
S2Reason MCP server
Which servers in the official MCP registry are S2Reason's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-20
- Registry namecom.s2reason/medicare-fee-scheduleverified in the MCP registry
The registry name sits under s2reason.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-20
- Tools2
- Server calls itselfs2reason
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-20 the server answered initialize and tools/list without a sign-in. First answer in 343 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 3 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.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer834 ms
- Space in an agent's context≈ 1,061 tokensthe definitions of all its tools (2), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results2 of 2 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · price each charge line against Medicare and UCR rates
- cannot · trace unlisted charge descriptions to CPT codes via hospital price files
- not sure · produce a cited bill reasonableness report in minutes
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 →
medicare_get_physician_feeUse this when you need what Medicare's Physician Fee Schedule allows for a CPT or HCPCS code on a given date of service, for the nation or for one state or locality, in the office or facility setting. It takes up to 25 lines (code…
medicare_list_fee_releasesUse this when you need to know which CMS Medicare Physician Fee Schedule releases the archive holds, with their effective dates, CMS source files, SHA-256 checksums and any gaps in coverage, before or instead of looking up a fee. It takes…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"medicare-fee-schedule": {
"type": "http",
"url": "https://s2reason.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http s2reason https://s2reason.com/mcpclaude.ai, ChatGPT and other clients: add https://s2reason.com/mcp as a custom connector in the settings.
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.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.