nodriver-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| NODRIVER_MCP_SCRIPTS_DIR | Yes | Path to the directory containing scrapers | |
| NODRIVER_MCP_ARTIFACTS_DIR | Yes | Path to the directory for artifacts | |
| NODRIVER_MCP_USER_DATA_DIR | Yes | Path to a dedicated browser profile directory | |
| NODRIVER_MCP_BROWSER_EXECUTABLE | Yes | Path to the Helium/Chromium browser executable |
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 |
|---|---|
| browser_statusA | Report browser state and metadata for MCP-accessible tabs. |
| browser_openA | Open or navigate an MCP tab, reusing the active tab unless new_tab is true. |
| browser_snapshotA | Return bounded visible text or outer HTML, optionally scoped to a CSS selector. |
| browser_queryA | Return text and safe attributes for elements matching a CSS selector. |
| browser_closeA | Close the managed browser, or close MCP-owned tabs and detach in attach mode. |
| scraper_listA | List metadata for saved scrapers. |
| scraper_getA | Return a saved scraper's source and metadata. |
| scraper_saveA | Validate and atomically save a scraper for the next run. |
| scraper_runA | Hot-load and run a saved scraper. Use either url or tab_id; new_tab requires url. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| scraper-contract | The Python entry point and helpers available to generated scrapers. |
TDQS
Scored across 9 tools
Tools are generally distinct, but browser_open and scraper_run could confuse an agent: both involve navigation, though scraper_run is specifically for executing a saved scraper. Descriptions mitigate this ambiguity largely.
All tools follow a consistent verb_noun pattern with clear prefixes (browser_ and scraper_), making the purpose predictable and easy to navigate.
Nine tools cover both browser interaction and scraper management without excess or deficiency, well-scoped for a focused MCP server.
The set covers core browser operations and CRUD-like scraper management (list, get, save, run), but lacks a delete scraper tool, which is a minor gap for full lifecycle management.