Skip to content
SaveWell logo

SaveWell MCP server

Which servers in the official MCP registry are SaveWell's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-22

← Back to SaveWell

Whose server it is
  • Registry namecom.savewellnow/careverified in the MCP registry

The registry name sits under savewellnow.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-22
  • Stateanswerschecked 2026-10-22
  • Tools2
  • Server calls itselfsavewell
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-22 the server answered initialize and tools/list without a sign-in. First answer in 305 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 1 of the 7 days it takes to judge reliability.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-22
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer1525 ms
  • Space in an agent's context≈ 401 tokensthe definitions of all its tools (2), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results0 of 2 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

What an agent can do with it

  • can do · compare surgery center and hospital costs in your county
  • not sure · find nearby specialists for an upcoming procedure
  • not sure · estimate coinsurance difference between surgery centers and hospitals

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers2 tools · read 2026-10-22
  • list_procedures

    List the outpatient procedures SaveWell compares for people with Original Medicare, with the id to pass to find_care.

  • find_care

    For a person with Original Medicare (not Medicare Advantage), compare what a procedure costs them at an outpatient surgery center versus a hospital in their county, any SaveWell reward with a Medigap plan, and SaveWell-network specialists…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "care": {
      "type": "http",
      "url": "https://savewellnow.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http savewellnow https://savewellnow.com/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://savewellnow.com/mcp as a custom connector in the settings.

OpenAPI spec

2 paths, read 2026-10-22. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.