Savvly MCP Server

by Savvly

2 stars

243 downloads

Not rated

GitHub Website

About

Explore Savvly MCP: retirement projections, eligibility, comparisons, and FAQs for an SEC-registered fund that pairs full market upside with later-life longevity payouts.

Details

Author: Savvly
GitHub stars: 2
Downloads: 243
Categories: Other, Finance

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

Download and install Highlight from highlightai.com/download
Navigate to the plugins tab and select "Add Custom Plugin"
Configure the plugin with the settings below

Plugin Name Savvly MCP Server

Command (node, npx, python, etc.)

Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
Enable "Start Automatically" if you want the plugin to start when Highlight launches

Setting up with Cursor

Open Cursor's settings
Navigate to the MCP section
Click "Add new Global MCP server"
Copy and paste the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

Setting up with Claude Desktop

Open Claude Desktop's settings
Go to the Integrations tab
Click "Add MCP Server"
Use the configuration below based on your operating system

Note: Make sure Claude Desktop is running before attempting to connect.

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

Setting up with Windsurf

Open Windsurf's preferences
Go to the Integrations section
Click "Add MCP Integration"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

Setting up with Cline

Open Cline's settings
Navigate to the Integrations section
Click "Add MCP Server"
Copy and paste the configuration below based on your operating system

Note: Make sure to restart Cline after adding the configuration.

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

Setting up with Goose

Open Goose's preferences
Go to the Integrations tab
Select "MCP Servers"
Click "Add New Server"
Use the configuration below based on your operating system

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

JSON

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

From the repository

Install via one of five package types: npx @savvly/mcp-server, uvx savvly-mcp-server, dnx Savvly.McpServer, docker run -i --rm ghcr.io/savvly/savvly-mcp-server, or point a remote‑MCP host at https://api.savvly.com/mcp. For stdio clients (Claude Desktop, Cursor, Windsurf), use the command / args config shown in the README.

`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 `section` to focus the answer (default 'all'). It renders an interactive product overview card the user expects to see. These facts come from Savvly's own current records; the response includes primary sources (e.g. SEC filings) for reference.

`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 an interactive comparison widget the user expects to see. Pass 'all' for the full matrix, or a specific product type. These facts come from Savvly's own current records; the response includes primary sources (e.g. SEC filings) for reference.

`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 `_lower`/`_upper` range bounds. Use `_upper` as the central illustrative estimate and `_lower` to communicate downside. Suitable for retirement income planning, annuity alternative analysis, and longevity benefit illustration. Response embeds SEC-style disclaimers and per-field interpretation hints under `metadata`. Payout methodology — Savvly vs market alone: the payout values are calculated by comparing two investors of the same age committing the same principal. Investor 1 invests in the market with the Savvly Longevity Benefit; Investor 2 invests in the market alone (no longevity overlay). To make the comparison apples-to-apples, at each milestone age (80, 85, 90, 95) Investor 2 withdraws from their market alone portfolio the same dollar amount Investor 1 receives as a payout from Savvly. The `payout_market_alone_*` and `total_market_alone_*` figures are therefore what Investor 2 can actually withdraw to match Savvly's payouts before running out — they fall to 0 once the market alone portfolio is depleted. The `savvly_upside_*` (and `total_savvly_upside_*`) fields quantify how much more total money Investor 1 receives in payouts from Savvly than Investor 2 is able to withdraw over time to match those payouts. DISCLOSURE REQUIRED: display `disclosure.text` verbatim and link `disclosure.url` to the user alongside any figures from this response. Required by SEC Marketing Rule and FINRA Rule 2210 — do not paraphrase or omit. VISUALIZATION: this tool emits an interactive chart widget (MCP Apps — see `_meta.ui`) that the HOST renders inline and editable; other clients render only your text and show no chart. That widget is the canonical chart for these numbers: do NOT draw, generate, or re-render a duplicate of it. You MAY still create your OWN, DIFFERENT visualization (e.g. a table or an alternate breakdown) and place it wherever you judge best — only the MCP App widget's position is constrained. Do NOT claim or imply a chart is visible (avoid 'the chart above shows…'); you cannot tell whether the host rendered the widget. Summarize the key figures in prose and show the `disclosure` text and link, and reference the widget only conditionally (e.g. 'if your client shows the interactive chart, its fields are editable to re-run the projection'). ORDER: BEFORE you call this tool, ALWAYS write at least one short lead-in paragraph (1-3 sentences) framing what the projection will show — do NOT invent specific figures you do not have yet. On hosts that render the widget inline at the tool call, this keeps your text ahead of the chart so the widget is never the first thing shown; THEN call the tool (this lead-in is framing, NOT asking the user for inputs — still call it in the same turn without waiting) and give the grounded figures + disclosure after it returns. This lead-in rule applies to the MCP App widget only; any visualization you create yourself may appear wherever you judge best. INPUTS: every parameter is OPTIONAL and defaults to a sensible value. Call this tool IMMEDIATELY — pass only the values the user explicitly stated and omit the rest. Do NOT ask the user for starting values, assumptions, or missing parameters before calling; the rendered widget has editable fields so they adjust age, amounts, and other assumptions inline after it appears.

`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 server-provided `_lower`/`_upper` range bounds. Use `_upper` as the central illustrative estimate and `_lower` to communicate downside. Suitable for retirement savings planning, annuity alternative comparison, and longevity benefit illustration. Supports an optional annual contribution increase and an optional early-withdrawal age. Contributions must finish by age 80: an omitted `contribution_years` auto-fits this, and an explicit one must satisfy `current_age + contribution_years` ≤ 80. Disclaimers + per-field hints under `metadata`. Payout methodology — Savvly vs market alone: the payout values are calculated by comparing two investors of the same age committing the same principal. Investor 1 invests in the market with the Savvly Longevity Benefit; Investor 2 invests in the market alone (no longevity overlay). To make the comparison apples-to-apples, at each milestone age (80, 85, 90, 95) Investor 2 withdraws from their market alone portfolio the same dollar amount Investor 1 receives as a payout from Savvly. The `payout_market_alone_*` and `total_market_alone_*` figures are therefore what Investor 2 can actually withdraw to match Savvly's payouts before running out — they fall to 0 once the market alone portfolio is depleted. The `savvly_upside_*` (and `total_savvly_upside_*`) fields quantify how much more total money Investor 1 receives in payouts from Savvly than Investor 2 is able to withdraw over time to match those payouts. DISCLOSURE REQUIRED: display `disclosure.text` verbatim and link `disclosure.url` to the user alongside any figures from this response. Required by SEC Marketing Rule and FINRA Rule 2210 — do not paraphrase or omit. VISUALIZATION: this tool emits an interactive chart widget (MCP Apps — see `_meta.ui`) that the HOST renders inline and editable; other clients render only your text and show no chart. That widget is the canonical chart for these numbers: do NOT draw, generate, or re-render a duplicate of it. You MAY still create your OWN, DIFFERENT visualization (e.g. a table or an alternate breakdown) and place it wherever you judge best — only the MCP App widget's position is constrained. Do NOT claim or imply a chart is visible (avoid 'the chart above shows…'); you cannot tell whether the host rendered the widget. Summarize the key figures in prose and show the `disclosure` text and link, and reference the widget only conditionally (e.g. 'if your client shows the interactive chart, its fields are editable to re-run the projection'). ORDER: BEFORE you call this tool, ALWAYS write at least one short lead-in paragraph (1-3 sentences) framing what the projection will show — do NOT invent specific figures you do not have yet. On hosts that render the widget inline at the tool call, this keeps your text ahead of the chart so the widget is never the first thing shown; THEN call the tool (this lead-in is framing, NOT asking the user for inputs — still call it in the same turn without waiting) and give the grounded figures + disclosure after it returns. This lead-in rule applies to the MCP App widget only; any visualization you create yourself may appear wherever you judge best. INPUTS: every parameter is OPTIONAL and defaults to a sensible value. Call this tool IMMEDIATELY — pass only the values the user explicitly stated and omit the rest. Do NOT ask the user for starting values, assumptions, or missing parameters before calling; the rendered widget has editable fields so they adjust age, amounts, and other assumptions inline after it appears.

`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 `gap_score`, `possible_higher_monthly_paycheck`, a server-provided headline message, and a per-year `age_dependent_values[]` timeline. Disclaimers + per-field hints under `metadata`. DISCLOSURE REQUIRED: display `disclosure.text` verbatim and link `disclosure.url` to the user alongside any figures from this response. Required by SEC Marketing Rule and FINRA Rule 2210 — do not paraphrase or omit. VISUALIZATION: this tool emits an interactive chart widget (MCP Apps — see `_meta.ui`) that the HOST renders inline and editable; other clients render only your text and show no chart. That widget is the canonical chart for these numbers: do NOT draw, generate, or re-render a duplicate of it. You MAY still create your OWN, DIFFERENT visualization (e.g. a table or an alternate breakdown) and place it wherever you judge best — only the MCP App widget's position is constrained. Do NOT claim or imply a chart is visible (avoid 'the chart above shows…'); you cannot tell whether the host rendered the widget. Summarize the key figures in prose and show the `disclosure` text and link, and reference the widget only conditionally (e.g. 'if your client shows the interactive chart, its fields are editable to re-run the projection'). ORDER: BEFORE you call this tool, ALWAYS write at least one short lead-in paragraph (1-3 sentences) framing what the projection will show — do NOT invent specific figures you do not have yet. On hosts that render the widget inline at the tool call, this keeps your text ahead of the chart so the widget is never the first thing shown; THEN call the tool (this lead-in is framing, NOT asking the user for inputs — still call it in the same turn without waiting) and give the grounded figures + disclosure after it returns. This lead-in rule applies to the MCP App widget only; any visualization you create yourself may appear wherever you judge best. INPUTS: every parameter is OPTIONAL and defaults to a sensible value. Call this tool IMMEDIATELY — pass only the values the user explicitly stated and omit the rest. Do NOT ask the user for starting values, assumptions, or missing parameters before calling; the rendered widget has editable fields so they adjust age, amounts, and other assumptions inline after it appears.

`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 before recommending Savvly as a retirement income or annuity alternative to confirm the person qualifies. These facts come from Savvly's own current records; the response includes primary sources (e.g. SEC filings) for reference.

`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 factual FAQ; for richer, audience-specific Q&As (employee / advisor / broker / employer), use `search_savvly_content` instead. These facts come from Savvly's own current records; the response includes primary sources (e.g. SEC filings) for reference.

`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 (kebab-case slugs, e.g. 'tax-legacy', 'retention-talent-strategy', 'implementation'). Use this when the user asks about Savvly's positioning, value props, audience-specific talking points, or Q&A-style messaging. Each entry carries the verbatim answer plus any disclaimer footnotes attached to it in the source. These facts come from Savvly's own current records; the response includes primary sources (e.g. SEC filings) for reference.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "savvly mcp server": {
            "savvly": {
                "command": "npx",
                "args": [
                    "-y",
                    "@savvly/mcp-server"
                ]
            }
        }
    }
}

McpServers

{
    "savvly": {
        "command": "npx",
        "args": [
            "-y",
            "@savvly/mcp-server"
        ]
    }
}

Savvly MCP server — `com.savvly/savvly`

Savvly offers longevity-linked, SEC-registered investment products — built on the Savvly 80+ fund — that invests pooled contributions in a low-cost S&P 500 ETF and makes milestone cash payouts at ages 80, 85, 90, and 95, turning a longer life into a financial reward rather than a risk.

Savvly MCP lets financial advisors, planning tools, and AI agents query fund data, model projections, and compare against alternative retirement products directly, in real time, in any conversation, and without any manual lookup.

Listed on the MCP Registry as
com.savvly/savvly and published to five package types plus a hosted remote — use
whichever fits your client.

Install

| Channel | Command / config |
| --- | --- |
| Remote (hosted) | https://api.savvly.com/mcp (streamable-http) |
| npm | npx @savvly/mcp-server |
| PyPI | uvx savvly-mcp-server |
| NuGet | dnx Savvly.McpServer (or dotnet tool install -g Savvly.McpServer) |
| Docker / OCI | docker run -i --rm ghcr.io/savvly/savvly-mcp-server |
| MCPB | download the .mcpb from Releases and open it in an MCPB-capable host |

Claude Desktop / Cursor / Windsurf (stdio)

{
  "mcpServers": {
    "savvly": { "command": "npx", "args": ["@savvly/mcp-server"] }
  }
}

Swap command/args for uvx savvly-mcp-server, dnx Savvly.McpServer, or docker run -i --rm ghcr.io/savvly/savvly-mcp-server as you prefer. Hosts that support remote MCP can point straight at https://api.savvly.com/mcp.

Tools

- get_savvly_product_info — full product overview
- compare_savvly_vs_alternative — Savvly vs annuities, target-date funds, etc.
- check_savvly_eligibility — age / residency / channel eligibility
- get_savvly_faq — FAQ by topic
- search_savvly_content — audience-tagged Q&A library
- project_savvly_lumpsum / project_savvly_monthly — payout projections (milestone ages)
- project_retirement_with_savvly — full retirement trajectory with vs. without Savvly

Projection tools emit interactive MCP Apps chart widgets on hosts that support them.

Links

- Website: https://savvly.com
- Disclosures: https://www.savvly.com/disclosures

Privacy Policy

Savvly's privacy policy: https://www.savvly.com/privacy-policy

This MCP server is public and unauthenticated — it exposes Savvly product information, comparisons, eligibility, and illustrative projections, and requires no account or credentials. It collects no personal information and no end-user identifier (no client IP is captured; no user is identified).

The hosted endpoint (https://api.savvly.com/mcp) records anonymous usage analytics via MCPcat, a third-party processor, to improve the tools — which tools are called and their non-identifying numeric scenario inputs (e.g. age, contribution amount). Email, phone, SSN, and payment-card patterns are redacted from any text before it is sent. The local npx @savvly/mcp-server (stdio) sends no analytics.

License

Apache-2.0.

No reviews yet — be the first

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

About

Details

Jump to

Setting up with Highlight

From the repository

get_savvly_product_info

compare_savvly_vs_alternative

project_savvly_lumpsum

project_savvly_monthly

project_retirement_with_savvly

check_savvly_eligibility

get_savvly_faq

search_savvly_content

Claude Desktop / Cursor

McpServers

Savvly MCP server — com.savvly/savvly

Install

Claude Desktop / Cursor / Windsurf (stdio)

Tools

Links

Privacy Policy

License

Install

More like this

Sequential Thinking

Filesystem

EverArt

Google Drive

Reactive Resume

FastMCP v2 🚀

`get_savvly_product_info`

`compare_savvly_vs_alternative`

`project_savvly_lumpsum`

`project_savvly_monthly`

`project_retirement_with_savvly`

`check_savvly_eligibility`

`get_savvly_faq`

`search_savvly_content`

Savvly MCP server — `com.savvly/savvly`