Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add po4yka/llm-wiki-skills --skill llm-wiki-mcp-integrationgit clone --depth 1 https://github.com/po4yka/llm-wiki-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-mcp-integration)<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-mcp-integration"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-mcp-integration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/po4yka/llm-wiki-skills/llm-wiki-mcp-integration"><img src="https://agentmods.dev/badge/skills/po4yka/llm-wiki-skills/llm-wiki-mcp-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00081 | $0.02512 |
| Opus 5 | $0.00041 | $0.01256 |
| Sonnet 5 | $0.00016 | $0.00502 |
| Haiku 4.5 | $0.00008 | $0.00251 |
Grade A, and why
llm-wiki-mcp-integration scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM-Wiki MCP Integration
Goal
Expose LLM-Wiki knowledge to agent clients through MCP or a local/remote API while keeping raw sources, retrieval filters, write permissions, review gates and audit logs explicit.
Use references/docs/17-mcp-api-integration.md as the reference playbook for the detailed MCP/API architecture, resource/tool contracts, auth/governance model, client compatibility, deployment patterns and testing checklist.
When to use
- The user wants Claude Code, Codex, Cursor, ChatGPT, VS Code, GitHub Copilot, LangGraph or another MCP client to search, read, lint, rescan, propose, review or export wiki knowledge.
- A wiki maintainer needs to pick an exposure mode (local stdio, local HTTP, remote read-only, remote governed-write) and is unsure which permission defaults apply.
- Someone is designing MCP resources/tools/prompts or a REST/OpenAPI facade in front of the wiki and needs the contract shapes.
- A team wants to add write/proposal tools and needs the auth scopes, PR/review gate and audit-log requirements defined before granting access.
- Before recommending client-specific integration behavior, re-verify each client's current MCP support against its own docs rather than assuming parity across Claude Code, ChatGPT, Copilot and LangGraph.
Inputs
- Target clients: Claude Code, Codex, Cursor, ChatGPT, VS Code, GitHub Copilot, LangGraph, OpenCode or other MCP-compatible tools.
- Current wiki layout and retrieval layer.
- Desired operations: search, read, graph traversal, lint, rescan, propose patch, approve review, export, reindex.
- Local-only, remote team, hosted product or enterprise deployment.
- Authentication, authorization and team permission requirements.
- Whether the wiki is git-backed, database-backed, desktop-local or hosted.
- Sensitivity/privacy requirements.
Procedure
1. Choose exposure mode
| Mode | Use when | Default permissions |
|---|---|---|
| local stdio MCP | Personal local-first wiki or editor integration. | Search/read/list only. |
| local HTTP MCP/API | Desktop app or local daemon. | Bind to 127.0.0.1, token for sensitive operations. |
| local reviewed-write MCP | User wants agents to propose link/page fixes. | Draft patches only. |
| local API + MCP wrapper | Existing app already exposes HTTP API. | MCP calls narrow domain endpoints. |
| remote read-only MCP/API | Team, ChatGPT/company knowledge, GitHub Copilot cloud or autonomous clients. | Search/read/fetch/lint only. |
| remote governed-write MCP/API | Team or product integration. | Auth, tenancy, audit logs, PR/review gates and rate limits required. |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 323 lines · 81 tokens per session scan A ebbcf9f1ffdd
llm-wiki-mcp-integration is a skill published in the GitHub repository po4yka/llm-wiki-skills (3 stars, last pushed 19d ago), licensed MIT. It adds 81 tokens to every session and 2,512 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
sandbox-environment
Sandbox API reference, proven patterns, and library recommendations for evaluateexpression.
okf-harness-bootstrap
This unified entrypoint routes setup and workspace maintenance without making the user choose a mode.
bus
Send and read messages between machines in a fleet over a shared Telegram group, so cross-machine coordination survives a file-sync outage and humans can watch the machines talk. A synced folder stays as the fallback for oversized payloads. Triggers: "/bus", "post to the bus", "check the bus", "tell the other…
routing
Version: 1.0 Autor: BACH System Datum: 2026-02-18 API-Key: Nicht erforderlich (OSRM public, Nominatim).
weather
Version: 1.0 Autor: BACH System Datum: 2026-02-18 API-Key: Nicht erforderlich (wttr.in).
okf-harness
One Door routes OKF Harness workspace requests to exactly one internal workflow at a time.