structured-extract-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| OPENAI_MODEL | No | Model name sent in the request. Default is gpt-4o-mini. | gpt-4o-mini |
| OPENAI_API_KEY | No | API key. Required when the provider is 'openai'. Servers that ignore the key still need a non-empty value. | |
| OPENAI_BASE_URL | No | Base URL for OpenAI-compatible server. The client posts to {base_url}/chat/completions. Default is https://api.openai.com/v1. | https://api.openai.com/v1 |
| STRUCTURED_EXTRACT_TIMEOUT | No | Seconds for one request. Default is 30. | 30 |
| STRUCTURED_EXTRACT_PROVIDER | No | Provider to use: 'fake' or 'openai'. Default is 'fake'. | fake |
| STRUCTURED_EXTRACT_LOG_LEVEL | No | Standard library log level. Default on the MCP server is WARNING. | WARNING |
| STRUCTURED_EXTRACT_MAX_ATTEMPTS | No | Validation attempts, including the first. Default is 3. | 3 |
| STRUCTURED_EXTRACT_RESPONSE_FORMAT | No | Response format: 'json_schema', 'json_object', or 'none'. Default is 'json_schema'. | json_schema |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_schemasA | Return the names of the extraction schemas this server can fill. |
| extractB | Extract validated JSON for Uses STRUCTURED_EXTRACT_PROVIDER (default: fake). The fake provider only understands the labeled examples in this repository. Failures raise a tool error instead of returning placeholder JSON. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: list_schemas discovers available schemas and extract performs the extraction. There is no overlap or ambiguity between them.
Both names are lowercase snake_case, but one follows verb_noun (list_schemas) while the other is a bare verb (extract). This is a minor deviation within an otherwise consistent convention.
Only 2 tools makes the surface quite thin, though each one earns its place for a focused extraction service. It sits at the borderline of being under-scoped.
The core workflow (discover schemas, extract data) is covered, but there is no way to inspect a schema's fields or validate text without extracting, leaving users partly blind to the expected structure.