# llmwiki (npm · llm-wiki-compiler)

Compile documents into a cited knowledge wiki. Retrieve evidence, query, and review via local MCP.

- Trust score: 88/100 (high trust)
- Change this week: +7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-17

## Components

- npm · `llm-wiki-compiler`: 88/100 (this document), [markdown](https://verifymcp.io/servers/atomicstrata-llmwiki/llm-wiki-compiler.md), [page](https://verifymcp.io/servers/atomicstrata-llmwiki/llm-wiki-compiler)

## Channel facts

- Registry: `npm`
- Package: `llm-wiki-compiler`
- Version: `1.4.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-17.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 59 of 218 dependencies flagged as unhealthy (1 deprecated).
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to atomicstrata/llm-wiki-compiler).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 88/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1864 tokens (~88/item across 21 items; 16 tools + 5 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 50/100
  - Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "run_eval" implies "eval" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the llmwiki MCP server?

llmwiki runs locally as an npm package, launched with npx -y llm-wiki-compiler. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add atomicstrata-llmwiki -- npx -y llm-wiki-compiler
```

### Cursor

```json
{
  "mcpServers": {
    "atomicstrata-llmwiki": {
      "command": "npx",
      "args": [
        "-y",
        "llm-wiki-compiler"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "atomicstrata-llmwiki": {
      "command": "npx",
      "args": [
        "-y",
        "llm-wiki-compiler"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add atomicstrata-llmwiki -- npx -y llm-wiki-compiler
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "atomicstrata-llmwiki": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "llm-wiki-compiler"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add atomicstrata-llmwiki --command npx --arg -y --arg llm-wiki-compiler
```

### Hermes

```yaml
mcp_servers:
  atomicstrata-llmwiki:
    command: "npx"
    args: ["-y", "llm-wiki-compiler"]
```

### Netclaw

```json
{
  "McpServers": {
    "atomicstrata-llmwiki": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "llm-wiki-compiler"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add atomicstrata-llmwiki -t stdio -c npx -a -y llm-wiki-compiler
```

### Other

```json
{
  "mcpServers": {
    "atomicstrata-llmwiki": {
      "command": "npx",
      "args": [
        "-y",
        "llm-wiki-compiler"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-16 (score 88, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 87, +6)

- [functional improvement] Stability: unverified → 0.40

### 2026-10-13 (score 81, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-10-11 (score 81, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-10-03 (score 81, +20)

- [security improvement] Malware scan: unverified → pass
- [security improvement] Source repository: unverified → pass

### 2026-10-02 (score 61)

First indexed and scored.

## MCP tools (16)

### `ingest_source` (~78 tokens)

Ingest Source

Add a user-requested document to this knowledge base: fetch a trusted URL or copy a trusted local file into sources/. Writes project files. Returns the saved filename, character count, and whether content was truncated to fit the size limit.

Input parameters:

- `source` (string, required): URL (http/https) or absolute path to a .md/.txt file

### `compile_wiki` (~59 tokens)

Compile Wiki

Update the persistent knowledge wiki after source documents change. Writes wiki pages or review candidates according to project policy. Extract concepts from new/changed sources, generate wiki pages, resolve interlinks, and rebuild the index. Requires an LLM provider with credentials.

### `query_wiki` (~146 tokens)

Query Wiki

Get a model-generated answer grounded in this knowledge base. For source evidence to reason over yourself, use get_context_pack instead. Selects relevant pages, loads them, and returns a grounded answer with citations. Set save=true to request publication as a wiki page; citation or profile refusals return the answer with publicationRefusal and no saved slug. Set debug=true to include the selected chunks and their scores. Requires an LLM provider.

Input parameters:

- `debug` (boolean): Include retrieval debug info (selected chunks/pages + scores).
- `question` (string, required): The natural-language question to answer.
- `save` (boolean): Request a wiki/queries/ page; publication requires fresh citation validation.

### `search_pages` (~57 tokens)

Search Pages

Select pages relevant to a question and return their full content. Uses semantic embeddings when available, falling back to LLM-based selection over the wiki index. Requires an LLM provider.

Input parameters:

- `question` (string, required): The query used to rank pages.

### `read_page` (~52 tokens)

Read Wiki Page

Read a single wiki page by slug. Searches concepts/ first, then queries/. Returns the parsed frontmatter and body. No LLM call required.

Input parameters:

- `slug` (string, required): Page slug, without .md extension.

### `lint_wiki` (~40 tokens)

Lint Wiki

Run rule-based quality checks (broken wikilinks, orphans, duplicates, empty pages, broken citations). Returns structured diagnostics. No LLM call.

### `wiki_status` (~170 tokens)

Inspect Knowledge Base

Start here to inspect this knowledge base before retrieval or updating it. No provider credentials required. Summarize page count, source count, last compile time, pending source changes, and freshness-derived page health. stalePages lists concept slugs whose source changed or partially disappeared since last compile. orphanedPages lists concept slugs whose every owning source was deleted OR that are frontmatter-flagged orphaned (superset of prior behavior). stateStatus reports state.json readability (ok | missing | corrupt) so corrupt state is never silent. Each list (stalePages, orphanedPages, pendingChanges) is capped at 100 entries for response size; the corresponding *Count fields (staleCount, orphanedCount, pendingChangesCount) give the true totals. Read-only — never modifies the workspace.

### `get_context_pack` (~269 tokens)

Get Evidence Context

Retrieve bounded evidence from this project knowledge base for research, document questions, or agent task context. Use it when you will reason over the evidence yourself. Build a token-budgeted pack for `prompt` over the compiled wiki: primary pages, semantic chunks, graph neighbors, citations, warnings, and suggested next actions. Returns the same v1 JSON envelope as `llmwiki context --json`. Read-only; no provider credentials required. Use this to PREPARE evidence; use `query_wiki` to GENERATE a grounded natural-language answer.

Input parameters:

- `budget` (number): Approximate output token budget (default 8000).
- `depth` (number): Graph neighborhood depth, 0..2 (default 1, 0 disables expansion).
- `includeSources` (boolean): Materialize `primary[].sourceWindows` from claim-level citations (reads files under `sources/` only; path-confined).
- `omitRoot` (boolean): Emit `project.root` as null instead of the absolute path.
- `prompt` (string, required): Free-text task or topic to assemble context for.
- `topChunks` (number): Max semantic chunks to surface (default 8, max 50).
- `topPages` (number): Max primary pages (default 5, max 20).

### `run_eval` (~131 tokens)

Run Eval

Run the wiki quality eval harness. fast suite checks health and citation coverage without LLM calls. full suite also LLM-judges a sample of citations (requires an LLM provider). Set record: true to append results to eval history (default false — read-only).

Input parameters:

- `record` (boolean): Append results to eval history (default false; set true to persist a checkpoint)
- `sampleSize` (integer): Citations to sample for citation support (full suite only, default 20)
- `suite` (string): fast=no LLM calls, full=includes citation support (requires LLM provider)

### `verify_artifact` (~116 tokens)

Verify Artifact

Verify a hash-pinned artifact ref against the active profile's declared artifact types. Returns manifest metadata (artifactType, slug, sha256, bytes, contentKind, writtenAt) plus a health verdict — NEVER the artifact body. Read-only; no write or store-wide list tool is exposed over MCP.

Input parameters:

- `artifactType` (string, required): The profile-declared artifact type.
- `sha256` (string, required): The 64-character lowercase-hex sha256 digest to verify against.
- `slug` (string, required): The artifact's slug.

### `export_okf` (~64 tokens)

Export OKF bundle

Export the wiki as an Open Knowledge Format (OKF) v0.1 bundle. `out` defaults to dist/exports/okf and must stay inside the project.

Input parameters:

- `out` (string): Output dir for the bundle (must resolve inside the project root)

### `import_okf` (~77 tokens)

Import OKF bundle (staged for review)

Import an OKF bundle from a path INSIDE the project as review candidates. Always staging-only — imported knowledge requires human review/approval before it enters the wiki. Use dryRun to preview.

Input parameters:

- `dir` (string, required): Bundle directory (must resolve inside the project root)
- `dryRun` (boolean): Preview only — stage nothing

### `list_workflow_actions` (~39 tokens)

List Workflow Actions

List the workflow actions declared by the active profile (id, label, workflow, operation). Read-only; takes no lock and mutates nothing.

### `describe_workflow_action` (~65 tokens)

Describe Workflow Action

Describe one declared workflow action, including its EFFECTIVE permission per surface = min(profile request, local grant, surface cap). The `mcp` surface is hard-capped at staged-write. Read-only.

Input parameters:

- `actionId` (string, required): The declared action id to describe.

### `run_workflow_action` (~94 tokens)

Run Workflow Action

Execute a declared workflow action. MCP actions are HARD-CAPPED at staged-write: they CANNOT perform trusted writes or satisfy human gates, regardless of what a profile or local config requests. A denied, unknown, or invalid action returns a clean error result rather than crashing.

Input parameters:

- `actionId` (string, required): The declared action id to execute.
- `inputs` (object): The action's inputs, validated against its schema.

### `workflow_run_status` (~90 tokens)

Workflow Run Status

Report the status of one workflow run (by runId) or of all runs, classified against the active profile (current / historical / needs-adaptation / blocked-by-config). Read-only and fail-visible: an unavailable store surfaces a problem row, never an empty result. Takes no lock and mutates nothing.

Input parameters:

- `runId` (string): A run id to report on; omit for all runs.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/atomicstrata-llmwiki/llm-wiki-compiler#diagnostics

## Score history

- 2026-10-17: 88
- 2026-10-16: 88
- 2026-10-15: 87
- 2026-10-14: 87
- 2026-10-13: 81
- 2026-10-12: 81
- 2026-10-11: 81
- 2026-10-07: 81
- 2026-10-04: 81
- 2026-10-03: 81
- 2026-10-02: 61

## Common questions

### What is the llmwiki MCP server?

llmwiki is an MCP server listed in the public MCP registry as io.github.atomicstrata/llmwiki. Compile documents into a cited knowledge wiki. Retrieve evidence, query, and review via local MCP. This page covers its npm package (llm-wiki-compiler).

### Is the llmwiki MCP server safe to use?

llmwiki scores 88 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 17 October 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the llmwiki MCP server expose?

llmwiki exposes 16 tools: ingest_source, compile_wiki, query_wiki, search_pages, read_page, and 11 more. Their descriptions and schemas cost roughly 1,547 tokens of context every time the server is loaded.

### Is the llmwiki MCP server still maintained?

llmwiki is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the llmwiki MCP server under?

llmwiki declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/llm-wiki-compiler
- Socket report: https://socket.dev/npm/package/llm-wiki-compiler
- Repository: https://github.com/atomicstrata/llm-wiki-compiler
- Website: https://llmwiki.atomicstrata.ai/guides/mcp-agent-integration
- Changelog RSS feed: https://verifymcp.io/servers/atomicstrata-llmwiki/llm-wiki-compiler.xml
- Changelog JSON feed: https://verifymcp.io/servers/atomicstrata-llmwiki/llm-wiki-compiler.json
- HTML version of this page: https://verifymcp.io/servers/atomicstrata-llmwiki/llm-wiki-compiler