Skip to content

docs(ai-tools): drop hosted Kapa MCP; move Context Hub to uvx + add C… #898

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
markbackman merged 1 commit into from
Jun 13, 2026
Merged

docs(ai-tools): drop hosted Kapa MCP; move Context Hub to uvx + add C… #898

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
114 changes: 27 additions & 87 deletions pipecat/get-started/ai-tools.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,97 +5,33 @@ description: "Use AI coding tools with Pipecat documentation and source code."

Pipecat offers several ways to give AI coding tools access to documentation and source code context, helping you build voice and multimodal applications faster.

## MCP Server
## Pipecat Context Hub (MCP Server)

The Pipecat docs MCP server is a cloud-hosted service powered by [Kapa.ai](https://www.kapa.ai/) that searches across the full Pipecat documentation site. It returns synthesized answers with source citations, covering guides, API references, and other docs content. No local setup required.

<Tabs>
<Tab title="Claude Code">
```bash
claude mcp add --transport http pipecat-docs https://daily-docs.mcp.kapa.ai
```
</Tab>
<Tab title="Codex">
```bash
codex mcp add pipecat-docs --url "https://daily-docs.mcp.kapa.ai"
```
</Tab>
<Tab title="Cursor">
<a href="cursor://anysphere.cursor-deeplink/mcp/install?name=pipecat-docs&config=eyJ1cmwiOiJodHRwczovL2RhaWx5LWRvY3MubWNwLmthcGEuYWkifQ%3D%3D">
<img
noZoom
src="https://cursor.com/deeplink/mcp-install-dark.svg"
alt="Add Pipecat MCP to Cursor"
height="32"
/>
</a>

Or manually add to your Cursor MCP config:

```json
{
"mcpServers": {
"pipecat-docs": {
"url": "https://daily-docs.mcp.kapa.ai"
}
}
}
```
</Tab>
<Tab title="VS Code">
<a href="vscode:mcp/install?%7B%22name%22%3A%22pipecat-docs%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fdaily-docs.mcp.kapa.ai%22%7D">
<img
noZoom
src="https://img.shields.io/badge/VS_Code-Install_MCP_Server-0098FF?style=flat-square&logo=visualstudiocode&logoColor=white"
alt="Add Pipecat MCP to VS Code"
height="32"
/>
</a>

Or manually add to your VS Code MCP config (`.vscode/mcp.json`):

```json
{
"servers": {
"pipecat-docs": {
"url": "https://daily-docs.mcp.kapa.ai"
}
}
}
```
</Tab>
</Tabs>

## Pipecat Context Hub

[Pipecat Context Hub](https://github.com/pipecat-ai/pipecat-context-hub) is a local-first MCP server that indexes Pipecat documentation, code examples, and framework API source on your machine. Unlike the cloud-hosted MCP server above, Context Hub runs a local vector database and is optimized for coding workflows — it returns relevant source code and snippets rather than synthesized answers, giving your AI coding tool the raw context it needs to solve implementation problems.
[Pipecat Context Hub](https://github.com/pipecat-ai/pipecat-context-hub) is a local-first MCP server that indexes Pipecat documentation, code examples, and framework API source on your machine. It runs a local vector database and is optimized for coding workflows. It returns relevant source code and snippets rather than synthesized answers, giving your AI coding tool the raw context it needs to solve implementation problems.

Because it runs locally, you can also add your own repositories (public or private) to the index for a more customized context.

Available tools include `search_docs`, `search_examples`, `search_api`, `get_code_snippet`, and `check_deprecation`.

### Setup

The hub is published to PyPI as `pipecat-ai-context-hub` and runs with [`uv`](https://docs.astral.sh/uv/) — no clone required. Build the local index once:

```bash
git clone https://github.com/pipecat-ai/pipecat-context-hub.git
cd pipecat-context-hub
uv sync
uv run pipecat-context-hub refresh # build local index (~2 min first run)
uvx pipecat-ai-context-hub refresh # build local index (~2 min first run)
```

### Add to your coding tool

<Tabs>
<Tab title="Claude Code">
```bash
claude mcp add pipecat-context-hub \
-- uv run --directory /path/to/pipecat-context-hub pipecat-context-hub serve
claude mcp add pipecat-context-hub -- uvx pipecat-ai-context-hub serve
```
</Tab>
<Tab title="Codex">
```bash
codex mcp add pipecat-context-hub \
-- uv run --directory /path/to/pipecat-context-hub pipecat-context-hub serve
codex mcp add pipecat-context-hub -- uvx pipecat-ai-context-hub serve
```
</Tab>
<Tab title="Cursor">
Expand All @@ -105,18 +41,13 @@ uv run pipecat-context-hub refresh # build local index (~2 min first run)
{
"mcpServers": {
"pipecat-context-hub": {
"command": "uv",
"args": [
"run",
"--directory",
"/path/to/pipecat-context-hub",
"pipecat-context-hub",
"serve"
]
"command": "uvx",
"args": ["pipecat-ai-context-hub", "serve"]
}
}
}
```

</Tab>
<Tab title="VS Code">
Add to `.vscode/mcp.json`:
Expand All @@ -125,21 +56,30 @@ uv run pipecat-context-hub refresh # build local index (~2 min first run)
{
"servers": {
"pipecat-context-hub": {
"command": "uv",
"args": [
"run",
"--directory",
"/path/to/pipecat-context-hub",
"pipecat-context-hub",
"serve"
]
"command": "uvx",
"args": ["pipecat-ai-context-hub", "serve"]
}
}
}
```

</Tab>
</Tabs>

A newly added MCP server loads when your coding tool starts a session, so add it before opening the session you want to use it in.

### Use it without MCP

The same tools are available as one-shot CLI commands, so you can query the index from a shell with no MCP setup — handy in a session where the MCP server isn't connected yet:

```bash
uvx pipecat-ai-context-hub check-deprecation PipelineTask
uvx pipecat-ai-context-hub search-api "WebsocketServerParams"
uvx pipecat-ai-context-hub status # index health / freshness
```

Each command prints the tool's JSON to stdout. The package name is `pipecat-ai-context-hub`; the command and MCP server are named `pipecat-context-hub` (both spellings of the command resolve once installed).

See the [repo docs](https://github.com/pipecat-ai/pipecat-context-hub) for additional configuration options, including pinning to a specific Pipecat version.

## CLAUDE.md
Expand Down
Loading