social Media Management - MCP Server

AI social media employee for planning campaigns, creating on-brand content, publishing across platforms, and growing your online presence.

Turn your AI assistant into a social media manager. Schedule and publish posts across 9 networks, pull profile and competitor analytics, run team approval workflows, manage the media library, and generate on-brand images with AI.