
FillTrust MCP server
Which servers in the official MCP registry are FillTrust's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-24
- Registry namecom.filltrust/questionsverified in the MCP registry
The registry name sits under filltrust.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-24
- Tools5
- Server calls itselffilltrust
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 172 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 3 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: 3 so far
- Answeredmeasuring3 of the 7 daily checks it takes to print a share
- Median first answer620 ms
- Space in an agent's context≈ 595 tokensthe definitions of all its tools (5), which an agent carries on every turn
- Tool definitionsB · 83 of 100
- Typed results0 of 5 toolsdeclared outputSchema: results come typed, read once
- Not saying whether it only reads or can destroy: 5 of 5
What an agent can do with it
- not sure · Draft vendor questionnaire answers from existing SOC 2 reports and policies
- not sure · Check each drafted answer against its source passage
- not sure · Leave unsupported questions blank for a person to answer
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 →
search_questionsFind guidance on how to answer a security questionnaire question. Search by the question text, a control area, or a standard and control identifier such as CEK-03. Returns matching entries with the URL of the page each came from.
get_questionThe complete published guidance for one questionnaire question: what it is really asking, which of your documents answers it, what evidence to attach, a model answer with the specifics left blank, the ways it usually goes wrong, and the…
list_standardsWhich questionnaire standards this corpus answers questions from, how many questions each has, and which controls are cited. Standards whose control lists are proprietary are named without reference numbers, on purpose.
get_filltrust_postureFillTrust's own answers to the questions it exists to answer, for anyone assessing it as a vendor. Includes the answers that are "no".
get_questionnaire_statisticsMeasured counts from 146 real vendor security questionnaires (17,697 questions) published by universities, purchasing consortia and companies: which topics are asked most, and detailed profiles of the questionnaires that have a name…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"questions": {
"type": "http",
"url": "https://www.filltrust.com/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http filltrust https://www.filltrust.com/api/mcpclaude.ai, ChatGPT and other clients: add https://www.filltrust.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.