Hive Web
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SEARXNG_URL | No | URL of the SearXNG endpoint | http://localhost:8888 |
| FIRECRAWL_API_URL | No | URL of the Firecrawl endpoint | http://localhost:3002 |
| HIVE_WEB_ARTIFACT_DIR | No | Directory for storing artifacts | ~/.cache/hive-web-runtime/artifacts |
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| static_web_searchA | Cheap stateless web search through local SearXNG. Returns compact normalized results and an artifact_id. |
| static_web_extractC | Cheap stateless page render/extract through local Firecrawl. Returns markdown plus artifact_id. |
| static_web_get_artifactC | Read a local artifact previously created by static-web/action-web. |
| action_web_session_createC | Create a live Playwright browser session for interactive sites/forms. |
| action_web_navigateA | Navigate a live session to a URL, or use static-web search_query to find the URL first. |
| action_web_snapshotB | Return a compact interactive snapshot: visible text and refs, not full HTML. |
| action_web_clickA | Click by snapshot ref or selector. Sensitive payment/password/2FA-looking targets require confirm_sensitive=true. |
| action_web_typeC | Type/fill text into a snapshot ref or selector. Do not send passwords/secrets through this tool. |
| action_web_pressB | Press a keyboard key in the live browser session, e.g. Enter, Escape, ArrowDown. |
| action_web_closeB | Close a live Playwright browser session. |
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 10 tools
Tools are clearly split into 'action_web_' for live browser interactions and 'static_web_' for static operations. Each tool has a distinct purpose (click, navigate, snapshot, search, etc.) with no overlapping functionality.
All tool names follow a consistent 'category_action' pattern in snake_case, with prefixes indicating live vs. static operations. The naming is predictable and intuitive.
10 tools is a reasonable count for a web automation and scraping server. It covers essential operations without being overwhelming or sparse.
The tool set covers core workflows: navigation, clicking, typing, snapshotting, searching, and extraction. Minor gaps exist (e.g., no explicit wait or form element selection), but agents can work around them using snapshots and existing actions.