Skip to main content
Glama
deenesjakoruzh
ProofStreamai

ProofStream MCP Server

Official
by ProofStreamai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

ProofStream MCP 서버

AI 에이전트에게 물리적 세계의 무언가를 직접 검증할 수 있는 인간 검증자를 파견할 수 있는 능력을 부여하세요.

기능

ProofStream은 AI 에이전트가 제품 진위 여부, 자산 상태, 문서 존재 여부 등을 물리적으로 검증하기 위해 사람을 파견하고, 사진, 동영상, 서면 결과가 포함된 타임스탬프 증거 보고서를 받을 수 있게 해주는 유일한 API입니다.

이제 에이전트가 물리적 세계의 제약에 가로막히지 않습니다.

Related MCP server: humanrail-mcp-server

도구

proofstream_submit_request

검증 요청을 제출합니다. 실제 사람이 현장에 카메라를 들고 출동하여 검증 과정을 실시간 스트리밍(선택 사항)하고, 전체 증거 패키지를 전달합니다.

서비스:

  • product — 물리적 제품 인증 ($39 / 실시간 스트리밍 포함 $79)

  • document — 문서 존재 및 내용 확인 ($99 / 실시간 스트리밍 포함 $149)

  • property — 부동산 또는 자산 상태 문서화 ($249 / 실시간 스트리밍 포함 $349)

긴급도: standard (24-72시간) | rush (+50%) | same_day (+100%)

proofstream_check_status

케이스 ID를 통해 제출된 요청의 상태를 확인합니다.

proofstream_get_pricing

현재 가격 및 서비스 세부 정보를 확인합니다.

설치

Claude Desktop / MCP 클라이언트

{
  "mcpServers": {
    "proofstream": {
      "command": "npx",
      "args": ["proofstream-mcp"]
    }
  }
}

npm (전역)

npm install -g proofstream-mcp

사용 예시

Agent: I need to verify that the product at 123 Main St, Columbus OH matches the description before we complete the purchase.

Tool call: proofstream_submit_request({
  "name": "Acme Corp",
  "email": "ops@acmecorp.com",
  "client_type": "AI Agent / Autonomous System",
  "service": "product",
  "livestream": "yes",
  "description": "Verify a 2024 MacBook Pro 16-inch (Space Black) — confirm serial number MXW73LL/A, check for damage, confirm all original accessories present",
  "location": "123 Main St, Columbus OH 43201",
  "preferred_date": "2026-05-06",
  "urgency": "standard"
})

Response: {
  "success": true,
  "case_id": "PS-XK9M2P",
  "quoted_amount": 79,
  "message": "Request received. ProofStream will review and respond within a few hours."
}

서비스 지역

오하이오, 인디애나, 켄터키, 웨스트버지니아, 펜실베이니아 서부, 미시간 남부 및 일리노이 동부. 곧 확장 예정입니다.

API

직접 REST API도 https://api.proofstream.ai에서 이용 가능합니다. 전체 접수 양식은 proofstream.ai/request.html을 참조하세요.

문의: verify@proofstream.ai | proofstream.ai

Available Tools

3 tools
proofstream_check_statusA

Check the status of a ProofStream verification request by case ID.

Status values:

  • pending_review: Request received, awaiting ProofStream acceptance

  • confirmed: Accepted, payment captured, verification scheduled

  • scheduled: Verification date/time confirmed

  • in_progress: Verifier on-site, livestream active (if requested)

  • completed: Verification done, report delivered to email

  • cancelled: Request declined (no charge)

When status is "completed", the full evidence report and invoice have been emailed to the address provided at submission.

NameRequiredDescriptionDefault
case_idYesCase ID returned from proofstream_submit_request (e.g., PS-ABC123)

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description fully bears the burden of behavioral disclosure. It lists all possible status values and their meanings, including what happens when completed (report and invoice emailed), providing comprehensive behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured, with a clear opening sentence followed by bullet points for statuses. Every sentence is informative with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete for a status-checking tool: it explains the input, the status values, and the outcome when completed. Since there is no output schema, the description adequately covers return behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter is fully described in the schema (100% coverage). The description adds value by specifying that the case ID comes from proofstream_submit_request and provides an example format, going beyond the schema's minimal description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool checks the status of a ProofStream verification request by case ID. It distinguishes itself from sibling tools (proofstream_submit_request and proofstream_get_pricing) by focusing solely on status retrieval.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage after submitting a request, but does not explicitly state when not to use it or mention alternatives. However, the sibling tool names make the context clear enough for an agent to select correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

proofstream_get_pricingA

Get current ProofStream pricing and service details without making a request.

NameRequiredDescriptionDefault

No parameters

TDQS

A3.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden. It implies a safe read operation via 'without making a request', but does not disclose authentication needs, rate limits, or whether pricing data is cached/real-time.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, front-loaded, no wasted words. Every part of the description adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple zero-param read tool, the description is adequate but minimal. It lacks details about the return format or any constraints (e.g., caching). Given no output schema, more context would help.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, and schema coverage is 100%. The description adds meaning by clarifying the tool is a read-only pricing lookup, which helps the agent understand its role beyond the empty schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool gets current ProofStream pricing and service details. The phrase 'without making a request' distinguishes it from mutation siblings like submit_request, but it could be more specific about what 'service details' encompasses.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool vs alternatives. The sibling names (check_status, submit_request) provide context, but there is no direct statement about when not to use it or which sibling to prefer.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

proofstream_submit_requestA

Submit a human verification request to ProofStream. A real human will go on-site with a camera, livestream the verification, and deliver a timestamped evidence report (photo + video + written findings). Use this when your workflow requires physical confirmation of something in the real world.

Services available:

  • product_verification ($39 standard / $79 with livestream): Authenticate a physical product — serial numbers, packaging, labels, authentication markers.

  • document_verification ($99 standard / $149 with livestream): Confirm a physical document exists, matches claimed content, photograph stamps/signatures/seals.

  • property_asset_check ($249 standard / $349 with livestream): On-site visual condition documentation of a property, vehicle, or asset.

Urgency options: standard (24-72 hours), rush (+50%, within 24h), same_day (+100%)

Returns a case_id you can use to check status. Card is authorized but NOT charged until ProofStream accepts the request.

NameRequiredDescriptionDefault
nameYesRequester full name
emailYesEmail for report delivery and credentials
companyNoOrganization name (optional)
client_typeNoType of requesterAI Agent / Autonomous System
serviceYesproduct = Product Verification | document = Document Verification | property = Property & Asset Check
livestreamNoWhether to include live video feed access (adds cost)no
urgencyNostandard = 24-72 hours | rush = within 24h (+50%) | same_day = +100%standard
descriptionYesWhat needs to be verified — be specific
locationYesPhysical address or location of the item/property to verify
preferred_dateNoPreferred verification date (YYYY-MM-DD)
metricsNoSpecific checkpoints or things to look for during verification
access_notesNoAccess instructions, contact info for site access
deliverablesNoRequired deliverables (Timestamped photo report always included)
billingNoone_time

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It details human on-site verification, livestream, report deliverables, and billing behavior (authorized but not charged until acceptance). Fully transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is informative but lengthy (multiple paragraphs). However, it is well-structured with clear sections for services, urgency, and process. Could be more concise without losing value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers purpose, parameters, pricing, services, process, and billing. No output schema but mentions return of case_id. Adequate for complex tool with 14 parameters.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 93%, so baseline is 3. Description adds pricing context per service and urgency surcharges, and clarifies billing authorization. Adds meaningful value beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool submits a human verification request to ProofStream for physical confirmation. It distinguishes from siblings (check_status and get_pricing) by specifying the action and scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use ('physical confirmation of something in the real world') and lists services/urgency options. Lacks explicit when-not-to-use or alternative tool references, but context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv0.1.0
    • First observedproofstream_check_status
    • First observedproofstream_get_pricing
    • First observedproofstream_submit_request
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored across 3 tools

Disambiguation5/5

The three tools have clearly distinct purposes: checking status, getting pricing, and submitting requests. No overlap in functionality.

Naming Consistency5/5

All tool names follow the consistent pattern 'proofstream_verb_noun' using snake_case, e.g., check_status, get_pricing, submit_request.

Tool Count5/5

Three tools is appropriate for a focused service that covers the main workflow: pricing inquiry, submission, and status checking.

Completeness4/5

The tool set covers the essential lifecycle: pricing, submission, and status check. Minor gaps exist, such as no explicit cancellation tool, but the status includes cancellation.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Related MCP Connectors

Related MCP Servers

  • humanrail-mcp-server

    prime001
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents to route tasks requiring human judgment (e.g., content moderation, refund decisions, data verification) to a vetted worker pool, with verified results returned via Lightning Network payments.
    MIT