Skip to content
RegimeShift logo

RegimeShift MCP server

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

read 2026-10-27

← Back to RegimeShift

Whose server it is
  • Registry namexyz.regimeshift/mcpverified in the MCP registry

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

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools4
  • Server calls itselfregimeshift
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 940 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 2 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: 2, the first on 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer1020 ms
  • Space in an agent's context≈ 532 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsB · 83 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Not saying whether it only reads or can destroy: 4 of 4

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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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 offers4 tools · read 2026-10-27
  • eth_vrp

    ETH Volatility Risk Premium (DVOL minus Parkinson realized vol, 72h). Positive = sell-vol opportunity, negative = buy-vol. Returns regime (LOW/MID/HIGH) and raw audit inputs (DVOL, RV_72h, RV_6h, spot). Live (~60s cache). $0.001 USDC on…

  • btc_vrp

    BTC Volatility Risk Premium (DVOL minus Parkinson realized vol, 72h). Positive = sell-vol opportunity, negative = buy-vol. Returns regime (LOW/MID/HIGH) and raw audit inputs (DVOL, RV_72h, RV_6h, spot). Live (~60s cache). $0.001 USDC on…

  • agent_sofr

    Agent-SOFR: decentralized USD short-rate benchmark for AI agents (weighted-median of 7 sources + variance + regime premiums; BNS-calibrated 6-mode classifier). Use as the risk-free benchmark for lend/borrow decisions. Returns annualized…

  • max_ltv

    Maximum-safe LTV for a collateralized agent loan — from variance over the loan horizon plus a 6-mode regime cap. Returns max_ltv, the math vs regime-cap binding constraint (so the agent sees WHY), regime, and sigma over the horizon…

How to connect

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

{
  "mcpServers": {
    "regimeshift": {
      "type": "http",
      "url": "https://mcp.regimeshift.xyz/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http regimeshift https://mcp.regimeshift.xyz/mcp

Add to CursorAdd to VS Code

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

OpenAPI spec

18 paths, read 2026-10-27. 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.