LLM WikiSAFE
Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with reserch-on-miss, semantic search, and a Wikipedia-style web UI. Knowledge compounds as you work.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An autonomous knowledge base that grows as you work.
LLM Wiki is a Claude Code plugin that captures research, ideas, and decisions into an interlinked wiki with semantic search, automatic research, and a Wikipedia-style web UI. Knowledge compounds over time — the more you use it, the smarter it gets.
Inspired by Andrej Karpathy's LLM Wiki pattern: raw sources are immutable, the LLM maintains the wiki layer, and a schema governs behavior.
Core Features
Knowledge Management
- Automatic capture — saves research, ideas, decisions, and findings to the wiki as you work
- Smart retrieval with research-on-miss — checks wiki first, automatically researches and ingests if not found
- Full-text search — TF-IDF keyword search with content-aware scoring and snippet extraction
- Block references & transclusion —
[[page#heading]]links and![[page#section]]embeds - Backlink panel with automatic unlinked mention detection
- Frontmatter query language — Dataview-like queries:
SELECT title, type FROM pages WHERE confidence = "high" - Intelligent freshness — 9-tier staleness system from
live(15 min) topermanent(never expires)
Research-on-Miss
- Automatic research —
/wiki-readresearches topics not in the wiki using available tools - Tool discovery — works with whatever tools the user has (WebSearch, WebFetch, Wikipedia API, MCP tools)
- Auto-ingestion — saves findings to wiki with proper citations
Web UI Features
- **Wikipe
a0aff075d745OBSERVED · 2026-10-08Exposed tools (10)
7 read · 3 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
wiki_backlinks | read | Get all pages that link to a given page, plus unlinked mentions. |
wiki_daily | write | Create or get today |
wiki_gaps | read | Analyze content gaps: missing pages, structural holes, stale content. |
wiki_list | read | List wiki pages, optionally filtered by type. |
wiki_query | write | Execute a frontmatter query (Dataview-like syntax). |
wiki_read | read | Read a wiki page by slug. Returns the full markdown content. |
wiki_search | read | Search the wiki using TF-IDF full-text search. |
wiki_stats | read | Get wiki statistics: page count, types, confidence distribution. |
wiki_wikipedia_search | read | Search Wikipedia articles via the MediaWiki Action API. |
wiki_write | write | Create or update a wiki page. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- declared (5 observation(s))
- Shell
- declared (1 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (2)
mod = importlib.import_module(module_name)
fastapi, uvicorn, markdown-it-py, mdit-py-plugins, jinja2, watchdog, aiosqlite, websockets
Gates applied: no_behavioural_pass.
a0aff075d745full audit observations/trust-audit/mcp-server/oshayr__llm-wiki-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | a0aff075d745 | SAFE | B | 89 | first audit |
Questions
What is the LLM Wiki MCP server?
Autonomous knowledge base plugin for Claude Code - captures reserch, ideas, and decisions into an interlinked wiki with reserch-on-miss, semantic search, and a Wikipedia-style web UI. Knowledge compounds as you work.
What tools does LLM Wiki expose?
10 in total: 7 read-only, 3 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is LLM Wiki safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does LLM Wiki need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (a0aff075d745), read on 2026-10-08. The repository is watched and re-audited when it changes.