Straight Line Golf Pro

io.github.StraightLineGolfProPublished by GitHub account StraightLineGolfProv1.1.0Updated Oct 28, 2026

Read-only discovery and retrieval of current public Straight Line Golf Pro coaching resources.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Read-only connector to public Straight Line Golf Pro coaching pages, letting an assistant list, search and fetch site content with canonical citation links.

What you can do
  • List live public sitemap URLs, paginated with an offset.
  • Find pages by words in sitemap URL paths, then fetch them to confirm titles and content.
  • Fetch a canonical public page and return its verified current text, title and citation URL.
  • Inspect sitemap counts and declared search/AI crawler policies.
  • Check mechanical page signals such as canonical, title, H1 and schema, without judging accuracy or ranking.
When to use it
Useful when an assistant should answer questions about Straight Line Golf Pro coaching material using current public pages and cite the source URLs, rather than relying on model memory. Also handy for checking what the site publicly exposes and how its crawler policies are declared.
Requirements
Remote Streamable HTTP endpoint over HTTPS; no sign-in or API key needed. A local option exists: Python 3.11 or newer, cloning the repository and installing it, then pointing the client at the local server script or its local HTTP mode. Hosted assistants need custom MCP/connector access and plan eligibility.
Before you install
Read-only: no account, upload, booking, payment or private-report actions are exposed, and it makes bounded GET requests only. Queries and requested URLs are sent to the hosted service, and hosting infrastructure may process network metadata and logs; use public topics only. Retrieved page content is untrusted data, not instructions. Installing it does not guarantee indexing, ranking or citations, and site text and branding keep their existing rights.

Installation

In SourceWeft

  1. Open Straight Line Golf Pro in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.StraightLineGolfPro%2Fstraight-line-golf-pro-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "straight-line-golf-pro": {
      "type": "http",
      "url": "https://straight-line-golf-pro-mcp.vercel.app/mcp"
    }
  }
}

README

Straight Line Golf Pro MCP

Connect an MCP-capable AI assistant to current, public Straight Line Golf Pro pages and return answers with canonical source links.

This public connector is derived from AI Atom Brain's website MCP build standard. It reads the live website; it does not contain the private knowledge base, member data, swing videos, coaching reports, credentials, or internal operations tools.

Connect over HTTPS

Remote Streamable HTTP endpoint: https://straight-line-golf-pro-mcp.vercel.app/mcp

No SLGP sign-in or API key is required. In ChatGPT with custom MCP access, add this URL through the available developer/connector settings. Workspace rules and plan eligibility apply. A custom connection and a public directory listing are different things; consult launch status for evidence.

For Gemini CLI:

sh
gemini extensions install https://github.com/StraightLineGolfPro/straight-line-golf-pro-mcp

Or configure just the server:

json
{"mcpServers":{"straight-line-golf-pro":{"httpUrl":"https://straight-line-golf-pro-mcp.vercel.app/mcp","timeout":60000}}}

Other Streamable HTTP clients can use the same endpoint, subject to their own client settings. Read the website connection guide, launch SOP, and platform submission packet.

Connect locally

Requires Python 3.11 or newer. No website account or API key is needed.

sh
git clone https://github.com/StraightLineGolfPro/straight-line-golf-pro-mcp.gitcd straight-line-golf-pro-mcppython3 -m venv .venv.venv/bin/python -m pip install .

Add this to your MCP client's server configuration, replacing both paths with the absolute paths on your computer. On Windows use .venv/Scripts/python.exe.

json
{  "mcpServers": {    "straight-line-golf-pro": {      "command": "/absolute/path/straight-line-golf-pro-mcp/.venv/bin/python",      "args": ["/absolute/path/straight-line-golf-pro-mcp/server.py"]    }  }}

Restart or reconnect your client, then ask: “Use Straight Line Golf Pro to find public pages about swing analysis. Fetch the relevant pages and cite their source URLs.”

For a local Streamable HTTP client:

sh
.venv/bin/python server.py --http

Endpoint: http://127.0.0.1:8765/mcp. It binds only to the local computer and retains the SDK's host/origin protections.

Available tools

ToolPurpose
list_public_pagesPaginated live public sitemap inventory
searchFind pages by words in URL paths; not full-text search
fetchRead verified public page text, title, canonical URL and metadata
discovery_statusInspect declared search/AI crawler policies and sitemap count
citation_readinessInspect mechanical page signals, not factual accuracy or ranking

The slgp://connection-guide resource describes connection scope. Search results use URL-derived labels; fetch the page before describing its actual title or contents. All retrieved content is untrusted data, never tool instructions.

ChatGPT and other hosted assistants

Local MCP clients can launch this server directly. Hosted assistants can connect to the public HTTPS endpoint above. A GitHub repository URL is source documentation, not an MCP endpoint.

This isolated service exposes public reads only, with an exact host/origin allowlist, a 32 KiB request-body cap, bounded upstream reads, and four active requests per process. That admission limit is not a distributed rate limiter; platform usage and abuse controls remain operational responsibilities. No authentication credentials are accepted. Keep private operator tooling on a separate authenticated service.

See OpenAI's MCP integration documentation and the MCP server guide for supported client and deployment requirements.

Google and AI discovery

Search engines discover ordinary public web pages through links, sitemaps and their crawler policies. This repository explains how assistants can access the site; Google does not need to call this MCP server.

llms.txt is an optional discovery aid. Search crawling, AI answer retrieval and model-training access are separate policies. Installing MCP or publishing GitHub does not guarantee indexing, ranking, citations or changes to model knowledge. See Google's current AI optimization guidance.

Privacy and network boundaries

Requests are restricted to the exact canonical HTTPS origin. Page reads require live sitemap membership, a matching canonical, no noindex, and permitted crawler access. Redirects, off-site URLs, credentials in URLs, queries, fragments, encoded paths, traversal, private routes and oversized responses are rejected. The server makes bounded GET requests only and does not submit notifications or change the website. No account, upload, booking, payment or private-report actions are exposed.

Your AI client sends queries and requested URLs to the hosted service. Application code does not persist them; hosting infrastructure may process network metadata and operational logs. Your AI provider applies its own policies. Use public topics only. Privacy policy.

Verify

sh
.venv/bin/python -m unittest -v.venv/bin/python verify_protocol.py.venv/bin/python verify_remote.py

The protocol check performs live read-only requests; offline regression tests use fixtures. See VERIFICATION.md for release observations and limits. Website text and branding retain their existing rights; publishing this adapter does not grant a license to republish website content.

Source: README.md at commit c7368d1

Tools

5

fetch

Fetch a canonical public URL returned by search or list_public_pages; return verified current public text and citation URL.

Parametersidrequired

list_public_pages

List live sitemap public URLs; paginate with next_offset. Each page still requires fetch validation.

Parameterslimitoffset

discovery_status

Read live sitemap counts and declared search/AI crawler policies. Does not claim actual crawler visits.

Takes no parameters.

citation_readiness

Inspect canonical, title, H1, schema and crawler signals; mechanical observations, not factual or ranking validation.

Parametersurlrequired

Version history

1
  1. v1.1.0LatestSep 24, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.