Connect ChatGPT to ToolRouter through developer-mode remote mcp. Add the remote server, complete the advertised account flow and check a real tool call. One connection reaches the live catalog of hosted tools and provider operations.
Before you start
Use ChatGPT on the web; this custom MCP setup is web only. You need Developer mode with remote MCP enabled and permission to add a custom server. The linked OpenAI developer guide lists Pro, Plus, Business, Enterprise and Education web accounts; availability and enabled actions still depend on your account and workspace policy. Check the Developer mode option in your own account before continuing. Free operations can be used without buying credits; paid operations need the account access and credits described by the response. Provider-account actions may need a separate connected account.
Connect ToolRouter
- Open Settings > Security and login and look for Developer mode. Availability depends on your account and workspace policy.
- Enable Developer mode, open ChatGPT Plugins at chatgpt.com/plugins, and use the plus button to create a developer-mode app.
- Name it ToolRouter, paste https://api.toolrouter.com/mcp as the remote MCP server, and select the detected OAuth authentication.
- Complete sign-in. In a conversation, choose Plus > Developer mode and enable the app.
https://api.toolrouter.com/mcpIf the first call returns an account-claim or setup link, use that link to retain the account and unlock the operations you need. For OAuth clients, complete browser sign-in. Keep credentials in the client credential store rather than pasting tokens into a prompt or shared configuration.
Check a real result
Ask for a free, read-only first task:
Use ToolRouter to discover a free operation for current weather in London, run it, and show the tool, skill and every field returned.
The useful check is a successful provider result in this conversation. A saved server entry or a visible tool list only establishes configuration. If no operation is available through this profile, report that result rather than inventing a tool name.
Bring external tools into a research conversation
ChatGPT can call discovered tools within the conversation where you are preparing a report. Keep external facts, model interpretation and the tool result distinct; ask for original source URLs and dates.
Example prompt:
Use ToolRouter to research the official sources behind the company names I give you. Discover the relevant public-data and web-search operations, inspect cost and requirements, and return a dated evidence table. Do not buy credits or contact anyone.
This is a task template, not a recorded run. Review the sources or output asset before using it in a report.
MCP and skill access are different
This setup connects the remote tools. A terminal skill installer is not a ChatGPT or Computer plugin install. Use the MCP workflow here; install the ToolRouter skill separately in a documented skill-capable runtime.
The discovery and execution workflow
- Call
discoverwith a query that describes the outcome: extract a page, research a company, check keyword demand, generate media or publish an authorised post. - Select the returned
toolandskill. Read the exact input schema, price, provider-account requirements and limitations. - Call
use_toolwith that tool, skill and schema-matching input. Built-in tools are called directly; inspect the currenttools/listfirst. - If the response returns an asynchronous job handle, use the advertised status operation, such as
job_get, until output is complete or an error is clear. - Return original source URLs, completed asset links or the provider action result. Keep the retrieval date and any provider error visible.
A search operation and a social publishing operation have different authority and account requirements. An installed skill does not choose a provider or authorise a purchase for you.
Costs, accounts and recurring work
Read the discovered price and check credits_balance before a paid batch. Review pricing and billing; do not assume every provider uses the same charging unit. Account actions require the correct upstream account and permission for the actual post or message.
An MCP connection does not schedule a background agent. Use ChatGPT's documented automation capability or your own scheduler for recurring jobs, with an explicit scope and budget. Check the previous job status before retrying an uncertain write.
Troubleshooting
The tools are missing
Enable the server for the conversation, reload MCP or restart the session, then check workspace policy. Configuration in a local editor does not automatically apply to a cloud agent.
Authentication or account access fails
Reconnect using the advertised OAuth flow, or use the returned account-claim link. A paid or provider-account operation can still fail after a free call works. Check the exact requirement returned by the tool.
The assistant answers without using ToolRouter
Ask it to name the actual operation and show returned fields or source URLs. A plausible answer without a tool result is not evidence of a provider call.
A job is queued or an action times out
Read the returned job status before repeating the call. A queued job is unfinished; an uncertain publishing response needs a status or provider readback before retrying.
Related workflows and sources
- All agent setup guides · MCP server reference
- Research and extract sources · SEO and competitor research
- Media generation · Authorised X and LinkedIn publishing
- Live provider index · Tool catalog
- ChatGPT Developer mode and MCP apps
- OpenAI setup documentation
Setup reviewed against the linked client documentation on 3 October 2026. Configuration instructions do not establish an authenticated end-to-end run in every client or an approved marketplace listing.