wiki-query-mcp

A search and reading tool for a local wiki memory service, which stores information in topic-based pages.

In plain words
What is it for?
Use it to search topics, read wiki pages, view recent activity, find pages that link to another page, and browse pages by tags. The wiki memory service must already be running.
Why use it?
It helps an agent find relevant notes without manually browsing every wiki page. It can search one topic or all topics and then open matching pages.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/rossoctl/examples/wiki-query-mcp
Any agent
npx skills add rossoctl/examples --skill wiki-query-mcp
Clone the repo
git clone --depth 1 https://github.com/rossoctl/examples

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 632 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00632
Opus 5 $0.00000 $0.00316
Sonnet 5 $0.00000 $0.00126
Haiku 4.5 $0.00000 $0.00063

Measured 2d ago against content hash 6f2f4a379d5b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wiki-query-mcp 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 2d 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.

mcp/wiki_memory_tool/skills/wiki-query-mcp/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kwiki Query Agent (MCP)

Query the wiki memory service to find and read information on behalf of a user.

Prerequisites

The wiki-memory MCP server must be registered and running (stdio or streamable-http on port 8322).

Procedure

  1. List available topics — Call wiki_list_topics to see what topics exist and their page counts.

  2. Search for information — Call wiki_query with:

    • topic_id: the topic to search (e.g. "ai", "security")
    • query: natural language search terms
    • limit: max results (default 10)
  3. Search across all topics — Call wiki_search_all with:

    • query: search terms
    • limit: max results (default 10)
  4. Read specific pages — Call wiki_read with:

    • topic_id: the topic
    • path: page filename (e.g. "transformers.md") Returns content with frontmatter metadata.
  5. Activity feed — Call wiki_activity with:

    • topic_id: (optional) specific topic, or empty for global
    • limit: max entries (default 20)
  6. Find backlinks — Call wiki_backlinks with:

    • topic_id: the topic
    • path: page to find references to
  7. Browse by tags — Call wiki_list_tags with topic_id, or wiki_pages_by_tag with topic_id and tag.

  8. Page graph — Call wiki_graph with topic_id to get nodes and edges.

  9. List drafts — Call wiki_list_drafts with topic_id.

  10. Get templates — Call wiki_get_template with optional template_id.

Example Flow

wiki_list_topics → "ai (4 pages), security (0 pages)"
wiki_query(topic_id="ai", query="attention mechanism") → ranked results
wiki_search_all(query="transformer") → results across all topics
wiki_read(topic_id="ai", path="transformers.md") → content + frontmatter
wiki_activity(topic_id="ai") → recent commits
wiki_backlinks(topic_id="ai", path="transformers.md") → pages linking here
wiki_list_tags(topic_id="ai") → tags with counts
wiki_pages_by_tag(topic_id="ai", tag="paper") → pages with tag
wiki_graph(topic_id="ai") → {"nodes": [...], "edges": [...]}
wiki_list_drafts(topic_id="ai") → pending drafts
wiki_get_template(template_id="paper-summary") → template content

Read the full file on GitHub · 64 lines

Changes

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.

  1. 2d ago First seen · 64 lines · 0 tokens per session scan A 6f2f4a379d5b

Subscribe to this mod's changes

wiki-query-mcp is a skill published in the GitHub repository rossoctl/examples (11 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 632 tokens. 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 2026-08-30.

Related

Other skills, from other repositories

importing-a-codebase

Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).

JetBrains/thinkrail · 69 tokens

starting-a-new-project

Use when the workspace is empty — no code yet — and the user brings a raw idea: the brand-new branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for features in an existing project — use brainstorming instead.

JetBrains/thinkrail · 61 tokens

todos

This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…

JetBrains/thinkrail · 127 tokens

writing-workflow-skills

Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.

JetBrains/thinkrail · 60 tokens

spec-graph

The project's specs are its ground truth: durable documents describing the architecture, decisions, contracts, and boundaries behind the code, organized as a connected graph. Read this skill and reach for the spec tools FIRST — before reading code — whenever you explore the project, plan or start a task, add or change…

JetBrains/thinkrail · 97 tokens

asking-user-questions

Use when composing an askuserquestion round inside a workflow, or when a workflow skill names it at a question step. Shared norms for the tool — not a workflow, nothing to execute.

JetBrains/thinkrail · 43 tokens