Physical Agency
Server Details
Human workforce for AI agents: field checks, user testing and device tests. Operator-reviewed work.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
TDQS
Score is being calculated.
Available Tools
6 toolsget_capabilitiesRead-onlyIdempotentInspect
Read what this human workforce pool does, task categories, lifecycle, terms, prohibited uses and limits. Call this first.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
get_productRead-onlyIdempotentInspect
Read product request conditions, completion criteria, consultation checks, related products and submit_task guidance by stable productId (e.g. LAB01, TRD001). Set locale=en for English or ko for Korean. Research rank is not availability.
| Name | Required | Description | Default |
|---|---|---|---|
| locale | No | ko | |
| productId | Yes |
Output Schema
| Name | Required | Description |
|---|---|---|
| id | Yes | |
| name | Yes | |
| work | Yes | |
| buyer | Yes | |
| group | Yes | |
| family | Yes | |
| status | Yes | |
| research | Yes | |
| agentNext | Yes | |
| groupName | Yes | |
| availability | Yes | |
| requestGuide | Yes | |
| discoveryTerms | Yes | |
| researchRegion | Yes | |
| contentLanguage | Yes | |
| relatedProductIds | Yes | |
| requestConditions | Yes | |
| completionCriteria | Yes | |
| consultationChecks | Yes |
get_worker_profileRead-onlyIdempotentInspect
Read one anonymous worker profile by handle (e.g. "w-7kq2xm").
| Name | Required | Description | Default |
|---|---|---|---|
| handle | Yes |
list_productsRead-onlyIdempotentInspect
Search the product catalog by Korean or English discovery terms, family or group. Paginated; use nextOffset. Includes agent tasks and traditional staffing (driving, housekeeping, construction, etc). Listings require consultation and do not confirm available workers, prices or booking.
| Name | Required | Description | Default |
|---|---|---|---|
| group | No | ||
| limit | No | ||
| query | No | ||
| family | No | ||
| locale | No | ko | |
| offset | No |
Output Schema
| Name | Required | Description |
|---|---|---|
| total | Yes | |
| offset | Yes | |
| version | Yes | |
| products | Yes | |
| nextOffset | Yes |
list_skillsRead-onlyIdempotentInspect
List skills, languages, categories and countries actually present in the active pool, with worker counts. Use these values in search_workers and submit_task.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
search_workersRead-onlyIdempotentInspect
Search anonymous worker profiles worldwide by skills, languages, category, remote/on-site location, verification and budget. Results are ranked with explainable match reasons. Searching does not reserve anyone.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | ||
| mode | No | remote | |
| limit | No | ||
| budget | No | ||
| skills | No | ||
| category | No | ||
| languages | No | ||
| countryCode | No | ||
| minVerification | No | ||
| estimatedMinutes | No |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
6 tool updates
- First observed
get_capabilities - First observed
get_product - First observed
get_worker_profile - First observed
list_products - First observed
list_skills - First observed
search_workers
Related MCP Connectors
Human field services for AI agents: site photos, equipment checks, remote hands and coordination.
AI agents hire a human to observe, log or film on site. Typed results, feasibility before payment.
AI agents hire a human to observe, log or film on site. Typed results, feasibility before payment.
Lets AI agents use a real human as a tool: visual checks, taste, phone calls, unblocking, approvals
Related MCP Servers
AlicenseAqualityCmaintenanceEnables AI agents to hire verified human operators for tasks requiring physical presence, human perception, or judgment, such as real-world verification, product testing, and data collection.6MIT
humanforaiofficial
AlicenseAqualityBmaintenanceEnables AI agents to hire real human operators for tasks requiring physical presence, human perception, or judgment, such as verification, testing, data collection, and physical-world tasks.458 npm1MIT- AlicenseNot gradedqualityDmaintenanceEnables 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
- AlicenseAqualityBmaintenanceEnables AI agents to recruit real humans for evaluation tasks like surveys, A/B tests, and ratings on text, images, audio, and video, returning aggregated results directly into the conversation.137MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.