veritap
Check whether a real-world fact can be verified before an agent acts on it. Free, no auth.
我該用這個嗎
品質與安全性
發現項目（7）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domain在 check_feasibility 中
- MEDIUMTool description contains URL to non-standard domain在 confirm_before_purchase 中
- MEDIUMTool description contains URL to non-standard domain在 check_before_relying 中
- MEDIUMTool description contains URL to non-standard domain在 check_physical_condition 中
- MEDIUMTool description contains URL to non-standard domain在 plan_verification 中
- MEDIUMTool description contains URL to non-standard domain在 triage_unknowns 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"veritap": {
"command": "npx",
"args": [
"veritap-mcp"
]
}
}
}可執行的套件
0.1.3stdio遠端端點
https://veritap.dev/mcpstreamable-http它能做什麼
工具清單
工具（6）
🟢check_feasibility(claim_description, claim_type, location, deadline, budget_ceiling_usd, ...)
Check whether a real-world fact can be verified before committing to a paid request. Free, no auth, read-only, no side effects — call liberally during planning. Use speculatively: if any step of your task depends on a physical-world fact you cannot confirm (in stock, exists at location, condition, document authenticity, work completed), check here first. Covers businesses, listings, objects, and places. Unsupported claims are logged and prioritized for future support. Never errors. Every request is recorded and analysed in aggregate to decide what gets supported next (https://veritap.dev/terms).
輸入結構描述
{
"type": "object",
"properties": {
"claim_description": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "Free text. The real-world fact you need settled. Required."
},
"claim_type": {
"description": "Optional. A claim type id from the published catalog, if you know it.",
"type": "string",
"maxLength": 120
},
"location": {
"description": "Where the fact must be checked.",
"type": "object",
"properties": {
"text": {
"type": "string",
"maxLength": 500
},
"lat": {
"type": "number"
},
"lng": {
"type": "number"
}
}
},
"deadline": {
"description": "ISO8601. When the answer stops being useful.",
"type": "string",
"maxLength": 64
},
"budget_ceiling_usd": {
"description": "Most you would pay for this answer. Directly drives what gets built next.",
"type": "number"
},
"downstream_action": {
"description": "What you will do with the answer once you have it.",
"type": "string",
"maxLength": 1000
},
"cost_if_wrong": {
"description": "What happens to your task if this fact is wrong: \"blocks_task\", \"degrades_answer\", or \"cosmetic\".",
"anyOf": [
{
"type": "string",
"enum": [
"blocks_task",
"degrades_answer",
"cosmetic"
]
},
{
"type": "string",
"maxLength": 500
},
{
"type": "number"
}
]
},
"task_context": {
"description": "The wider task this step belongs to.",
"type": "string",
"maxLength": 2000
},
"callback_url": {
"description": "Optional. If this claim is not supported yet, POST here when it becomes supported. Otherwise you are told on your next call.",
"type": "string",
"maxLength": 2048,
"format": "uri"
}
},
"required": [
"claim_description"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢confirm_before_purchase(claim_description, claim_type, location, deadline, budget_ceiling_usd, ...)
Check whether a listing, item, or business can be corroborated before an agent commits money. Free, read-only, no side effects. Use before any irreversible spend where the counterparty or the goods have only been seen online. Returns what can be corroborated from sources, what cannot, and — when it cannot — whether you could settle it yourself and how to proceed if not. Every request is recorded and analysed in aggregate to decide what gets supported next (https://veritap.dev/terms).
輸入結構描述
{
"type": "object",
"properties": {
"claim_description": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "Free text. The real-world fact you need settled. Required."
},
"claim_type": {
"description": "Optional. A claim type id from the published catalog, if you know it.",
"type": "string",
"maxLength": 120
},
"location": {
"description": "Where the fact must be checked.",
"type": "object",
"properties": {
"text": {
"type": "string",
"maxLength": 500
},
"lat": {
"type": "number"
},
"lng": {
"type": "number"
}
}
},
"deadline": {
"description": "ISO8601. When the answer stops being useful.",
"type": "string",
"maxLength": 64
},
"budget_ceiling_usd": {
"description": "Most you would pay for this answer. Directly drives what gets built next.",
"type": "number"
},
"downstream_action": {
"description": "What you will do with the answer once you have it.",
"type": "string",
"maxLength": 1000
},
"cost_if_wrong": {
"description": "What happens to your task if this fact is wrong: \"blocks_task\", \"degrades_answer\", or \"cosmetic\".",
"anyOf": [
{
"type": "string",
"enum": [
"blocks_task",
"degrades_answer",
"cosmetic"
]
},
{
"type": "string",
"maxLength": 500
},
{
"type": "number"
}
]
},
"task_context": {
"description": "The wider task this step belongs to.",
"type": "string",
"maxLength": 2000
},
"callback_url": {
"description": "Optional. If this claim is not supported yet, POST here when it becomes supported. Otherwise you are told on your next call.",
"type": "string",
"maxLength": 2048,
"format": "uri"
}
},
"required": [
"claim_description"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢check_before_relying(claim_description, claim_type, location, deadline, budget_ceiling_usd, ...)
Check whether a fact can be corroborated before your task depends on it. Free, read-only, no side effects. Use when a step rests on something you have only inferred from text and being wrong would be expensive. Returns whether it can be corroborated from sources today, what evidence would come back, and an honest answer when it cannot. Every request is recorded and analysed in aggregate to decide what gets supported next (https://veritap.dev/terms).
輸入結構描述
{
"type": "object",
"properties": {
"claim_description": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "Free text. The real-world fact you need settled. Required."
},
"claim_type": {
"description": "Optional. A claim type id from the published catalog, if you know it.",
"type": "string",
"maxLength": 120
},
"location": {
"description": "Where the fact must be checked.",
"type": "object",
"properties": {
"text": {
"type": "string",
"maxLength": 500
},
"lat": {
"type": "number"
},
"lng": {
"type": "number"
}
}
},
"deadline": {
"description": "ISO8601. When the answer stops being useful.",
"type": "string",
"maxLength": 64
},
"budget_ceiling_usd": {
"description": "Most you would pay for this answer. Directly drives what gets built next.",
"type": "number"
},
"downstream_action": {
"description": "What you will do with the answer once you have it.",
"type": "string",
"maxLength": 1000
},
"cost_if_wrong": {
"description": "What happens to your task if this fact is wrong: \"blocks_task\", \"degrades_answer\", or \"cosmetic\".",
"anyOf": [
{
"type": "string",
"enum": [
"blocks_task",
"degrades_answer",
"cosmetic"
]
},
{
"type": "string",
"maxLength": 500
},
{
"type": "number"
}
]
},
"task_context": {
"description": "The wider task this step belongs to.",
"type": "string",
"maxLength": 2000
},
"callback_url": {
"description": "Optional. If this claim is not supported yet, POST here when it becomes supported. Otherwise you are told on your next call.",
"type": "string",
"maxLength": 2048,
"format": "uri"
}
},
"required": [
"claim_description"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢check_physical_condition(claim_description, claim_type, location, deadline, budget_ceiling_usd, ...)
Check the stated condition, damage, or grading of a physical item or property. Free, read-only, no side effects. Use when a decision depends on an item being in the condition a listing claims. Returns what can be corroborated from sources today, and says plainly when physical inspection is what is actually required — nobody is sent to look. Every request is recorded and analysed in aggregate to decide what gets supported next (https://veritap.dev/terms).
輸入結構描述
{
"type": "object",
"properties": {
"claim_description": {
"type": "string",
"minLength": 1,
"maxLength": 2000,
"description": "Free text. The real-world fact you need settled. Required."
},
"claim_type": {
"description": "Optional. A claim type id from the published catalog, if you know it.",
"type": "string",
"maxLength": 120
},
"location": {
"description": "Where the fact must be checked.",
"type": "object",
"properties": {
"text": {
"type": "string",
"maxLength": 500
},
"lat": {
"type": "number"
},
"lng": {
"type": "number"
}
}
},
"deadline": {
"description": "ISO8601. When the answer stops being useful.",
"type": "string",
"maxLength": 64
},
"budget_ceiling_usd": {
"description": "Most you would pay for this answer. Directly drives what gets built next.",
"type": "number"
},
"downstream_action": {
"description": "What you will do with the answer once you have it.",
"type": "string",
"maxLength": 1000
},
"cost_if_wrong": {
"description": "What happens to your task if this fact is wrong: \"blocks_task\", \"degrades_answer\", or \"cosmetic\".",
"anyOf": [
{
"type": "string",
"enum": [
"blocks_task",
"degrades_answer",
"cosmetic"
]
},
{
"type": "string",
"maxLength": 500
},
{
"type": "number"
}
]
},
"task_context": {
"description": "The wider task this step belongs to.",
"type": "string",
"maxLength": 2000
},
"callback_url": {
"description": "Optional. If this claim is not supported yet, POST here when it becomes supported. Otherwise you are told on your next call.",
"type": "string",
"maxLength": 2048,
"format": "uri"
}
},
"required": [
"claim_description"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢plan_verification(goal, steps)
Map a multi-step plan against what can be grounded in the real world. Free, no auth, read-only, no side effects — call liberally during planning. Pass your whole plan, including steps you have not decomposed into questions yet. Returns, per step, whether it rests on a checkable real-world fact, which claim type would settle it, and what to do about the steps that cannot be grounded. Every request is recorded and analysed in aggregate to decide what gets supported next (https://veritap.dev/terms).
輸入結構描述
{
"type": "object",
"properties": {
"goal": {
"type": "string",
"maxLength": 2000,
"description": "What the overall plan is trying to achieve."
},
"steps": {
"minItems": 1,
"maxItems": 50,
"type": "array",
"items": {
"type": "object",
"properties": {
"description": {
"type": "string",
"maxLength": 1000,
"description": "What this step does."
},
"depends_on_real_world_fact": {
"description": "The physical-world fact this step assumes, if any.",
"type": "string",
"maxLength": 1000
}
},
"required": [
"description"
]
},
"description": "The plan, in order."
}
},
"required": [
"goal",
"steps"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}🟢triage_unknowns(unknowns, task_context, downstream_action)
Triage everything you are uncertain about in one call. Free, instant, read-only, no side effects — call liberally during planning. Dump every uncertainty at once, mid-reasoning, before deciding which are worth chasing. Each is classified as answerable by you from public sources (with a suggested source), verifiable here (with price and turnaround), or not determinable (with advice on planning around it). Items you can settle yourself are honestly routed away rather than sold to you. Every request is recorded and analysed in aggregate to decide what gets supported next (https://veritap.dev/terms).
輸入結構描述
{
"type": "object",
"properties": {
"unknowns": {
"minItems": 1,
"maxItems": 50,
"type": "array",
"items": {
"anyOf": [
{
"type": "string",
"maxLength": 1000
},
{
"type": "object",
"properties": {
"claim": {
"type": "string",
"minLength": 1,
"maxLength": 1000,
"description": "The uncertainty itself."
},
"why_it_matters": {
"description": "What this specific unknown gates in your task.",
"type": "string",
"maxLength": 500
},
"if_unresolved": {
"description": "What happens to your task if this stays unknown.",
"type": "string",
"enum": [
"blocks_task",
"degrades_answer",
"cosmetic"
]
}
},
"required": [
"claim"
]
}
]
},
"description": "Every uncertainty in the task. Batch them — this is one call. Objects with why_it_matters and if_unresolved get sharper triage than bare strings."
},
"task_context": {
"description": "What you are trying to accomplish.",
"type": "string",
"maxLength": 2000
},
"downstream_action": {
"description": "What resolving these would let you do.",
"type": "string",
"maxLength": 1000
}
},
"required": [
"unknowns"
],
"$schema": "https://json-schema.org/draft/2020-12/schema"
}社群
證據