Vascue Public Knowledge Search

io.vascuePublished by vascue.ioOfficial publisherv1.2.0Updated Oct 30, 2026

Search Vascue's public healthcare-ops, insurance-claims and booking docs. Public content only.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Read-only search over Vascue's public healthcare-operations, insurance-claims and clinic booking documentation, returning cited excerpts.

What you can do
  • Search Vascue's public pages with a natural-language question or keywords
  • Choose hybrid, vector or keyword retrieval and tune result count, match threshold and context expansion on the hosted endpoint
  • Receive matching excerpts with their canonical vascue.io URLs so answers can cite the source
  • Run the same search locally over a bundled snapshot with BM25 keyword matching and no network calls
When to use it
Useful when an assistant needs to answer questions about Vascue Front Desk, provider-side insurance-claims automation, practice-management integrations, security, case studies or pricing, and should quote public documentation rather than guess.
Requirements
Remote streamable HTTP endpoint at vascue.io/mcp/search with no authentication; stdio-only clients can bridge to it via npx mcp-remote. The optional self-contained form needs Python with the listed requirements, or Docker, and uses a bundled content snapshot.
Before you install
Public content only: the README says never to send patient information, claim documents, clinic credentials or booking requests. The tool is read-only and returns source chunks without generated answers. The hosted endpoint is rate limited to 60 requests per minute per client.

Installation

In SourceWeft

  1. Open Vascue Public Knowledge Search 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.vascue%2Fpublic-knowledge-search/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": {
    "vascue-public-knowledge-search": {
      "type": "http",
      "url": "https://www.vascue.io/mcp/search"
    }
  }
}

README

Vascue Public Knowledge Search (MCP server)

[io.vascue/public-knowledge-search on the MCP Registry] [CI] [License: MIT] [public-knowledge-search MCP server]

[public-knowledge-search MCP server]

A Model Context Protocol server that searches Vascue's public documentation: healthcare operations, Vascue Front Desk for clinics, provider-side insurance claims automation, practice-management integrations (two-way sync with Cliniko and Nookal; Jane, Mindbody, PracticeHub, HexaHealth, Halaxy, Clinicea, ClinicOffice, Semble, Plato Medical and JERA in progress), security, case studies and pricing.

It comes in two equivalent forms:

  • Hosted (always current): https://www.vascue.io/mcp/search - streamable HTTP, no authentication.

  • Self-contained (this repo): python server.py - local BM25 search over a bundled snapshot of the public pages (content/, refreshed per release with scripts/fetch_content.py). No network calls at runtime, so it also works offline and is what directory-built releases run.

  • Endpoint: https://www.vascue.io/mcp/search (streamable HTTP, no authentication)

  • Server card: https://www.vascue.io/.well-known/mcp/server-card.json

  • Registry name: io.vascue/public-knowledge-search

  • Operated by: Vascue Limited (ISO 27001 certified)

Public content only. This server indexes public product and educational pages. Never send patient information, claim documents, clinic credentials or booking requests to it. Agent-based clinic booking is a separate research pilot, not a public API.

Connect

Any MCP client that speaks streamable HTTP can connect to the endpoint directly.

Claude Code

bash
claude mcp add --transport http vascue-search https://www.vascue.io/mcp/search

Cursor / Claude Desktop / other stdio-only clients (via mcp-remote)

json
{  "mcpServers": {    "vascue-search": {      "command": "npx",      "args": ["-y", "mcp-remote", "https://www.vascue.io/mcp/search"]    }  }}

Self-contained local server (stdio; bundled snapshot, no network)

bash
pip install -r requirements.txtpython server.py

Docker (builds the self-contained server)

bash
docker build -t vascue-public-knowledge-search .docker run -i --rm vascue-public-knowledge-search

Tools

One tool, search, in both forms: no authentication, read-only. The inputs differ between the hosted endpoint and the local server.

Hosted endpoint (https://www.vascue.io/mcp/search)

Hybrid (keyword + vector) search over Vascue's public pages. Returns matching excerpts with their canonical https://www.vascue.io/... URLs so answers can cite the source.

InputTypeNotes
querystring (required)Natural-language question or keywords, e.g. "how does Vascue handle insurance claim pre-authorisation".
ai_search_options.retrieval.retrieval_type"hybrid" | "vector" | "keyword"Default hybrid.
ai_search_options.retrieval.max_num_resultsinteger 1–50Default 8.
ai_search_options.retrieval.match_thresholdnumber 0–1Default 0.35.
ai_search_options.retrieval.context_expansioninteger 0–3Neighbouring chunks to include.

Query rewriting and reranking are disabled server-side; the server returns source chunks only and never a generated answer, so nothing is presented as a Vascue statement without a citation. Rate limit: 60 requests per minute per client.

Example call:

json
{ "name": "search", "arguments": { "query": "Cliniko integration for Vascue Front Desk" } }

The endpoint is backed by a Cloudflare AI Search instance over the approved public Markdown export of vascue.io (the service descriptor at https://www.vascue.io/.well-known/ai-search.json states what is and is not indexed).

Local server (server.py)

BM25 keyword search over the bundled content/ snapshot. No network calls at runtime. Returns {"chunks": [...]}, each chunk with url, title, score (0–1, relative to the best match) and text.

InputTypeNotes
querystring (required)Natural-language question or keywords; 3–15 words, one topic per call.
max_num_resultsinteger 1–50Default 8.

Example call:

json
{ "name": "search", "arguments": { "query": "Cliniko integration", "max_num_results": 5 } }

Development

bash
docker build -t vascue-public-knowledge-search .node scripts/smoke.mjs docker run -i --rm vascue-public-knowledge-search   # initialize -> tools/listnode scripts/smoke.mjs npx -y mcp-remote https://www.vascue.io/mcp/search --transport http-only

CI runs the same build and smoke test on every push and weekly, so the badge above doubles as an endpoint health indicator.

Directory build specs

Directories that build the server from source (e.g. Glama) run the self-contained form. Generated build images vary (uv-managed Python without pip, or a PEP 668 externally-managed system Python), so use an explicit venv:

  • Build steps: ["uv venv /opt/venv && uv pip install --python /opt/venv/bin/python -r requirements.txt"]
  • CMD: ["/opt/venv/bin/python", "server.py"]
  • No environment variables.

Where a normal pip exists, plain pip install -r requirements.txt + ["python", "server.py"] works too.

bash
pip install -r requirements.txtSMOKE_CALL_QUERY="Cliniko integration" node scripts/smoke.mjs python server.py   # local servernode scripts/smoke.mjs python bridge.py                                          # stdio bridge to the hosted endpointpython scripts/fetch_content.py                                                  # refresh the content/ snapshot

Other machine-readable surfaces

  • https://www.vascue.io/llms.txt
  • https://www.vascue.io/openapi.json (public, read-only content API)
  • https://www.vascue.io/.well-known/agent-skills/index.json (agent skills; also at vascue-io/skills)

Licence

This repository (README, manifest, Dockerfile) is MIT licensed. The content served by the endpoint is Vascue's public website content.

Source: README.md at commit 5c4c73a

Tools

1

Version history

2
  1. v1.2.0LatestOct 30, 2026
  2. v1.1.0Sep 16, 2026

Score

100% 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