
WealthSchema MCP server
Which servers in the official MCP registry are WealthSchema's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-19
- Registry namecom.wealthschema/mcpverified in the MCP registry
The registry name sits under wealthschema.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-19
- Tools8
- Server calls itselfwealthschema
- Server version0.1.0
- Protocol version2025-06-18
On 2026-10-19 the server answered initialize and tools/list without a sign-in. First answer in 189 ms.
- Whether its tools do the product's job has not been judged yet.
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.
- INITE MCP score94 of 100answers 100 · definitions 83 · context 100
- Answered100% of days8 of 8 daily checks
- Median first answer244 ms
- Space in an agent's context≈ 838 tokensthe definitions of all its tools (8), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 8 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 8 of 8
What an agent can do with it
- not sure · Test AI agents against decisions with known answer keys
- not sure · Pull cited 2026 tax limits into software at request time
- not sure · Build and demo without real customer data
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 (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 →
list_archetypesList all synthetic household archetypes (id, name, life stage, wealth tier, household type).
list_bundlesList product bundles (themed household datasets) with use cases and one-time-purchase links.
get_sample_householdGet one deliberately-insufficient sample household (PII removed, dollar amounts banded, 96-month trajectory truncated to 12 months, projections withheld). Free sample archetypes: F-01, A-01, H-01, H-02, S-01, R-01, RE-01, RL-01. Other…
describe_household_schemaDescribe the top-level fields of a synthetic household record.
get_purchase_linkGet the one-time-purchase product URL for a bundle.
list_reference_parametersList the U.S. federal financial-planning parameters for a tax year (keys, labels, domains), marking which are in the free sample. Optionally filter by domain.
get_reference_parameterGet a source-verified U.S. federal financial-planning parameter by key and tax year, with its value and primary-source citation. Without a paid key, only the headline free-sample figures return values.
get_planning_benchmarkGet Planning Benchmark v2 - 50 free evaluation tasks for AI financial-advice systems with answer keys by construction: required figures cited to primary source documents, wrong-but-plausible stale values enumerated with reason codes (the…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"wealthschema": {
"type": "http",
"url": "https://www.wealthschema.com/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http wealthschema https://www.wealthschema.com/api/mcpclaude.ai, ChatGPT and other clients: add https://www.wealthschema.com/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.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.