get_blog_post
Get a full blog post by its slug. Returns the complete post content, metadata, and URL. Source: getrecon.xyz
LABSCO SUMMARY
Returning whole chapters instead of matched snippets is the right call for this material, where the answer is usually the surrounding argument.
Invariant testing is a subject where a matched paragraph is often actively misleading — the useful part is the setup and the caveat around it. Tools that return the complete chapter or post let a model read the argument rather than reassemble it from fragments. Searching three sources in one call is the other practical piece, because this corpus is genuinely split across a docs site, a book and a newsletter, and knowing which one holds an answer is not something a reader should have to know first. refresh_cache is a small thing that says a lot: documentation caching is a normal cause of a confidently outdated answer, and having a way to clear it is better than having no explanation for why the answer is old.
What it is
A documentation retrieval client over three Recon properties: getrecon.xyz with its blog, glossary, comparisons and tool listings; the Recon Book of chapters and technical concepts; and the Recon Substack archive.
What you get
- search_all queries every source at once, with search_site, search_book and search_substack when the source matters.
- Retrieval returns full documents rather than excerpts — get_book_chapter, get_blog_post and get_substack_post each return the complete content with metadata.
- get_book_concept covers technical concepts directly, and search_glossary returns the top matching terms for vocabulary questions.
- get_comparison returns both entities with their strengths, which is a shape a plain search result cannot give you.
- list_book_chapters groups by category and list_substack_posts sorts by date, so the corpus can be browsed rather than only queried.
- list_tools enumerates the developer tools documented on the site.
- refresh_cache forces a reload from all three sources, so a stale answer has a remedy that does not involve restarting anything.
Requirements
Nothing to supply — the sources are public.
Setup effort
One command — npx @recon-fuzz-mcp/knowledge
USE CASES
01
Finding out what the docs say, wherever they say it
Search all three sources in one call rather than guessing whether an answer lives in the book, the blog or the newsletter.
02
Reading the whole argument, not a matched paragraph
Pull the full chapter or post once the search has located it — the surrounding context is usually where the caveat lives.
03
Settling a vocabulary question
Search the glossary for the term, or pull the comparison article that lays out both sides with their strengths.
04
Browsing rather than querying
List the book's chapters by category, the newsletter by date, or the developer tools the site documents.
14 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
get_book_chapter
Get a book documentation chapter by slug. Returns the full chapter content, category, and URL. Source: book.getrecon.xyz. Covers: Chimera framework, invariant testing, bootcamp, Recon Pro, tools, OSS repos.
get_book_concept
Get a technical concept explanation from the Recon Book. Covers: invariant testing, Chimera, stateful fuzzing, handlers, ghost variables, clamping, optimization mode, dynamic replacement, governance fuzzing, Recon Magic.
get_comparison
Get a comparison article by slug. Returns both entities, their strengths, conclusion, and FAQs. Source: getrecon.xyz
get_substack_post
Get a full Substack post by slug. Returns title, author, date, and full article content. Source: getrecon.substack.com (36 posts on invariant testing, fuzzing, engagement retrospectives, product updates).
list_book_chapters
List all chapters in the Recon Book, grouped by category (Getting Started, Writing Invariant Tests, Bootcamp, Using Recon Pro, Free Tools, OSS, Reference).
list_substack_posts
List all Recon Substack newsletter posts sorted by date. Shows title, subtitle, date, word count, and slug for each post.
list_tools
List all developer tools documented on getrecon.xyz. Returns up to 20 tools with descriptions and URLs.
refresh_cache
Force refresh the documentation cache from all three sources (getrecon.xyz, book.getrecon.xyz, getrecon.substack.com). Rate limited to once per 60 seconds.
search_all
Search across ALL Recon content — getrecon.xyz (blog, glossary, comparisons, tools), book.getrecon.xyz (chapters, concepts, FAQs), and getrecon.substack.com (newsletter posts). Returns top 15 matches with source labels.
search_book
Search across Recon Book documentation (chapters, concepts, FAQs). Returns top 10 matches. Source: book.getrecon.xyz
search_glossary
Search the Recon glossary for terms matching a query. Returns top 5 matching glossary terms with full definitions. Source: getrecon.xyz
search_site
Search across getrecon.xyz content (blog posts, glossary, comparisons, tools). Returns top 10 matches.
search_substack
Search across all Recon Substack posts. Returns top 10 matches with titles, dates, and content snippets.
BEFORE YOU INSTALL
What to know first
Tools you get
14 tools when we connected. Every tool reads; refresh_cache re-fetches sources at most once a minute. list_tools returns Recon's own developer tools, not this server's tool list.
Requires
npx on PATH
Where it runs
All 3 documented clients run the server on your machine.
CONTEXT COST
Light Standing cost
Rated by the size of the 14 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
TERMINAL
npx @recon-fuzz-mcp/knowledgeMCP Clients
Claude Code
CLAUDE CODE · TERMINAL
claude mcp add recon-knowledge -- npx @recon-fuzz-mcp/knowledgeClaude Desktop, Cursor
JSON
{
"mcpServers": {
"recon-knowledge": {
"command": "npx",
"args": [
"@recon-fuzz-mcp/knowledge"
]
}
}
}
