MCP Server

Connect any MCP-capable AI client to InSkill to ask copilots questions and author expertise as yourself.

The Model Context Protocol (MCP) is a standard way for an external AI system to connect to and interact with InSkill's tools, data, and services. You can connect any MCP-capable AI client, such as Claude, to InSkill and work with your copilots and expertise in the flow of work: ask copilots questions, and read and author copilots, resources, tasks, and steps.

MCP also supports faster analytical and administrative work — adding a user, managing user groups, reading the user log, optimizing prompts, exporting data, or identifying knowledge gaps. In every case, each call runs against your own InSkill account and acts as the signed-in user, so it only ever sees and does what that user is permitted to.

Server URLhttps://mcp.expert.inskill.ai/mcp
TransportStreamable HTTP
AuthenticationOAuth 2.1

Before You Start

The InSkill sign-in page, where you sign in with your InSkill account during connector setup.

Signing in with your InSkill account

You need an InSkill account. You sign in with it during setup, and everything the connector does happens as you.

What you can do depends on that account. Asking copilots questions and reading the expertise behind them is available to anyone; creating and editing content requires a role that already permits it in InSkill.

Answers come from the expertise loaded against a copilot rather than from general knowledge, so a copilot with no resources will connect but have little to draw on.

Nothing needs installing, and there are no keys or tokens to generate.

Connecting a Client

The pattern is the same everywhere: point the client at the server URL, then complete a one-time browser sign-in when prompted. The URL above points at the live expert server, so the connector works with the resources, tasks, and tools your authoring team has reviewed, approved, and pushed to production.

For authors, connecting through MCP turns time-consuming, back-burner work into quick projects — for example:

  • Comparing tasks against resources to find discrepancies.
  • Identifying the users with the most and least recorded interactions.
  • Determining which resource types your technical team actually prefers.
  • Scheduling team seminars around the common knowledge gaps the AI uncovers.

Connecting Claude on desktop and web

Follow these steps to connect Claude:

  1. Open Settings > Connectors and choose Add custom connector.

    The Add custom connector option in Claude's connector settings.

    Add custom connector in Claude's settings

  2. Enter the server URL https://mcp.expert.inskill.ai/mcp.

    The server URL entered in the custom connector dialog.

    The InSkill server URL in the connector dialog

  3. Select Add. Claude opens the connector portal; select Connect, then sign in to InSkill and approve access in the browser window that opens.

    The InSkill sign-in and approval window opened by the connector.

    Signing in to InSkill to approve access

  4. The InSkill tools are now available in your conversations.

    InSkill tools listed as available in a Claude conversation.

    The InSkill tools available in a conversation

In Claude Code, add the server from the command line and run /mcp in a session to complete the sign-in:

claude mcp add --transport http inskill https://mcp.expert.inskill.ai/mcp

Connecting to the Author Account

The Author Account has its own MCP server. Follow the same steps, pointing at this URL instead:

https://mcp.author.inskill.ai/mcp

Two tools differ between the Author Account and production. create_product is refused in the Author Account, because copilots are created in production. push_product runs only in the Author Account, because pushing is one-directional toward production.

Cursor, VS Code, and other JSON-configured clients

Clients that use a JSON config register the server as a remote endpoint:

{
  "mcpServers": {
    "inskill": {
      "url": "https://mcp.expert.inskill.ai/mcp"
    }
  }
}

On first use the client opens a browser for sign-in. Consult your client's documentation for where its MCP config lives.

Your own application

If you are building your own AI application rather than using an off-the-shelf client, there is no connector screen and your application handles sign-in itself. Most MCP client libraries speak the protocol for you but leave the OAuth flow to you.

Discovery starts from an unauthenticated request to the server URL, which returns 401 with a WWW-Authenticate header pointing at:

https://mcp.expert.inskill.ai/.well-known/oauth-protected-resource

That document names the authorization server, whose metadata lives at:

https://expert.inskill.ai/.well-known/oauth-authorization-server

From there the flow is standard OAuth 2.1: register the client (dynamic client registration is supported), send the user to the authorization endpoint with PKCE, exchange the returned code for tokens, then send Authorization: Bearer <access_token> on every request to the MCP server. Refresh tokens are issued, so each user signs in once rather than every session.

Tokens are always tied to a signed-in user. There is currently no way to obtain one without a user completing sign-in, so plan for each of your users to authenticate once and for your application to hold their tokens.

What You Can Ask

You do not call tools yourself. You describe what you want and the client picks the tools. These are the patterns the connector is built for — replace anything in angle brackets with your own values.

Ask a copilot a question

The copilot answers from the expertise loaded against it, rather than from general knowledge.

Ask the <copilot> copilot how to replace the intake filter, and summarise the steps.

Ask about a specific unit

If a serial number is registered as an asset, the answer can take that unit's configuration into account.

Using the <copilot> copilot, what does error code <code> mean on unit <serial number>?

Find what expertise exists

Useful before adding anything, to see what a copilot already covers.

List the tasks and resources on the <copilot> copilot, and tell me which areas look thin.

Author a procedure

The connector can create tasks and their steps, so a procedure can be drafted in conversation and reviewed in InSkill afterwards.

Create a task on the <copilot> copilot called <name>, with steps covering <the procedure>.

Review how a copilot is performing

Sessions and feedback are readable, so you can see what people are asking and where answers fall short.

Show me the recent sessions on the <copilot> copilot and what people asked.

Authentication

InSkill is the authorization server. On first connect the client registers itself through dynamic client registration, then runs a standard OAuth 2.1 sign-in with PKCE that opens your browser once. SSO works through the normal InSkill sign-in page. After that the client refreshes access silently, and you are not prompted again until the session ends.

Access is governed by your InSkill role. The connector acts as the signed-in user, so every tool call inherits exactly what that user is permitted to do, scoped to their account. If a user is not permitted to do something, the call returns a permission error, exactly as it would in the portal.

This means two people connecting to the same server see different things. A colleague may see copilots you cannot, and a tool that works for them may return a permission error for you. That is intended, and it mirrors what each of you sees when signing in to InSkill directly.

Tools

The connector exposes a curated set of the InSkill public API as tools. Names match what your client lists. The list and get tools are read-only; create and update tools require the corresponding permission on the signed-in user's role. Delete is intentionally not exposed; the one removal is remove_group_members, which ends group memberships without deleting the users.

AreaTools
Copilotscreate_gpt_session, create_gpt_message, list_gpt_sessions, get_gpt_session, list_gpt_messages, get_gpt_message, feedback_gpt_message, escalate_gpt_session, create_gpt_messages_comment
Productslist_products, get_product, create_product, update_product, push_product
Resourceslist_resources, get_resource, create_resource, update_resource
Taskslist_expertise_tasks, get_expertise_task, create_expertise_task, update_expertise_task
Stepslist_expertise_steps, get_expertise_step, create_expertise_step, update_expertise_step
Assetslist_assets, get_asset, create_asset, update_asset
Data dictionarylist_data_dictionary, get_data_dictionary, create_data_dictionary, update_data_dictionary
Users and roleslist_users, get_user, create_user, update_user, deactivate_user, resend_invite, list_roles, get_role
User groupslist_groups, get_group, create_group, update_group, list_group_members, add_group_members, remove_group_members
Scriptslist_scripts, get_script, create_script, update_script
GPT toolslist_gpt_tools, get_gpt_tool, create_gpt_tool, update_gpt_tool
User loglist_userlog, get_userlog
📘

Note

Tool names use product where the rest of the documentation says copilot. They are the same thing: list_products lists your copilots. The script tools manage a copilot's task scripts, which run when a task session starts and when it finishes; see Scripts. The GPT tool tools manage the Data Query and Script tools on a copilot's GPT Tools tab; see GPT Tools.

The tools map directly to the InSkill public API, so the API reference covers field-level detail for every tool. Tools that change existing records are marked as such, so most clients ask you to confirm before running them.

Uploading document, image, and video files is done through the portal or the public API's file-upload endpoint, not through an MCP tool. The connector's resource tools manage everything else: metadata, URLs, visibility, and dependencies.

Troubleshooting

The sign-in window opens but nothing happens, or returns me to the start. Check you are signing in to the account you expect. If your browser is already signed in to a different InSkill account, sign out there first and try again.

I approved access but no InSkill tools appear. Most clients fetch the tool list once when they connect. Disconnect the connector and add it again to force a fresh fetch.

A tool returns a permission error. The connector can only do what your role allows. If the same action is unavailable to you in the portal, it is unavailable here. Ask an administrator to adjust your role.

A copilot I expect to see is not listed. You only see copilots your role gives you access to. Confirm you can see it when you sign in to InSkill directly.

The copilot says it cannot find the information. The answer comes from the expertise loaded against that copilot, not from general knowledge. If the manual or procedure covering your question has not been added, there is nothing to draw on. Adding the resource is the fix.

I want to connect as a different user or account. Each connection is tied to the user who signed in. To switch, remove the connector and add it again, then sign in as the other user. Reconnecting is what clears the stored credentials.

Can I use an API key instead of signing in? Not for the MCP connector, which is deliberately per-user so that permissions and attribution follow the person. For service-level access in a backend integration, use the InSkill public API with an API key instead.