remove-paywall-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | Bind address for HTTP mode. | 0.0.0.0 |
| MCP_PORT | No | Port for HTTP mode. | 8000 |
| MCP_DB_DIR | No | Database directory. | ~/.remove-paywall-mcp |
| MCP_TRANSPORT | No | Transport mode: 'stdio' or 'streamable-http'. | stdio |
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 |
|---|---|
| remove_paywallA | Remove a paywall from an article URL by searching internet archives. First tries a direct fetch with Googlebot user-agent (many sites serve full content to crawlers), then 12ft.io proxy, iitty textise, Wayback Machine (CDX API with dedup + newest-first), archive.is/ph mirrors, and Wayback Availability API. Archives are tried in parallel using historical success rates to prioritize the best one for each domain. Returns extracted article text with title and snapshot info. |
| search_archivesA | Search all archive sources for snapshots of a URL. Returns a list of available snapshot URLs from each archive source: Googlebot direct fetch, 12ft.io proxy, iitty textise, Wayback Machine, archive.is/ph mirrors, and Wayback Availability API. Does not extract content — use remove_paywall for full article retrieval. |
| get_from_archiveB | Fetch an archived version of a URL from a specific source. source must be one of: googlebot, 12ft, iitty, wayback, archive_is, wayback_available. Returns the extracted article text. |
| domain_infoA | Look up stored knowledge about a paywall domain. Returns paywall status, user notes, historical archive success rates, and the best archive order for this domain. Use add_domain to register new domains. |
| add_domainA | Register a domain in the paywall knowledge base. Set has_paywall=true for sites that normally have paywalls (so archives are tried first). Set has_paywall=false for sites that don't (so archive search is skipped and the live page is fetched directly). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| remove_paywall_prompt | Use this prompt when you encounter a URL blocked by a paywall or login wall. The remove_paywall tool tries a direct Googlebot fetch, then 12ft.io proxy, iitty textise, Wayback Machine, archive.is/ph mirrors, and Wayback Availability API for an archived copy that bypasses the paywall. Non-paywalled domains are fetched live. Archive sources are tried in parallel, with order optimized per-domain based on historical success rates. |
| bypass_paywall | Short alias for remove_paywall_prompt. Use when you hit a paywall, login wall, or subscriber-only article — this prompt instructs the assistant to search archives for a readable copy. |
| handle_paywalls | System prompt fragment. Instructs the assistant to automatically use the remove_paywall tool whenever it encounters a URL that is behind a paywall, login wall, metered paywall, or subscriber-only content. Load this as part of the assistant's system instructions for automatic paywall bypass. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool has a distinct purpose: remove_paywall is the high-level bypass, search_archives lists snapshots, get_from_archive fetches from a named source, and domain_info/add_domain manage domain knowledge. No two tools appear to do the same thing.
Most tool names follow a verb_noun pattern (remove_paywall, search_archives, add_domain), but get_from_archive uses verb-preposition-noun and domain_info is a noun phrase. This is a minor deviation from an otherwise consistent snake_case style.
With 5 tools, the server is well-scoped for its purpose: one main operation, two low-level retrieval ops, and two knowledge-base ops. No redundancy and no missing essential functionality.
The tool surface covers the full workflow: automatic bypass, manual archive search/fetch, and persistent domain knowledge. The ability to consult and add domain info ensures agents can adapt to known paywall patterns. No major gaps evident.