proxy-scraper
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| get_proxiesA | Get working free proxies right now, fastest first. Instant: comes from a public list that is re-checked every hour from GitHub's servers, so a proxy may have died since, and some behave differently from this machine's network. Use check_proxies when they must work from here right now. Every result has a ready-to-use url like socks5://1.2.3.4:1080. |
| check_proxiesA | Find proxies that work from this machine's network right now. Runs the same checks as the public list – handshake, second request, byte-for-byte content check, verified TLS – but from here, so the results were verified seconds ago from the network your code runs on. Slower than get_proxies: 30-90 s in live mode, and progress is reported while it runs. It also updates the local statistics proxy-scraper learns from. |
| fetch_urlA | Load a web page through a verified free proxy and return it as readable text. If a proxy fails, the next one is tried by itself (up to 8), redirects are followed. HTTPS only goes through proxies that passed a verified-TLS test, so the page can't be changed on the way. Local and private addresses are refused, also when a redirect points there. Useful to see a site from another country or when a site blocks this machine. GET only; don't use it for logins or anything with personal data. |
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 3 tools
get_proxies and check_proxies both return proxy lists and could be confused at a glance, but the descriptions clearly delineate cached-public-list vs. locally-verified, and fetch_url is a distinct consumer action. Boundaries are recoverable without much risk of misselection.
All three tools use a clean snake_case verb_noun pattern (get_proxies, check_proxies, fetch_url) with consistent imperative verbs. No mixed conventions or vague naming.
Three tools is slightly lean but each earns its place: acquire a list, verify locally, then use a proxy to fetch. The small surface fits a narrow proxy-scraping domain rather than feeling arbitrarily truncated.
The core workflow (list, validate, use) is fully covered, but the toolset mentions updating local statistics that no tool can read back, and there is no filtering by protocol/country or proxy-detail retrieval. These are minor gaps an agent can work around.