
Ecocitizenz MCP server
Which MCP servers are Ecocitizenz'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 2026-10-24
- Registry namecom.ecocitizenz/trust-mcpverified in the MCP registry
The registry name sits under ecocitizenz.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-24
- Tools7
- Server calls itselfeczid-trust-mcp
- Server version0.2.0
- Protocol version2025-06-18
On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 657 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 4 of the 7 days it takes to judge reliability.
Once connected
- create_request_to_resolve change data without a sign-in: anyone with the address can call them.
- Parameters are untyped or undescribed in 2 of 7 tools: check arguments before calling.
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: 4 so far
- Answeredmeasuring4 of the 7 daily checks it takes to print a share
- Median first answer668 ms
- Space in an agent's context≈ 1,185 tokensthe definitions of all its tools (7), which an agent carries on every turn
- Tool definitionsB · 79 of 100
- Typed results0 of 7 toolsdeclared outputSchema: results come typed, read once
- Parameters without a description: in 2 of 7
- Not saying whether it only reads or can destroy: 7 of 7
What an agent can do with it
- cannot · register identities for agents, MCP servers and APIs
- not sure · check whether an operator may act before an action runs
- not sure · examine recorded evidence of what a machine action did
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_request_to_resolve
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 →
resolve_identityResolve an ECZ-ID through the public ECZ-ID Resolver and return the exact canonical state with checked_at, Resolver proof link, re-check action and the local-policy caveat. Never asserts safety, approval or compliance.
get_current_stateReturn the narrow current Resolver-derived state for an ECZ-ID (state, checked_at, Resolver link). No risk/safety/compliance inference.
get_resolver_linkReturn the deterministic public Resolver proof/re-check URL for an ECZ-ID. No network call.
explain_statusDeterministically render the exact ECZ-ID status using the claims-safe renderer (VERIFIED is an ECZ-ID state, not a Microsoft certification). Absence of evidence renders the approved neutral wording — never "unsafe". No LLM.
find_productGiven narrow context flags, return ONE best next ECZ-ID product action (free/community routes win where correct; neutral context routes to free public verification).
get_install_instructionsReturn deterministic official install/discovery routes for an ECZ-ID product or surface (canonical URLs only; planned Microsoft surfaces carry no URLs).
create_request_to_resolveAUTHENTICATED: create a neutral, shareable request for independently re-checkable ECZ-ID evidence. Requires a Microsoft Entra bearer token with the RequestToResolve.Create scope (or app role). It never verifies a target, never sends…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"trust-mcp": {
"type": "http",
"url": "https://trust-mcp.ecocitizenz.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http ecocitizenz https://trust-mcp.ecocitizenz.com/mcpclaude.ai, ChatGPT and other clients: add https://trust-mcp.ecocitizenz.com/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.