How do I connect an AI agent to savvly?

Use the MCP streamable HTTP endpoint https://api.savvly.com/mcp.

Catalog › com.savvly/savvly

Is savvly reliable?

Flaky Partly. Faceabot measured savvly 22 times and only 96% of checks succeeded. Plan a fallback. It also does the job: its real read-only task worked 21 of 21 times.

Last check: 2026-10-13 03:41 UTC · answered in 8000 ms · remote (no install)

En français : Instable. Faceabot teste cet outil lui-même, en continu, sans dépendre de ce que son auteur affirme.

What it does

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

Source: official MCP registry (registry.modelcontextprotocol.io) · version 1.0.98 · publisher website

Connect your agent

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

Or ask Faceabot first: MCP tool check_reliability {"id":"com.savvly/savvly"} on https://faceabot.com/api/mcp.

Does it actually do the job?

Does the job (tested) — Faceabot asked get_savvly_faq to do a small read-only task 21 time(s): 21 returned a real result, the last 21 in a row. Last result: ok in 3770 ms.

Sample input: {}. A success means a non-empty result without error; it does not certify the accuracy or safety of the content.

Faceabot measurements

When	Answers	Real task	Latency
2026-10-13 03:41 UTC	❌ timeout		8000 ms
2026-10-12 21:35 UTC	✅ ok	✅ done	9252 ms
2026-10-12 15:32 UTC	✅ ok	✅ done	7220 ms
2026-10-12 09:20 UTC	✅ ok	✅ done	9650 ms
2026-10-12 03:16 UTC	✅ ok	✅ done	9396 ms
2026-10-11 21:11 UTC	✅ ok	✅ done	6930 ms
2026-10-11 15:01 UTC	✅ ok	✅ done	9517 ms
2026-10-11 08:55 UTC	✅ ok	✅ done	7751 ms
2026-10-11 02:50 UTC	✅ ok	✅ done	7694 ms
2026-10-10 20:45 UTC	✅ ok	✅ done	7902 ms
2026-10-10 14:40 UTC	✅ ok	✅ done	7245 ms
2026-10-10 08:31 UTC	✅ ok	✅ done	10074 ms
2026-10-10 02:21 UTC	✅ ok	✅ done	9678 ms
2026-10-09 19:55 UTC	✅ ok	✅ done	10398 ms
2026-10-09 13:01 UTC	✅ ok	✅ done	8543 ms
2026-10-09 05:35 UTC	✅ ok	✅ done	10432 ms
2026-10-08 21:01 UTC	✅ ok	✅ done	9791 ms
2026-10-08 11:50 UTC	✅ ok	✅ done	9502 ms
2026-10-08 02:25 UTC	✅ ok	✅ done	7961 ms
2026-10-07 16:10 UTC	✅ ok	✅ done	8090 ms

Method: MCP initialize then tools/list from Faceabot (FaceabotProbe/1.0), plus one read-only tool call with a neutral input when the server declares one, repeated over time. This checks that the server is up and speaks MCP correctly; it does not certify the quality or safety of each tool. How measurement works.

Find tools similar to savvly →

Publisher of savvly?

Show your measured reliability on your README or website:

[![Measured by Faceabot](https://faceabot.com/badge/com.savvly/savvly.svg)](https://faceabot.com/tools/com.savvly/savvly)

Data in JSON: /api/catalog?id=com.savvly/savvly · Stop probes: POST /api/reliability/opt-out

AI agents: all of this is available without keys over MCP https://faceabot.com/api/mcp · HTTP https://faceabot.com/api/catalog?q=… · Guide : llms.txt

Best tool by topic · Pulse: what is changing in agent commerce · Is your store ready for AI shopping agents? · State of MCP (weekly) · MCP server doctor · Reliability data · Faceabot app · Faceabot → AI assistants · What AI agents cannot find yet · Add Faceabot to your AI · Badge for tool publishers · Help · Privacy · Terms