MCP server exposing 4 tools for algorithm-finder.
This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.
POST https://gateway.pipeworx.io/algorithm-finder/mcp
Content-Type: application/json
{"jsonrpc":"2.0","id":1,"method":"tools/list"}algorithm_find — Which algorithm, data structure or technique fits a computational problem. Describe the problem in words ("shortest route between two points with positive costs", "assign workers to jobs minimising cost", "find near-duplicate records", "schedule jobs to minimise lateness") and get the standard textbook methods (preconditions, worst-case / expected / amortized bounds, when to use and when not, alternatives, each fact cited to CLRS and other textbooks and to the NIST Dictionary of Algorithms and Data Structures), the open questions whose answers decide between them, Skiena Algorithm Repository problem pages, and recent research papers with dates from Hugging Face Papers and arXiv. want=common for textbook only, novel for recent papers only.algorithm_compare — Compare candidate algorithms against the facts of YOUR instance and get a verdict. Pass method names (e.g. ["dijkstra","bellman-ford"]) or a problem description, plus constraints such as {"negative_weights": true, "query": "single_source"}, {"stable": true, "key_type": "integer_small_range"}, {"exact": false, "dimensions": "high"}, {"false_positives_ok": true, "dynamic": "fully_dynamic"}. Each candidate gets satisfied / violated / unknown per constraint, read from a curated table cited to textbooks, papers and library docs; unknown means the table records nothing and is never guessed. Returns the winner (or "conditional" with the unknowns named, or "none_compatible"), each candidate's bounds and when-not advice, and the decisive questions you have not answered that would change the choice.algorithm_lookup — One named algorithm, data structure or technique in full: what it solves, preconditions, complexity bounds with their kind (worst-case / expected / amortized) and textbook citations, when to use it and what to use instead, the NIST DADS dictionary entry (definition, relations, implementation links), the cp-algorithms article, Skiena Algorithm Repository problem pages, and which languages Rosetta Code has solutions in. Accepts short names ("Dijkstra", "KMP", "union-find") and aliases.algorithm_implementations — Implementations of a named algorithm: the languages Rosetta Code has solutions in and, with language set, the source code of that solution (CC BY-SA 4.0, labelled educational), plus reference implementation links from the NIST DADS entry, the cp-algorithms article, and the Skiena Algorithm Repository implementation links for the problem.Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/algorithm-finder/
Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io