Dutiful MCP server
Which MCP servers are Dutiful'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 2026-10-29
- Registry namework.dutiful/dutifulverified in the MCP registry
The registry name sits under dutiful.work. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-29
- Tools3
- Server calls itselflookthrough
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-29 the server answered initialize and tools/list without a sign-in. First answer in 81 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 6 of the 7 days it takes to judge reliability.
Once connected
- create_order change data without a sign-in: anyone with the address can call them.
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: 6 so far
- Answeredmeasuring6 of the 7 daily checks it takes to print a share
- Median first answer98 ms
- Space in an agent's context≈ 496 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · research a company using registry facts and sanctions
- not sure · check a company's officers and owners
- cannot · look up US import value for product categories
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
- Tools that change data, on a server that answers without a sign-in: create_order
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 →
check_coverageFree. Searches the official company register of the given country for the company name and returns the matching entities (idx, registry reference, name, address), an order id, and what a report covers. Nothing is charged. Supported…
create_orderSelects one entity from the check_coverage results (idx, starting at 0) and returns the x402 payment requirements for a report (USDC on Base, exact amount in the requirements). This tool does not pay. To pay, send the signed payment in a…
get_reportReturns the status of an order and, once delivered, the report (structured JSON and plain text). Status values: pending_entity, pending_payment, paid, delivered. An unpaid order returns its payment requirements.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"dutiful": {
"type": "http",
"url": "https://dutiful.work/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http dutiful https://dutiful.work/mcpclaude.ai, ChatGPT and other clients: add https://dutiful.work/mcp as a custom connector in the settings.
OpenAPI spec
6 paths, read 2026-10-29. Open the spec ↗
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.
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.