Skip to main content
Glama

Wiki Explorer MCP Server

A generic MCP (Model Context Protocol) server that exposes any project wiki to AI assistants, enabling contextual wiki lookups during development sessions.

Features

  • Lazy loading — indexes headings once, loads content on-demand via byte positions

  • Auto-reload — watches the wiki file or markdown directory for changes with debouncing

  • Fuzzy search — handles typos and partial matches via levenshtein distance

  • Content search — searches within section content, not just headings

  • Custom anchors — use {#anchor} syntax in headings for stable TOC links

  • Directory mode — index entire markdown directory trees with file-prefixed keys

  • Legacy key support — backward-compatible lookup of heading-only keys

  • Heading hierarchy — tracks full breadcrumb path for nested sections

  • Batch fetch — retrieve multiple sections in one call (max 20)

  • Smart suggestions — returns similar keys when a section isn't found

  • Path safety — validates markdown sources and safe path resolution

  • Graceful shutdown — handles SIGINT/SIGTERM, cleans up watchers

  • Structured logging — configurable log levels for debugging

Related MCP server: WikiJS MCP Server

Setup

# 1. Install dependencies
npm install

# 2. Configure wiki path
cp .env.example .env

# 3. Run tests
npm test

.env

WIKI_PATH=path/to/your/wiki-source  # file (.md/.markdown) or directory
LOG_LEVEL=info  # debug, info, warn, error

MCP Tools

Tool

Description

Parameters

list_wiki

List all available wiki sections

none

browse_wiki

Browse sections by topic/parent

topic (string, optional)

search_wiki

Search sections by keyword

query (string), fuzzy (boolean)

get_wiki_section

Get a single section's content

key (string), offset (number), limit (number)

get_wiki_sections

Get multiple sections at once

keys (string[], max 20)

Connecting to AI Assistants

Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

{
  "mcpServers": {
    "wiki-explorer": {
      "command": "node",
      "args": ["/path/to/wiki-explorer/index.js"],
      "env": {
        "WIKI_PATH": "/path/to/your/docs/wiki"
      }
      }
  }
}

Cursor

Add to Cursor MCP settings:

{
  "mcpServers": {
    "wiki-explorer": {
      "command": "node",
      "args": ["/path/to/wiki-explorer/index.js"],
      "env": {
        "WIKI_PATH": "/path/to/your/docs/wiki"
      }
      }
  }
}

VS Code (GitHub Copilot)

Add to .vscode/mcp.json:

{
  "servers": {
    "wiki-explorer": {
      "command": "node",
      "args": ["/path/to/wiki-explorer/index.js"],
      "env": {
        "WIKI_PATH": "/path/to/your/docs/wiki"
      }
      }
  }
}

Running

# Start MCP server (stdio transport)
npm start

# Debug mode
LOG_LEVEL=debug npm start

Architecture

index.js          → MCP server + tool registration + signal handlers
utils.js          → WikiParser class (indexing, search, content extraction)
logger.js         → Structured logging with configurable levels
test.js           → 67 assertions covering all functionality
.env              → WIKI_PATH, LOG_LEVEL configuration

WikiParser Class

  • Constructor — validates file/directory source, loads markdown docs, builds heading index with byte positions

  • search(query, { fuzzy, limit }) — find sections by keyword

  • findSimilar(key) — get similar keys via levenshtein distance

  • getSection(key) — retrieve content for a single section

  • getSections(keys) — batch retrieve multiple sections

  • reload() — re-read file and rebuild index

  • close() — stop file watcher

Key Compatibility

  • Canonical keys in directory mode are prefixed by file slug (e.g. user-wiki-approval-workflow-deep-dive)

  • Legacy heading-only keys are still accepted in getMeta/getSection for backward compatibility

  • Ambiguous legacy keys require suffixed form (-1, -2) to resolve deterministically

  • Search accepts legacy key queries but returns canonical keys

Custom Anchors

Headings can include a custom anchor using {#anchor-name} syntax at the end of the heading text:

## Backend Architecture {#portage-backend-architecture}

This creates a stable anchor that can be used in table of contents or direct links. The anchor is stripped from the displayed title but registered as a legacy alias for lookup.

Search matches both heading text and section content. Results are prioritized:

  1. Header matches — exact or fuzzy match in heading text

  2. Content matches — keyword found within section body

This ensures the most relevant sections appear first.

Security

  • Source validation (.md/.markdown file or directory)

  • Safe path resolution via path.resolve + fs stat checks

  • File size cap (50MB default)

  • Key format validation (lowercase alphanumeric + hyphens)

  • Batch request limits (max 20 keys)

Graceful Shutdown

Handles SIGINT, SIGTERM, uncaughtException, and unhandledRejection. Cleans up file watchers and exits cleanly.

Testing

npm test

Covers: initialization, path validation, directory mode, search (headers + content), fuzzy search, findSimilar, meta, sections, batch fetch, boundaries, reload, file watcher, key format validation, custom anchors, legacy key resolution, and cleanup.

CI/CD

GitHub Actions runs tests on Node 20 and 22 for every push/PR to main. See .github/workflows/ci.yml.

Available Tools

6 tools
browse_wikiA
Read-only

Browse wiki sections by topic/parent. Returns section keys and titles without full content. Use this to discover relevant sections before fetching content.

Inputs: topic. Returns: count, error, groups

get_wiki_infoA
Read-only

Get metadata about the connected wiki instance — path, mode (file/directory), and section count.

Inputs: no named parameters. Returns: mode, uptime, wikiPath, sectionCount, +1 more

get_wiki_sectionA
Read-only

Retrieve markdown content of a wiki section. Defaults to 8000 chars to save tokens. Set limit higher or use offset to read the full section.

Inputs: key (required), limit, offset. Returns: error, limit, title, offset, +9 more

get_wiki_sectionsA
Read-only

Retrieve multiple wiki sections at once. Each section is truncated to save tokens.

Inputs: keys (required). Returns: error, sections, errorCount, successCount

list_wikiA
Read-only

List all available wiki section keys. Use browse_wiki instead for topic-filtered results.

Inputs: no named parameters. Returns: count, error, sections

search_wikiA
Read-only

Search wiki section titles and content by keyword. Returns matching section keys with snippets. Header matches are prioritized over content matches.

Inputs: query (required), fuzzy, limit. Returns: count, error, results, suggestions

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 6 tools

    Disambiguation4/5

    Most tools have clear distinct purposes: search, browse, get single, get multiple, and info are unambiguous. However, list_wiki and browse_wiki overlap significantly since both return section keys, though browse offers topic filtering.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case: list_, browse_, search_, get_wiki_section(s), get_wiki_info. The verbs are descriptive and predictable.

    Tool Count5/5

    Six tools is well-scoped for a wiki server. Each tool covers a distinct aspect of reading wiki content, and the count feels neither sparse nor bloated.

    Completeness4/5

    The surface covers all read-related workflows: discovery (list/browse/search), retrieval (single/multiple sections), and metadata. Missing write operations (create/update/delete) but likely outside the apparent read-only scope.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers