Skip to main content
Glama
ma-nakaya

GitHub Pages Retrieval MCP

by ma-nakaya

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
GPR_PLUGIN_DATANoOverrides the persistent data directory for manual startup. Normally Claude Code uses CLAUDE_PLUGIN_DATA and GitHub Copilot CLI uses COPILOT_PLUGIN_DATA.

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
list_pages_sourcesA

Checks whether any Pages search targets are configured. Call this before authentication or search so an agent can request a site URL when the list is empty.

configure_pages_sourceA

Persists a user-provided HTTPS Pages URL as a local search target, derives its exact origin allowlist, and creates a dedicated browser-profile path. Existing configuration is never replaced.

get_source_auth_statusB

Returns the last known authentication state for a configured GitHub Pages source without exposing browser credentials.

begin_source_reauthC

Opens a visible, persistent local browser at the configured GitHub Pages URL. The user completes GitHub, SAML, and MFA themselves.

validate_source_authB

Validates a completed interactive authentication session against the configured protected Pages URL and persists only the resulting status.

fetch_pages_contentB

Fetches one allowlisted GitHub Pages URL through its persistent local browser profile. It never reads the source repository.

refresh_pages_indexA

Starts a parallel background crawl of allowlisted rendered Pages links. Returns immediately; poll get_pages_index for compact progress and final statistics.

get_pages_indexA

Returns index status, locale counts, and one page of a compact URL/title list. Use search_pages_index for named items; follow nextOffset only when a complete listing is required.

search_pages_indexA

Searches one source or all configured sources in the local multilingual trigram index. Use sourceId all for cross-site search; each result includes its actual sourceId for fetch_indexed_section.

fetch_indexed_sectionA

Returns one cached page or exact heading/anchor with a strict character cap. Prefer a heading returned by search_pages_index to minimize tokens.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ma-nakaya/github-pages-retrieval-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server