
RestoreWorth MCP server
Which MCP servers are RestoreWorth's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-27
- Registry namecom.restoreworth/fema-dataverified in the MCP registry
The registry name sits under restoreworth.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-27
- Tools5
- Server calls itselfrestoreworth-fema-data
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 95 ms.
- Its tools do none of the product's use cases we checked: Check what a contractor quote includes; Estimate drywall replacement cost per square foot.
- Checked on 1 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.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- What an agent can do with it0 of 2 use cases
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer125 ms
- Space in an agent's context≈ 760 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · Estimate water damage restoration cost by affected area
- cannot · Check what a contractor quote includes
- cannot · Estimate drywall replacement cost per square foot
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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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 →
nfip_claims_by_stateNFIP paid building claims for one US state or DC, 2020-2024 (FEMA OpenFEMA, NFIP Redacted Claims v3): number of paid claims, quartiles and median of the amount paid, dominant flood event and its share. These are amounts paid by NFIP, not…
nfip_claims_by_countyNFIP paid building claims for one county, 2015-2024 and 2020-2024. Give a 5-digit FIPS code, or a county name and its state. A county absent from the table (it keeps counties with at least 100 paid claims) gets the state row, and the…
flood_damage_by_water_depthMedian damage ratio (FEMA actual cash value of the damage / actual cash value of the building) on NFIP paid claims 2015-2024, by interior water depth band and single-family one-floor segment. With building_value_usd, returns ratio x…
county_profileFEMA open-data profile of one county by 5-digit FIPS: NFIP paid claims summary, disaster declarations since 2000, FEMA inspections of owner applicants (Individuals and Households Program), NFIP Community Status Book and CRS classes. A…
list_sourcesLists every source file this server reads, with publisher, dataset page, terms, as-of and retrieval dates, and the RestoreWorth page that publishes it.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"fema-data": {
"type": "http",
"url": "https://restoreworth.com/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http restoreworth https://restoreworth.com/api/mcpclaude.ai, ChatGPT and other clients: add https://restoreworth.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.