Skip to content
Sentralis logo

Sentralis MCP server

Which MCP servers are Sentralis'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 2026-10-26

← Back to Sentralis

Whose server it is
  • Registry nameio.sentralis/portfolio-riskverified in the MCP registry

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

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools4
  • Server calls itselfsentralis-portfolio-risk
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 721 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: estimate realistic losses in a bad month from history; replay portfolio through past market shocks.
  • Checked on 2 of the 7 days it takes to judge reliability.

Once connected

  • For "estimate realistic losses in a bad month from history", the likely first call is list_risk_engines.
  • For "replay portfolio through past market shocks", the likely first call is list_risk_engines.
  • Parameters are untyped or undescribed in 3 of 4 tools: check arguments before calling.

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 2026-10-26
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
  • What an agent can do with it2 of 2 use cases
  • Answeredmeasuring2 of the 7 daily checks it takes to print a share
  • Median first answer848 ms
  • Space in an agent's context≈ 715 tokensthe definitions of all its tools (4), which an agent carries on every turn
  • Tool definitionsC · 71 of 100
  • Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 3 of 4
  • Not saying whether it only reads or can destroy: 4 of 4

What an agent can do with it

  • can do · estimate realistic losses in a bad month from history
  • can do · replay portfolio through past market shocks
  • not sure · check how much of a position could exit without slippage

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 (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 2026-10-26
  • list_risk_engines

    List the available risk-analysis engines with their JSON-Schema config contracts, limits, and asOfDate (point-in-time) support. Call this before run_risk_analysis to learn the exact config fields each engine requires.

  • list_supported_symbols

    Search the supported asset universe (max 100 results). Preflight inline-portfolio symbols here — unknown symbols are dropped from valuation or yield INSUFFICIENT_DATA.

  • run_risk_analysis

    Submit a risk analysis (engines: monte-carlo, historical-replay, sector-concentration-stress, liquidity-stress, correlation-regime-stress, counterparty-infrastructure-risk, factor-shock, macro-sensitivity). Provide EXACTLY ONE portfolio…

  • get_analysis_result

    Fetch an analysis by id. status=queued → poll again shortly; succeeded → result contains the risk envelope ({ok:true, result} or a persisted domain error like INSUFFICIENT_DATA) plus resolved data dates and the deterministic inputs hash…

How to connect

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

{
  "mcpServers": {
    "portfolio-risk": {
      "type": "http",
      "url": "https://app.sentralis.io/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http sentralis https://app.sentralis.io/api/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://app.sentralis.io/api/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.