Skip to content

Add ParlayAPI MCP integration with runnable Haystack examples - #601

Open
JacobiusMakes wants to merge 1 commit into
deepset-ai:mainfrom
JacobiusMakes:catalog/parlayapi-mcp-20260912
Open

JacobiusMakes wants to merge 1 commit into
deepset-ai:mainfrom
JacobiusMakes:catalog/parlayapi-mcp-20260912

Conversation

@JacobiusMakes

Copy link
Copy Markdown

Adds a ParlayAPI catalog page using the existing mcp-haystack MCPToolset and published parlayapi-mcp server. The default example discovers selected read-only tools locally without an API key, endpoint call or model. A separate explicit example makes one public sports-metadata call and prints sport keys with reported event counts. Private account setup and data-use limits are documented.

Validated on Python 3.12 with Haystack 2.31.0, mcp-haystack 1.5.1 and parlayapi-mcp 0.3.7. Actual stdio discovery passes with network access blocked in the server subprocess. The public metadata call returned HTTP 200 through MCP; its saved response was replayed through the exact final example. Six focused checks pass, covering frontmatter, credential isolation, secret serialization, metadata parsing and error handling. Dependency checks and all linked pages pass. No paid API request or model inference was performed.

Authored by Astra, an AI assistant working with the ParlayAPI team, and reviewed in that workflow. It follows the existing MCP catalog pattern without adding another SDK or changing Haystack runtime code.

@JacobiusMakes
JacobiusMakes requested a review from a team as a code owner September 12, 2026 22:54
@vercel

vercel Bot commented Sep 12, 2026

Copy link
Copy Markdown

Someone is attempting to deploy a commit to the deepset Team on Vercel.

A member of the Team first needs to authorize it.

@kacperlukawski kacperlukawski left a comment

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think the page should have an example of how to use it within an agent, not just by calling the MCP tools directly.

Use Python 3.10 or newer in a private virtual environment:

```bash
pip install "haystack-ai==2.31.0" "mcp-haystack==1.5.1" "parlayapi-mcp==0.3.7"

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Haystack 3.0 has been released in the meantime. Could you do not pin specific version here?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants