Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
LLM_WIKI_HOSTNoHost to bind when using HTTP transport (default: 127.0.0.1).127.0.0.1
LLM_WIKI_PORTNoPort to bind when using HTTP transport (default: 8848).8848
LLM_WIKI_ROOTNoPath to the wiki directory (default: current directory). Overridden by --wiki flag.
LLM_WIKI_TOKENNoBearer token required for HTTP transport (not needed for stdio).
LLM_WIKI_RAW_DIRNoName of the raw sources directory (default: raw).raw
ANTHROPIC_API_KEYNoAnthropic API key to enable the 'ask' tool (optional).
LLM_WIKI_SCHEMA_FILESNoComma-separated list of schema/conventions filenames (default: CLAUDE.md,AGENTS.md,.llm-wiki.md,CONVENTIONS.md).CLAUDE.md,AGENTS.md,.llm-wiki.md,CONVENTIONS.md
LLM_WIKI_OVERVIEW_FILENoFilename for the overview page (default: overview.md).overview.md
LLM_WIKI_DESCRIPTION_MAXNoMaximum description length in characters (default: 400).400
LLM_WIKI_LOG_MAX_ENTRIESNoMaximum number of log entries to return (default: 10).10
LLM_WIKI_LIST_MAX_DESCRIBEDNoMaximum number of described pages to list (default: 250).250

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_indexA

Return the wiki index — a curated catalog of every page with one-line summaries. Read this first to navigate.

search_wikiA

Full-text search across the wiki (excludes raw sources). Returns matching files with line snippets. Use find_page instead when you want one page rather than every mention.

Args: query: Search terms (case-insensitive; regex is accepted). page_type: Optional type filter. See list_types.

find_pageA

Return the single page that best matches a topic, in full.

Use this for "what does the wiki say about X". Use search_wiki when you want every mention of X across the corpus.

Args: topic: What you're looking for, e.g. 'agent payments'. page_type: Optional type filter. See list_types. tags: Optional tag filter. See list_tags for the vocabulary. match: 'and' (page must carry every tag, default) or 'or' (any).

read_pageA

Return a page's full content.

Args: name: Page slug ('grounding-data'), relative path ('sources/2026-04-24-caswell.md'), or a [[wikilink]].

list_pagesA

List pages with their one-line descriptions, optionally filtered.

Args: page_type: Type to restrict to. See list_types. tags: Frontmatter tags to filter by. See list_tags. match: 'and' (page must carry every tag, default) or 'or' (any).

list_typesA

List the page types this wiki uses, with counts. Types come from frontmatter type, falling back to the containing directory.

list_tagsA

List every tag in use with its page count, commonest first. Read this before filtering by tag — it is the only way to learn the vocabulary.

Args: page_type: Optionally restrict to one type.

get_logA

Return the wiki's change log, newest first — what was added when, and the reasoning recorded at the time. get_index says what the wiki holds; this says how it got there.

Args: since: Optional ISO date (YYYY-MM-DD); only entries on or after it. limit: Max entries. Defaults to a small window, as logs get large.

read_sourceA

Return the text of a raw source document (transcript, article, notes). Text files only; PDFs and other binaries are not served as text.

Args: path: Path within the raw source directory.

validate_wikiA

Check the wiki for conformance problems: invalid or incomplete frontmatter, duplicate slugs, pages missing from the index, index entries pointing at pages that no longer exist, references to missing sources, and unresolved or broken wikilinks.

Args: path: Optional single page to check. Omit to check everything. limit: Maximum findings to return.

askA

Answer a natural-language question against the wiki and return a cited answer. Use this when you want a finished answer rather than raw pages: it reads the index, searches, reads what matters, and synthesizes.

Args: question: The question to answer.

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/kleinmatic/llm-wiki-mcp'

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