WolframResearch/AgentTools

Implements a model context protocol server using Wolfram Language

This repository also configures its own agents. See what AgentTools tells them →

96Stars on the repository
21Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

wolfram-alpha

01

WolframResearch/AgentTools

Skill Claude CodeCodex

Queries Wolfram|Alpha for up-to-date computational results and retrieves contextual information via semantic search. Use this skill when the user needs real-world data, calculations, or factual answers about entities in science, math, geography, history, finance, and more.

not rated 96 +1 changed 18d ago A SkillSpector: pass 55 tokens original MIT

dup-skill

02

WolframResearch/AgentTools

Skill Claude CodeCodex

A skill with both a skill directory and a definition file.

not rated 96 +1 yesterday A 16 tokens original MIT

other-name

03

WolframResearch/AgentTools

Skill Claude CodeCodex

A skill directory whose SKILL.md name differs from the declared name.

not rated 96 +1 yesterday A 17 tokens original MIT

wrong-name

04

WolframResearch/AgentTools

Skill Claude CodeCodex

The skill directory named by the Location of bad-location-skill, which has a different name.

not rated 96 +1 yesterday A 22 tokens original MIT

located-skill

06

WolframResearch/AgentTools

Skill Claude CodeCodex

A skill whose LLMSkill definition has a relative Location inside an extension root.

not rated 96 +1 yesterday A 20 tokens original MIT

dev-skill

07

WolframResearch/AgentTools

Skill Claude CodeCodex

A skill directory in the second extension root.

not rated 96 +1 yesterday A 13 tokens original MIT

foreign-skill

08

WolframResearch/AgentTools

Skill Claude CodeCodex

A skill directory outside of the extension roots, which must never be used.

not rated 96 +1 yesterday A 19 tokens original MIT

wolfram-debugging

09

WolframResearch/AgentTools

Skill Claude CodeCodex

Verified recipes and tested helpers for debugging Wolfram Language code. Use whenever code issues messages, returns $Failed, Failure or unevaluated calls, gives wrong results, is slow, hangs or crashes, or works in one environment but not another; for stack traces, call logs, profiles, mocks or overrides, watchpoints…

not rated 96 +1 yesterday A 115 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: