Skip to content
Savvly logo

Savvly MCP server

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

read 2026-10-17

← Back to Savvly

Whose server it is
  • Registry namecom.savvly/savvlyverified in the MCP registry

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

When we asked itchecked 2026-10-17
  • Stateanswerschecked 2026-10-17
  • Tools8
  • Server calls itselfsavvly
  • Server version1.0.97
  • Protocol version2025-06-18

On 2026-10-17 the server answered initialize and tools/list without a sign-in. First answer in 223 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 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.

Measured dailydaily checks: 3, the first on 2026-10-19
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • Use568 PyPI downloads a week3 GitHub stars
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer233 ms
  • Space in an agent's context≈ 5,070 tokensthe definitions of all its tools (8), which an agent carries on every turn
  • Tool definitionsA · 100 of 100
  • Typed results8 of 8 toolsdeclared outputSchema: results come typed, read once
  • Every tool passes all six checks.

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 offers8 tools · read 2026-10-17
  • get_savvly_product_info

    Get complete product information about Savvly, an SEC-registered security offering longevity protection — use it whenever the user asks what Savvly is, how it works, its expenses, eligibility, or payouts, or wants an overview. Pass…

  • compare_savvly_vs_alternative

    Get a structured comparison between Savvly and another retirement product type — use it whenever the user compares Savvly to annuities, target-date funds, managed-payout funds, or any alternative, or asks how Savvly stacks up. It renders…

  • project_savvly_lumpsum

    Retirement projection for a lump-sum investment in the Savvly Longevity Benefit. Returns payout amounts at each milestone age (80, 85, 90, 95) with Savvly vs market alone cumulative totals, per-age breakdowns, and server-provided…

  • project_savvly_monthly

    Retirement projection for monthly contributions to the Savvly Longevity Benefit over a number of years. Returns payout amounts at milestone ages 80/85/90/95 with Savvly vs market alone cumulative totals, per-age breakdowns, and…

  • project_retirement_with_savvly

    Full retirement simulation showing the projected savings trajectory WITH and WITHOUT a Savvly allocation across the planning horizon (current_age → life_expectancy). Requires current_age ≤ retirement_age ≤ life_expectancy. Returns…

  • check_savvly_eligibility

    Check if a person is eligible to invest in the Savvly Longevity Benefit. Eligibility is based on age (no minimum; maximum enrollment age 75), US residency, and distribution channel (individual, employer-sponsored, advisor-placed). Use…

  • get_savvly_faq

    Get answers to frequently asked questions about Savvly. Use when the user has specific questions about how Savvly works, expenses, withdrawals, or regulatory status. It is a convenience view of `search_savvly_content` scoped to the…

  • search_savvly_content

    Search the Savvly Q&A Content Library — audience-tagged questions and answers compiled from Savvly's marketing collateral plus the factual FAQ, organized by stakeholder (employee, advisor, broker, employer, universal, general) and section…

How to connect

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

{
  "mcpServers": {
    "savvly": {
      "type": "http",
      "url": "https://api.savvly.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http savvly https://api.savvly.com/mcp

Add to CursorAdd to VS Code

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

Also shipped through: mcpb, npm, nuget, oci, pypi

OpenAPI spec

12 paths, read 2026-10-17. 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.