KnitKnot

# Connect to your AI tools (MCP)

Connect an OAuth-capable assistant to your KnitKnot workspace and query benchmark evidence from it.

## At a glance

  1. 1. **Copy the server URL**: Open Settings → MCP and copy the remote MCP server URL.
  2. 2. **Connect your client**: Add that URL in an OAuth-capable client and choose Connect or Authenticate.
  3. 3. **Sign in**: Complete KnitKnot sign-in in the browser window and try a workspace query.

KnitKnot exposes a curated view of your authorized workspace through the **Model Context Protocol (MCP)**, a way for an assistant to call tools that return workspace data. This authenticated customer connection is separate from the read-only customer-domain `/mcp` interface managed under [Content → Interfaces](/docs/manage-agent-interfaces/) in eligible workspaces.

The server lives at `https://mcp.knitknot.ai/mcp/`.

## Connect a client

  1. 1. Open [Settings → MCP](https://app.knitknot.ai/settings/mcp) and choose **Copy URL**. The page shows the remote server URL and setup steps.
  2. 2. Add the URL as a remote MCP server in an OAuth-capable client, such as Claude, Cursor, or ChatGPT.
  3. 3. Choose **Connect** or **Authenticate** in that client. Sign in to KnitKnot in the browser window that opens.
  4. 4. Ask the connected assistant for your workspace context to confirm it can read the intended workspace.

The current console setup uses your KnitKnot sign-in and workspace membership. It does not require an API key. If you belong to several workspaces, the available MCP tools let you list them and switch the active one.

## What you can do through it

Customer-facing MCP tools are controlled by an explicit allowlist : deliberately lean, so a model picks the right one without mis-routing. At a high level you can:

  • - **Query your presence** : pull the competitive overview (score, threats, capability gaps) and drill into a single competitor.
  • - **Diagnose gaps** : list issues (what AI gets wrong about you, or where you lose) and open the verbatim evidence behind one.
  • - **Plan content** : list playbooks (the fixes, ranked) and open one for the buyer keywords + ready-to-paste draft brief.
  • - **Act** : update a playbook's status; a change made through your assistant appears in the console.
  • - **Orient an agent** : retrieve workspace context before it starts a task.

MCP and the console use the same authorized workspace data. A supported playbook status change made through an assistant appears in the console.

For the full list of tools an assistant can call : what each does, its parameters, and what it returns : see the [MCP tools reference](/docs/mcp-tools/).

## When to use it

Reach for MCP when your workflow already lives in an AI assistant : for example, to ask which issue needs attention, bring source evidence into research, or move a playbook into progress. For dense review, configuration, benchmark execution, and publishing, the console is still the richer surface.

Next: back to [running benchmarks](/docs/run-and-schedule-benchmarks/), or read how gaps become [issues and playbooks](/docs/issues-and-playbooks/).

Docs navigation
Docs › Guides

Connect to your AI tools (MCP)

Connect an OAuth-capable assistant to your KnitKnot workspace and query benchmark evidence from it.

Updated

At a glance

  1. Copy the server URL

    Open Settings → MCP and copy the remote MCP server URL.

  2. Connect your client

    Add that URL in an OAuth-capable client and choose Connect or Authenticate.

  3. Sign in

    Complete KnitKnot sign-in in the browser window and try a workspace query.

KnitKnot exposes a curated view of your authorized workspace through the Model Context Protocol (MCP), a way for an assistant to call tools that return workspace data. This authenticated customer connection is separate from the read-only customer-domain /mcp interface managed under Content → Interfaces in eligible workspaces.

The server lives at https://mcp.knitknot.ai/mcp/.

Connect a client

  1. Open Settings → MCP and choose Copy URL. The page shows the remote server URL and setup steps.
  2. Add the URL as a remote MCP server in an OAuth-capable client, such as Claude, Cursor, or ChatGPT.
  3. Choose Connect or Authenticate in that client. Sign in to KnitKnot in the browser window that opens.
  4. Ask the connected assistant for your workspace context to confirm it can read the intended workspace.

The current console setup uses your KnitKnot sign-in and workspace membership. It does not require an API key. If you belong to several workspaces, the available MCP tools let you list them and switch the active one.

What you can do through it

Customer-facing MCP tools are controlled by an explicit allowlist : deliberately lean, so a model picks the right one without mis-routing. At a high level you can:

  • Query your presence : pull the competitive overview (score, threats, capability gaps) and drill into a single competitor.
  • Diagnose gaps : list issues (what AI gets wrong about you, or where you lose) and open the verbatim evidence behind one.
  • Plan content : list playbooks (the fixes, ranked) and open one for the buyer keywords + ready-to-paste draft brief.
  • Act : update a playbook’s status; a change made through your assistant appears in the console.
  • Orient an agent : retrieve workspace context before it starts a task.

MCP and the console use the same authorized workspace data. A supported playbook status change made through an assistant appears in the console.

For the full list of tools an assistant can call : what each does, its parameters, and what it returns : see the MCP tools reference.

When to use it

Reach for MCP when your workflow already lives in an AI assistant : for example, to ask which issue needs attention, bring source evidence into research, or move a playbook into progress. For dense review, configuration, benchmark execution, and publishing, the console is still the richer surface.

Next: back to running benchmarks, or read how gaps become issues and playbooks.