MCP-Human
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FORM_URL | No | URL where the form is hosted. Needs to be https. Default: https://syskall.com/mcp-human/ | https://syskall.com/mcp-human/ |
| AWS_REGION | No | AWS region for MTurk. Default: us-east-1 | us-east-1 |
| AWS_PROFILE | No | AWS profile to use for credentials. Default: mcp-human | mcp-human |
| MTURK_SANDBOX | No | Use MTurk sandbox (true) or production (false). Default: true | true |
| DEFAULT_REWARD | No | The reward amount in USD. Default: 0.05 | 0.05 |
| AWS_ACCESS_KEY_ID | No | AWS access key ID for MTurk API | |
| AWS_SECRET_ACCESS_KEY | No | AWS secret access key for MTurk API |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| askHumanD | – |
| checkHITStatusD | – |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| ask-human | A prompt for asking human workers questions via MTurk |
| check-hit | A prompt for checking the status of a HIT |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| balance | Get MTurk account balance |
| hits | List active HITs |
| config | Get MTurk configuration |
TDQS
Scored across 2 tools
The two tools have distinct names suggesting different functions (asking vs. checking status), but without descriptions, an agent may not fully grasp their specific roles or parameters, leading to potential confusion.
Both tool names follow a camelCase pattern with verb-first structure (askHuman, checkHITStatus), though 'HIT' is capitalized, which is acceptable for an acronym. Overall, naming is clear and consistent.
With only 2 tools, the server feels minimal for a domain centered on human interaction. It could be acceptable for a very narrow purpose, but likely leaves users wanting more functionality.
The tool set covers only asking a human and checking status of a HIT, but lacks essential operations like creating, updating, or listing HITs. This creates significant gaps for typical interaction workflows.