EnriWeb
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ENRIPROXY_URL | No | The URL of the EnriProxy server (e.g., http://127.0.0.1:8787). | http://127.0.0.1:8787 |
| ENRIPROXY_API_KEY | Yes | An EnriProxy API key used to authenticate with the EnriProxy server. | |
| ENRIWEB_TIMEOUT_MS | No | Timeout for requests in milliseconds. | 60000 |
| ENRIWEB_GITHUB_TOKEN | No | Used for GitHub API enrichment to improve rate limits. | |
| ENRIWEB_WEB_FETCH_DEFAULT_MAX_CHARS | No | Maximum characters allowed for web fetch content defaults. | 200000 |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_searchA | Busca en la web mediante el servicio multi-nivel de EnriProxy. Cuándo usarla:
Características:
Notas:
|
| web_fetchA | Obtiene y lee el contenido de una URL mediante el servicio multi-nivel de EnriProxy. Cuándo usarla:
Características:
Notas:
|
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
web_search and web_fetch have clearly distinct purposes: one discovers URLs and information from the web, the other retrieves content from a specific URL. There is no overlap or ambiguity in choosing between them.
Both tools consistently follow the web_verb pattern (web_search, web_fetch), making the domain and action immediately clear and predictable.
Two tools is minimal, but it fully covers the core need of a web access server: searching and fetching. It is slightly under the typical 3-15 range yet remains well-scoped and not bloated.
For the stated purpose of web search and retrieval, the pair forms a complete workflow: search returns candidate URLs and web_fetch reads the chosen page, including pagination and content-shaping options. There are no obvious dead ends.