wiki-explore
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@wiki-exploresearch the wiki for authentication"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
wiki-explore
A dependency-free local CLI and stdio MCP server for searching, reading, and inspecting a Git-backed Markdown wiki. It is a reader, not a hosted knowledge service.
wiki-explore never uploads wiki content, starts a network listener, creates credentials, or
writes wiki pages. Query commands are read-only. sync is explicit and only fast-forwards a
clean checkout on main; install --yes only writes an owned local MCP configuration entry.
Install
Requires Python 3.11+.
python3 -m pip install --user --no-deps "git+https://github.com/halaprix/wiki-explore.git"For development:
python3 -m pip install --user --no-deps .
python3 -m unittest discover -s tests -vRelated MCP server: wikicapsule
Wiki contract
The selected checkout must contain SCHEMA.md and index.md. Pages exposed by search and read
must live directly in one of these directories:
entities/concepts/comparisons/queries/
Other files, nested files, and symlinked pages are not exposed. This deliberately keeps the tool small and prevents an MCP client from traversing outside the curated page surface.
CLI
wiki-explore status --repo /path/to/wiki
wiki-explore search --repo /path/to/wiki "rate limits"
wiki-explore read --repo /path/to/wiki concepts/rate-limits.md
# An explicit, safe Git update: clean checkout, main branch, origin remote, fast-forward only.
wiki-explore sync --repo /path/to/wikiSearch returns JSON. Read returns the original Markdown for one canonical page. Status reports the local revision and worktree state.
MCP
The stdio server exposes exactly three read-only tools:
wiki_search(query, limit?)wiki_read(path)wiki_status()
Run it directly:
wiki-explore serve --mcp --repo /path/to/wikiOr install an owned MCP entry for supported local clients. Installation is a dry-run unless
--yes is supplied. It refuses to replace a conflicting wiki-explore entry and backs up an
existing configuration before changing it.
wiki-explore install --targets claude,codex --repo /path/to/wiki
wiki-explore install --targets claude,codex --repo /path/to/wiki --yesSupported installer targets: agy, claude, codex, and grok.
Security model and non-goals
This project is intentionally local-first:
no hosted API, proxy, index, telemetry, or background synchronization;
no content editing, candidate submission, authentication, or secrets;
no recursive filesystem browsing; only canonical Markdown pages are queryable;
no implicit Git writes; synchronization is user-invoked and uses
git pull --ff-only.
It is not a replacement for a wiki's review process or source control. The Git remote remains the shared source of truth; this tool only reads a local checkout.
Development
python3 -m unittest discover -s tests -v
python3 scripts/check_public_safety.py
python3 -m buildSee CONTRIBUTING.md, SECURITY.md, and docs/ARCHITECTURE.md.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Read-only MCP for the Eco game wiki: search, Markdown pages, and wiki_* lookups. No keys, no writes.
Read-only MCP server for the OrchestKit docs: full-text search + Markdown fetch. No auth.
Read-only search and Markdown access to liz's public docs, prompts, resources, and an MCP App.
- FlowdexOAuthdk.flowdex
Read and write your team's shared, AI-readable wiki from any MCP client.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables lexical search over local Markdown wiki folders using SQLite FTS5, with MCP tools for querying and managing wiki indices.-
- AlicenseNot gradedqualityBmaintenanceTurns a git-backed markdown directory into an MCP-compatible knowledge server, enabling any MCP client to read, search, ingest, and maintain a persistent wiki that compounds across sessions.MIT
- AlicenseNot gradedqualityAmaintenanceServes local Markdown wikis as a read-only knowledge source with MCP tools for agent context retrieval.6Apache 2.0
- AlicenseNot gradedqualityCmaintenanceMCP server to query a Git-hosted Wiki, offering tools to list, search, and read Markdown documents via Codex or VS Code.MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/halaprix/wiki-explore'
If you have feedback or need assistance with the MCP directory API, please join our Discord server