Trust Live is an MCP server published by io.github.ChanghuLiu, hosted at mcp-selection-lab-production.up.railway.app. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 5 tools, including recommend_provider, compare_providers, get_provider_profile, get_capability, evaluate_safe_call.
Evidence-linked MCP selection and non-executing Safe-Call review; surfaces unknowns.
18 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Recommend a provider with hard-filter outcomes, component scores, evidence, and Safe-Call constraints.
| Parameter | Type | Description |
|---|---|---|
| task_requirements * | object | Structured capability, operation, auth, payment, data and evidence requirements. |
{
"name": "recommend_provider",
"description": "Recommend a provider with hard-filter outcomes, component scores, evidence, and Safe-Call constraints.",
"inputSchema": {
"type": "object",
"title": "recommend_providerArguments",
"required": [
"task_requirements"
],
"properties": {
"task_requirements": {
"type": "object",
"title": "Task Requirements",
"description": "Structured capability, operation, auth, payment, data and evidence requirements.",
"additionalProperties": true
}
}
},
"outputSchema": {
"type": "object",
"title": "recommend_providerDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Compare matching providers across capability, verification, safety, payment, freshness and unknowns.
| Parameter | Type | Description |
|---|---|---|
| task_requirements * | object | Structured task requirements. |
{
"name": "compare_providers",
"description": "Compare matching providers across capability, verification, safety, payment, freshness and unknowns.",
"inputSchema": {
"type": "object",
"title": "compare_providersArguments",
"required": [
"task_requirements"
],
"properties": {
"task_requirements": {
"type": "object",
"title": "Task Requirements",
"description": "Structured task requirements.",
"additionalProperties": true
}
}
},
"outputSchema": {
"type": "object",
"title": "compare_providersDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Get a canonical provider profile with capabilities, evidence references, and safe-call contracts.
| Parameter | Type | Description |
|---|---|---|
| provider_id * | string |
{
"name": "get_provider_profile",
"description": "Get a canonical provider profile with capabilities, evidence references, and safe-call contracts.",
"inputSchema": {
"type": "object",
"title": "get_provider_profileArguments",
"required": [
"provider_id"
],
"properties": {
"provider_id": {
"type": "string",
"title": "Provider Id",
"maxLength": 128,
"minLength": 1
}
}
},
"outputSchema": {
"type": "object",
"title": "get_provider_profileDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Get every provider capability with this canonical action ID, including evidence and Safe-Call contract.
| Parameter | Type | Description |
|---|---|---|
| capability_id * | string |
{
"name": "get_capability",
"description": "Get every provider capability with this canonical action ID, including evidence and Safe-Call contract.",
"inputSchema": {
"type": "object",
"title": "get_capabilityArguments",
"required": [
"capability_id"
],
"properties": {
"capability_id": {
"type": "string",
"title": "Capability Id",
"maxLength": 128,
"minLength": 1
}
}
},
"outputSchema": {
"type": "object",
"title": "get_capabilityDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Evaluate Safe-Call constraints without invoking the provider tool.
| Parameter | Type | Description |
|---|---|---|
| arguments * | object | Proposed arguments; evaluated locally and never sent to the provider. |
| provider_id * | string | |
| data_classes | any | |
| capability_id * | string | |
| user_confirmed | boolean | |
| repository_visibility | any |
{
"name": "evaluate_safe_call",
"description": "Evaluate Safe-Call constraints without invoking the provider tool.",
"inputSchema": {
"type": "object",
"title": "evaluate_safe_callArguments",
"required": [
"provider_id",
"capability_id",
"arguments"
],
"properties": {
"arguments": {
"type": "object",
"title": "Arguments",
"description": "Proposed arguments; evaluated locally and never sent to the provider.",
"additionalProperties": true
},
"provider_id": {
"type": "string",
"title": "Provider Id",
"maxLength": 128,
"minLength": 1
},
"data_classes": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Data Classes",
"default": null
},
"capability_id": {
"type": "string",
"title": "Capability Id",
"maxLength": 128,
"minLength": 1
},
"user_confirmed": {
"type": "boolean",
"title": "User Confirmed",
"default": false
},
"repository_visibility": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Repository Visibility",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "evaluate_safe_callDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Trust Live is the decision workspace in Agent Trust. It recommends a provider for explicit task requirements using deterministic filters and versioned provider evidence. Selection Lab measurements and provider evidence are distinct evidence types. Unknown safety properties remain unknown. Its bundled catalog includes synthetic decision fixtures and does not imply live provider audits. It never calls provider tools or executes payments.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.