@pipeworx/wolfram-alpha

Connect: https://gateway.pipeworx.io/wolfram-alpha/mcp · Install: one-click buttons

Tools: 3

Wolfram Alpha MCP — computational, factual, and quantitative queries.

Tools

  • short_answer(query, units?) — single terse plain-text answer.
  • full_query(query, units?, include_pods?, format?) — structured pods.
  • wolfram_compute(code, time_constraint_seconds?) — evaluate Wolfram Language code in a real kernel (keyless; proxies Wolfram’s hosted MCP evaluator).

Auth

  • Platform key: gateway env PLATFORM_WOLFRAM_KEY (short_answer / full_query only).
  • BYO: ?_apiKey=<appid> after registering at https://developer.wolframalpha.com (free 2,000/mo).
  • wolfram_compute needs no key.

Evaluation semantics (triage note)

wolfram_compute transmits code verbatim — as a JSON field, no URL encoding anywhere in the path — and the kernel evaluates exactly what was sent. A result that disagrees with the intent of a question is almost certainly a bug in the submitted code, not in transmission or the kernel. Before filing a tool bug, echo the parse back through the tool itself:

wolfram_compute({ code: "ToString[Hold[<the code>], InputForm]" })

Worked incident (fleet #422, 2026-08-17): Length[Select[Permutations[Range[5]], And@@Thread[#!=Range[5]]&]] was reported as “returns 119, should be 44 (derangements of 5)”. 119 is the correct value of that code: on two concrete lists, perm != Range[5] evaluates eagerly to a single True/False (whole-list Unequal) before Thread can split it elementwise, so the predicate collapses to “permutation ≠ identity” and counts 120 − 1 = 119. The elementwise form And @@ MapThread[Unequal, {#, Range[5]}] & (or just Subfactorial[5]) returns 44 through the same tool.

Data source

  • Short Answers v1: https://api.wolframalpha.com/v1/result
  • Full Results v2: https://api.wolframalpha.com/v2/query (output=JSON)
  • Wolfram Language kernel: https://agenttools.wolfram.com/mcp (hosted by Wolfram Research)

Tools

  • short_answer — Get a single terse plain-text answer from Wolfram Alpha. Best for: arithmetic, unit conversion, “what is X”, “how many Y in Z”, factual lookups (planet diameter, country GDP, element atomic weight, cu
  • full_query — Get the full structured result from Wolfram Alpha. Returns named “pods” (Input, Result, Solution, Plot, Properties, etc.) — useful when short_answer is too terse or you need multiple facets (e.g., ele
  • wolfram_compute — Evaluate Wolfram Language code in a real Wolfram kernel — symbolic math (Integrate, Solve, DSolve, Simplify, Series, Limit), exact arithmetic, matrix algebra, number theory, unit conversion, and any W

Tools

  • full_query — Get the full structured result from Wolfram Alpha. Returns named pods (Input, Result, Solution, Plot, Properties, etc.) — useful when short_answer is too terse or you need multiple facets (e.g., eleme
  • short_answer — Get a single terse plain-text answer from Wolfram Alpha. Best for: arithmetic, unit conversion, what is X , how many Y in Z , factual lookups (planet diameter, country GDP, element atomic weight, curr
  • wolfram_compute — Evaluate Wolfram Language code in a real Wolfram kernel — symbolic math (Integrate, Solve, DSolve, Simplify, Series, Limit), exact arithmetic, matrix algebra, number theory, unit conversion, and any W

Regenerated from source · build September 10, 2026