solocrawl
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SOLOCRAWL_LOG_FILE | No | Optional log file path (also logs to stderr) | |
| SOLOCRAWL_LOG_LEVEL | No | Log level: DEBUG, INFO, WARNING, ERROR | |
| SOLOCRAWL_PROXY_LIST | No | Comma-separated proxy URLs | |
| SOLOCRAWL_PROXY_MODE | No | Proxy mode: list (rotate a pool) or endpoint (single rotating endpoint) | |
| SOLOCRAWL_USER_AGENT | No | Override HTTP User-Agent for API requests | |
| SOLOCRAWL_MAX_RETRIES | No | Retries on network errors / rate limits | |
| SOLOCRAWL_SEARXNG_URL | No | Base URL of a self-hosted SearXNG instance (enables the searxng provider) | |
| SOLOCRAWL_PROXY_ENABLED | No | Enable optional proxy layer | |
| SOLOCRAWL_PROXY_ENDPOINT | No | Single rotating proxy endpoint | |
| SOLOCRAWL_PROXY_PASSWORD | No | Proxy auth password | |
| SOLOCRAWL_PROXY_USERNAME | No | Proxy auth username | |
| SOLOCRAWL_RESPECT_ROBOTS | No | Honour robots.txt on scrape (fail-open); set false to skip | |
| SOLOCRAWL_BROWSER_ALLOWED | No | Allow Playwright fallback when installed | |
| SOLOCRAWL_MAX_CONCURRENCY | No | Global fetch concurrency limit | |
| SOLOCRAWL_TIMEOUT_SECONDS | No | Per-request timeout in seconds | |
| SOLOCRAWL_ENABLE_PROVIDERS | No | Comma-separated opt-in provider names | |
| SOLOCRAWL_PER_DOMAIN_LIMIT | No | Per-domain concurrency limit | |
| SOLOCRAWL_CACHE_TTL_SECONDS | No | In-memory fetch cache TTL in seconds (0 = disabled) | |
| SOLOCRAWL_MAX_RESPONSE_BYTES | No | Cap on fetched response body size (10 MiB) | |
| SOLOCRAWL_ALLOW_INTERNAL_URLS | No | Allow scraping localhost/private IPs (dev only) |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_searchB | Search the web across SoloCrawl's configured providers and return unified results. |
| scrapeA | Fetch a URL and return the main page content as markdown suitable for LLM context. |
| researchA | Search the web, scrape the top results, and return an aggregated cited report. |
| package_versionB | Look up the latest or constraint-satisfying version of a package from a registry. |
| list_providersA | List the registered search and package providers (default vs. opt-in). |
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 5 tools
Tools like research and web_search both perform web searches, with research also scraping and aggregating results. Similarly, scrape is available alongside research's scraping capability. While descriptions differentiate them, the boundaries could confuse an agent.
Tool names mix patterns: list_providers follows verb_noun, package_version uses noun_noun, while research and scrape are bare verbs, and web_search is noun_noun. No consistent style is maintained.
Five tools cover the core functionality—provider listing, package version lookup, web search, scraping, and combined research—without being excessive or insufficient for the server's stated purpose.
The tool set covers primary use cases (search, scrape, package lookup) but lacks features like crawling multiple pages or provider management, which are minor gaps for a research-focused server.