Docs

API

tirogla is one remote MCP server that gives your AI the building blocks of real systems. Ask for a system and your AI gets its component graph: every part it needs, how the parts fit together, and the design questions to settle first. Then it reads deep-dives on single blocks (how it works, code, pitfalls, libraries) while it builds. Your AI designs from proven building blocks instead of guessing.

System graph: every building block a system needs, with alternatives and design questions.
Block deep-dives: how it works, code, complexity, pitfalls, efficiency and libraries, one section at a time.
Build bundle: what your AI needs to build the system, in one call.

Connect: add https://tirogla.com/mcp in Claude, Cursor or any MCP client, for example claude mcp add --transport http tirogla https://tirogla.com/mcp. For scripts, the same calls are HTTP JSON under /v1.

Plans: free for everyone during early access (until 15 November 2026). After that, Free gives search and the core page sections at about 100 calls a day; Pro adds system graphs with design questions, all page sections, the build bundle and higher limits.

claude mcp add --transport http tirogla https://tirogla.com/mcp

No key needed to read; an API key from your account raises the limits.

Tools

MCP tool	HTTP	What it returns
`search`	`GET /v1/search?q=`	Systems and building blocks for a query, each with why it matched
`system_graph`	`GET /v1/system/{id}`	The component graph of a system: every part, what it builds on, alternatives and design questions
`get_entry`	`GET /v1/entry/{slug}?part=`	A page: overview, or one section (Code, Pitfalls, Efficiency, …), with its relations
`list_systems`	`GET /v1/systems`	All systems by section
`list`	—	Block pages by domain
`request_entry`	`POST /v1/requests`	Ask for a missing topic; repeats count as votes

Example call

search{query: "rate limiter for an API"} returns

system  global-rate-limiter
system  api-gateway
block   distributed-rate-limiting   Enforce one rate limit across N servers: a central atomic counter,
                                    a limit split per node, or batched token leases…

and get_entry{slug: "distributed-rate-limiting", part: "overview"} returns the page's overview.