Data · Remote MCP server

Savvly

Savvly MCP: query fund data, model projections, and compare against alternative retirement products.

Visit Savvly's website

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
com.savvly/savvly
Version
1.0.93
Status
Active
Category
data
Transport
Streamable HTTP, stdio (local process)
Package
npm, PyPI, NuGet, OCI image (Docker), MCP Bundle (.mcpb)
Published
2026-09-09
Updated
2026-09-09
Publisher
com.savvly
Website
savvly.com
Repository
github.com/Savvly/savvly-mcp
Source
Registry API entry

Remote endpoints

TransportURLHeaders declared
Streamable HTTPhttps://api.savvly.com/mcpNone

Packages

RegistryPackageVersionTransportEnvironment variables
npmruntime: npx@savvly/mcp-server1.0.93stdioNone declared
PyPIruntime: uvxsavvly-mcp-server1.0.93stdioNone declared
NuGetruntime: dnxSavvly.McpServer1.0.93stdioNone declared
OCI image (Docker)ghcr.io/savvly/savvly-mcp-server:1.0.93—stdioNone declared
MCP Bundle (.mcpb)https://github.com/Savvly/savvly-mcp/releases/download/v1.0.93/savvly-mcp-server.mcpbSHA-256 checksum stated—stdioNone declared

How to connect Savvly

Savvly is a remote MCP server: there is nothing to install. Its endpoint is https://api.savvly.com/mcp, served over Streamable HTTP. In an assistant that accepts remote MCP servers (often under a setting named connectors, integrations or tools), add a new server and give it this URL; in a client configured by file, add it as a remote (HTTP) server with the same URL.

No headers are declared in the registry entry. If the server needs you to sign in, a client that supports MCP authorization opens the service's own sign-in page when it first connects.

It can also run locally from a Node.js package published to the npm registry: @savvly/mcp-server version 1.0.93. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @savvly/mcp-server@1.0.93.

It can also run locally from a Python package published to PyPI: savvly-mcp-server version 1.0.93. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install — the usual command is uvx savvly-mcp-server.

It can also run locally from a .NET package published to NuGet: Savvly.McpServer version 1.0.93. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs the .NET SDK; run as a .NET tool; the entry names dnx as the runtime.

It can also run locally from a container image in an OCI registry such as Docker Hub or GitHub Container Registry: ghcr.io/savvly/savvly-mcp-server:1.0.93. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Docker or another OCI container runtime; started with docker run — the usual command is docker run -i --rm ghcr.io/savvly/savvly-mcp-server:1.0.93.

It can also run locally from an MCP Bundle: a single downloadable archive holding a local server and a manifest that describes it: https://github.com/Savvly/savvly-mcp/releases/download/v1.0.93/savvly-mcp-server.mcpb. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs a client that installs MCP Bundles; the file is opened in, or added to, that client.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "savvly": {
      "command": "npx",
      "args": [
        "-y",
        "@savvly/mcp-server@1.0.93"
      ]
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More data servers

All 4,395 →
ServerRunsEndpoint or package
Santismm Knowledge — Harness Engineering, Agentic AI & GovernanceQuery core AI knowledge, essays, executable Labs, Homeric data and epistemic claims.Remote · HTTPsantismm.com
Satnogs MCPSatNOGS DB: satellite transmitter and observation data.Local · stdionpm: satnogs-mcp
Save This OneSave, search, read, tag, and organize your bookmarks from AI assistants with OAuth sign-in.Remote · HTTPmcp.savethisone.com
SaveeRead your Savee saves, boards and home feed, and search its public library. Read-only.Remote · HTTPmcp.savee.com
Saylor Innovations: pay-per-call data271 x402 agent APIs: research, law, medicine, science, finance, public data, security and crypto.Remote · HTTPsaylorinnovations.com
sayouPersistent knowledge workspace for AI agents. Versioned files, search, and MCP tools.Local · stdioPyPI: sayou
ScalpStreamPay-per-call data over x402: air quality, border waits, fuel prices, market research.Local · stdioOCI image (Docker): ghcr.io/dv1-321/scalpstream-mcp:v0.1.6
ScanbaseWebsite compliance checks for Russian personal data law 152-FZ: score, violations, fix instructions.Local · stdionpm: scanbase-mcp