> ## Documentation Index
> Fetch the complete documentation index at: https://www.conductor.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# MCP FAQs

Here are frequently asked questions about Conductor's MCP server and its various connectors.

## About Conductor's MCP Server

<Accordion title="MCP server? Sounds technical… I'm not an engineer! 😬">
  Don't worry! While it's easy to get caught up in the terminology, this feature is super straightforward to set up and use. You'll just find the connector in your AI account, enter your Conductor credentials, and you're ready to go.

  An MCP (model context protocol) server is just a technology that lets existing AI models (like ChatGPT or Claude) connect to data from a third-party. Conductor's MCP server connects AI models your Conductor data, so you can query the AI model about your data.
</Accordion>

<Accordion title="Why should I use Conductor’s connector instead of asking LLMs directly?">
  Standard LLMs generate answers based on training data, which is often outdated or prone to "hallucinations" (guessing). Conductor’s connector uses a "split reasoning" architecture: LLMs understand the user’s intent and handles the conversation, but Conductor’s API provides the data and facts. This ensures you get verified, accurate intelligence rather than a best guess.
</Accordion>

<Accordion title="What’s the difference between a local MCP server versus a remote MCP server (e.g., ChatGPT, Claude)?">
  "Local MCP" means the connection runs directly on your personal computer, whereas "remote MCP" runs in the cloud as a direct server-to-server connection. Conductor has architected our platform to support both. While we are launching our Remote MCP first to power this integration with ChatGPT, this infrastructure is universal—allowing us to easily expand our verified connector to other LLMs and interfaces (e.g., Copilot, Gemini, etc.) in the future.
</Accordion>

<Accordion title="What is the difference between Conductor’s Data API and MCP Server? ">
  Conductor's Data API is the core infrastructure that allows you to request data programmatically for any use case—including BI dashboards, custom applications, and automated reporting. The MCP Server is a specialized connector built on top of the API that formats this data specifically for AI agents like ChatGPT and Claude. You get access to the power of both.
</Accordion>

## Data & Capabilities

<Accordion title="What data from Conductor is available through the MCP server?">
  Check out [our article](/mcp/what-data-is-available-in-conductors-mcp) about the available tools you can call with your LLM.
</Accordion>

<Accordion title="Can the MCP write data back into Conductor?">
  Currently, Conductor's MCP is focused on letting you query and analyze your Conductor data—it doesn't write data back into the platform.
</Accordion>

<Accordion title="What can't the MCP do right now? What's on the roadmap">
  Capabilities like pulling exact citation URLs for every prompt or integrating directly with third-party BI tools aren't available yet. Several capabilities like these are on our roadmap.

  If there's something you'd like the MCP to do, share it with your Conductor team as product feedback—it helps us prioritize.
</Accordion>

## Connecting to AI Platforms

<Accordion title="What AI platforms can I connect Conductor's MCP server to?">
  To start, we allow connections to:

  * OpenAI's **ChatGPT Pro**, **Business**, or **Enterprise** plans, using an App available in their App marketplace.
  * Anthropic's **Claude Pro** or **Max** plans, using a custom connector you can build.
  * Microsoft's **Copilot**. Note that access can vary across  plans and access level. Check with your IT team to verify what you have access to.
  * Perplexity's individual **Pro** plans and **Enterprise** plans.
  * Most other AI surfaces that allow connections to MCP servers.
</Accordion>

<Accordion title="Who can get access to Conductor's connectors to LLMs?">
  The connectors are available to all Conductor customers with access to supported LLMs. You will need an active Conductor login to authenticate the connection.
</Accordion>

<Accordion title="Why don't I see the Conductor app in my LLM's marketplace?">
  The most common reason you don't see it has to do with permissions or security settings at your organization. Many apps need to be requested and approved by your IT team.

  Also, be sure to note which LLMs Conductor supports with a native app in their ecosystem.
</Accordion>

<Accordion title="Why do custom connections sometimes have access to more MCP tools?">
  When Conductor releases new tools for your MCP connections to use, we add them to our MCP server, and you can then immediately update your connection to get access.

  New versions of native apps—like Conductor in ChatGPT or Claude—go through an approval process when submitted to an LLM. Because of this, there is a lag between when we submit a new MCP version with new tools and when those new tools appear for use in the LLM apps.

  This lag may be as little as a few days or as much as a few months.
</Accordion>

<Accordion title="I don't see a Conductor connector in Claude's directory. Where is it?">
  Conductor's native Claude connector is currently in review with Anthropic, and we expect to publish it soon. In the meantime, you can add Conductor to Claude in just a couple of minutes using a **custom connector**—which also gives you the latest set of tools, including both AI Search and traditional (keyword) Search data. See our [Claude setup guide](/mcp/claude) for step-by-step instructions.
</Accordion>

<Accordion title="I don't see the keyword (traditional search) tools in ChatGPT or Microsoft Copilot. How do I get them?">
  The published ChatGPT and Copilot apps currently run one version behind Conductor's MCP server, because each new version goes through an app-approval process with OpenAI and Microsoft. That's why the newest tools—like keyword data—may not appear right away.

  If you use **ChatGPT**, you can get the latest tools sooner by setting up a custom connector—reach out to your Conductor team and we'll help you and your ChatGPT administrator get it configured.

  For **Copilot**, a custom-connector option isn't available yet, so if you need keyword tools right away and your organization also permits another supported assistant like Claude or ChatGPT, we can help you get set up there.
</Accordion>

<Accordion title="Can I connect Conductor's MCP to Gemini?">
  Not yet. Gemini isn't supported during Beta. We're working with the Google team to understand their app-directory process, similar to how Conductor is listed with ChatGPT and Copilot.
</Accordion>

<Accordion title="My AI tool doesn't support OAuth. Are there other ways to connect?">
  Today, connections authenticate through OAuth. API-key–based authentication is coming soon, which will let you connect tools that don't support OAuth. If this is a blocker for you, let your Conductor team know so we can keep you posted.
</Accordion>

<Accordion title="Can I connect Conductor's MCP to an AI tool that isn't listed?">
  Generally speaking, yes! Conductor's MCP server can connect to any AI tool or platform that supports MCP connectivity via OAuth or API bearer token. Setup for a specific tool may need some extra configuration details. Reach out to your Conductor team with the name of your tool, the authentication method it supports, and any setup documentation or screenshots, and we'll help you work through the connection.
</Accordion>

## Subscription, Usage & Pricing

<Accordion title="How many MCP tool calls does my plan include?">
  Every Conductor subscription includes  allocated MCP tool calls, refreshed each contract year. If you're an account admin, you can see the exact number included with your plan—and how much you've used—on the **Subscription** page in Conductor. If you're not sure, your CSM or Account Manager can confirm your allocation.

  <Frame>
    <img src="https://mintcdn.com/conductor-0f65a05d/5hYVFmhCsR2C4aU9/images/mcp-subscription.png?fit=max&auto=format&n=5hYVFmhCsR2C4aU9&q=85&s=e2e5c6c063ba79b2e82a3bb2c95e5f36" alt="Mcp Subscription" width="1920" height="1080" data-path="images/mcp-subscription.png" />
  </Frame>
</Accordion>

<Accordion title="Do my MCP tool calls reset, or is it a one-time allocation?">
  Your allocation refreshes automatically on an annual basis. You don't need to purchase additional tool calls to keep the same allocation from year to year—your plan's included calls renew for you.
</Accordion>

<Accordion title="What happens when I use up my tool-call allocation?">
  Once you've used the tool calls included with your plan for the period, new requests are declined until more calls are added. You'll never be charged for overages—requests simply pause rather than billing you unexpectedly. If you need more, reach out to your CSM or Account Manager, who can help you add additional tool calls to your subscription.
</Accordion>

<Accordion title="How can I tell how many tool calls a query or skill will use?">
  Different queries and skills use different numbers of tool calls depending on how much data they retrieve. If you're planning heavier usage—like running several skills (your own or from the Template Gallery)—your CSM or Account Manager can help you estimate the tool calls involved so you can plan your allocation with confidence.
</Accordion>

<Accordion title="How much of my allocation should I add if I've run out?">
  The best estimate is based on your own usage. Your CSM or Account Manager can review your recent consumption, account for any one-off spikes, and help you project the tool calls you're likely to need for the rest of your term—so you purchase the right amount rather than guessing.
</Accordion>

<Accordion title="Where can I see my MCP usage?">
  Account admins can view usage at the account level on the **Subscription** screen in Conductor. A breakdown of usage by individual user is planned for a future release—until then, your Conductor team can help if you need a more detailed view.
</Accordion>

<Accordion title="I used the MCP before and never hit limits—why am I hitting them now?">
  Conductor's MCP is now available to all customers. To keep the service fast and reliable for everyone, we've introduced rate limits—**30 requests per hour per user** and **120 requests per minute across the system**—so that no single user or agent can affect everyone else. Your plan also now includes a set allocation of MCP tool calls. Rest assured, you'll never be charged for overages.
</Accordion>

<Accordion title="Why are my MCP tool calls now being metered?">
  Each plan comes with a pre-allocated number of tool calls. If you use up your allocation, you can choose to add more—but you'll never be charged for overages. Your CSM or Account Manager can share details on adding tool calls if you need them.
</Accordion>

<Accordion title="The rate limits are too restrictive for what I need. Can they be raised?">
  We review rate-limit increases on a case-by-case basis. If the current limits are getting in the way of your workflow, contact your Conductor team with details on what you're trying to do, and we'll assess whether an adjustment is possible.
</Accordion>

## Access & Troubleshooting

<Accordion title="I connected the MCP but got a 403 or a response like “this feature isn't included in your plan”. What should I do?">
  This usually means one of a few things: MCP access isn't yet enabled on your subscription, your plan term has ended, or you've used up your tool-call allocation for the period. Start by confirming your Conductor plan includes MCP access, then reach out to your CSM or Account Manager—they can verify your entitlement and help restore access.
</Accordion>

<Accordion title="One user on my account can't access the MCP, but others can. Why?">
  MCP access follows account membership in Conductor. If a specific user can't connect while others can, the most common reason is that they haven't been added to that Conductor account yet. Ask your admin to confirm the user is a member of the account they're trying to reach.
</Accordion>

<Accordion title="I can only see data for a subset of my accounts. How do I see the rest?">
  The MCP returns data for the Conductor accounts you're a member of. If you expected to see more accounts than are showing up, confirm with your admin that you've been added to all of those account—access to each account's data depends on your membership.
</Accordion>

<Accordion title="I'm getting an “Internal Server Error” (500). What should I do?">
  A 500 error is most often a temporary service disruption. Wait a moment and try your request again. If it keeps happening, contact your Conductor team so we can look into it.
</Accordion>

## Security & Privacy

<Accordion title="Does using Conductor’s connectors train public models?">
  No. The Conductor connector is not used to train their models. You can query your enterprise data with confidence, knowing it remains secure and private to your organization.
</Accordion>

<Accordion title="My security or IT team needs to review the MCP before we roll it out. What can you share?">
  We know security review is an important step. Our [MCP Quick Start guide](/mcp/quick-start) includes an example email you can copy and send to your security or admin team to kick off their review. If your team has deeper due-diligence questions, your Conductor team can coordinate the right details with our product and engineering teams.
</Accordion>