From 8e1e5817c297dda5443480eb0edbdba1391f61db Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pedro=20Hern=C3=A1ndez?= Date: Tue, 8 Sep 2026 22:16:10 -0400 Subject: [PATCH 1/2] Add peopleworks/SignsofAI to Education Rebased onto current main and updated: the server now exposes ten tools, eight of them fully local. Co-Authored-By: Claude Opus 5 Claude-Session: https://claude.ai/code/session_015PEbbiYSNPw7jE3LrPNhyF --- README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/README.md b/README.md index 6b4acd70b..22a8e3d10 100644 --- a/README.md +++ b/README.md @@ -1829,6 +1829,8 @@ MCP servers for learning management systems (LMS) and educational tools. - [anzy-renlab-ai/pronounce](https://github.com/anzy-renlab-ai/pronounce) [![pronounce MCP server](https://glama.ai/mcp/servers/anzy-renlab-ai/pronounce/badges/score.svg)](https://glama.ai/mcp/servers/anzy-renlab-ai/pronounce) ๐Ÿ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - Community pronunciation dictionary for developer project / product / jargon names (kubectl, nginx, GIF, JSON, Pydantic, Knative, LaTeX โ€” 1,848 entries). Each entry carries IPA, a General-American respelling, alternate readings where the pronunciation is contested, a source citation (creator interview / project FAQ / Wikipedia ยง Pronunciation), and a confidence level. Tools: `pronounce(word)`, `search_pronunciations(query)`, `list_pronunciations(category)`. Install: `uvx pronounce-mcp`. Live browse: . - [sf-shenfeng/learn-shell](https://github.com/sf-shenfeng/learn-shell) [![sf-shenfeng/learn-shell MCP server](https://glama.ai/mcp/servers/sf-shenfeng/learn-shell/badges/score.svg)](https://glama.ai/mcp/servers/sf-shenfeng/learn-shell) ๐Ÿ“‡ ๐Ÿ  - Agent-native teaching OS: gives your AI a classroom that remembers. 50 tools for courses, lessons, FSRS flashcards, graded exercises, real-time teaching sessions, and teaching-memory read-back (`get_context`) โ€” the agent authors and grades, reflects with evidence, and revises its own lessons; lesson completion belongs to the learner. Self-hosted (Postgres + web app), MIT. +- [peopleworks/SignsofAI](https://github.com/peopleworks/SignsofAI/tree/main/src/SignsOfAI.Mcp) [![peopleworks/SignsofAI MCP server](https://glama.ai/mcp/servers/peopleworks/SignsofAI/badges/score.svg)](https://glama.ai/mcp/servers/peopleworks/SignsofAI) #๏ธโƒฃ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - Explainable AI-writing detection and originality checking for teachers, students and writers, in English **and Spanish**. `analyze_ai_writing` returns a 0โ€“100 score *and every tell behind it* โ€” overused vocabulary, rhetorical crutches, syntactic patterns and sentence-rhythm burstiness โ€” each with the matched text and a concrete fix, instead of a black-box percentage. Ten tools in all: `check_originality` returns the shared passages between documents as evidence, `check_citations` cross-checks a bibliography against the text offline, `compare_to_baseline` runs Burrows's Delta against the same writer's earlier work, `inspect_characters` finds hidden and lookalike characters, `write_report` exports the evidence. Eight of the ten run entirely on the machine and the text never leaves it; two optional ones (perplexity, cross-language paraphrase) call a server and say so. Published false-positive rate at its 30/100 boundary: 2 of 296 texts written before generative models were in use (0.7%, 95% interval 0.2โ€“2.4%). .NET 10, MIT. Browser demo: + ### ๐Ÿ›’ E-Commerce MCP servers for e-commerce platforms and online store management. From b87d9234f92dc3e400b57dc05f5e8420c89c4a56 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Pedro=20Hern=C3=A1ndez?= Date: Wed, 9 Sep 2026 19:37:08 -0400 Subject: [PATCH 2/2] Say 'before 2022', and stop the entry counting its own tools Two corrections to the pending entry, both mine. The corpus line said the texts were written 'before generative models were in use'. GPT-3's API was in beta from mid-2020, so that is not true of a 2021 revision; the claim that holds is 'before 2022', which is weaker and correct. It is the wording the project itself uses in Docs/CALIBRATION.md. And the entry counted tools -- 'ten in all', 'eight of the ten'. An entry that enumerates goes stale the next time one ships; one that characterises does not. This now says 'every tool but two runs entirely on the machine', which stays true without anybody editing it. Also adds the install command, since the package is on NuGet. Co-Authored-By: Claude Opus 5 Claude-Session: https://claude.ai/code/session_015PEbbiYSNPw7jE3LrPNhyF --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 22a8e3d10..7639b0aee 100644 --- a/README.md +++ b/README.md @@ -1829,7 +1829,7 @@ MCP servers for learning management systems (LMS) and educational tools. - [anzy-renlab-ai/pronounce](https://github.com/anzy-renlab-ai/pronounce) [![pronounce MCP server](https://glama.ai/mcp/servers/anzy-renlab-ai/pronounce/badges/score.svg)](https://glama.ai/mcp/servers/anzy-renlab-ai/pronounce) ๐Ÿ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - Community pronunciation dictionary for developer project / product / jargon names (kubectl, nginx, GIF, JSON, Pydantic, Knative, LaTeX โ€” 1,848 entries). Each entry carries IPA, a General-American respelling, alternate readings where the pronunciation is contested, a source citation (creator interview / project FAQ / Wikipedia ยง Pronunciation), and a confidence level. Tools: `pronounce(word)`, `search_pronunciations(query)`, `list_pronunciations(category)`. Install: `uvx pronounce-mcp`. Live browse: . - [sf-shenfeng/learn-shell](https://github.com/sf-shenfeng/learn-shell) [![sf-shenfeng/learn-shell MCP server](https://glama.ai/mcp/servers/sf-shenfeng/learn-shell/badges/score.svg)](https://glama.ai/mcp/servers/sf-shenfeng/learn-shell) ๐Ÿ“‡ ๐Ÿ  - Agent-native teaching OS: gives your AI a classroom that remembers. 50 tools for courses, lessons, FSRS flashcards, graded exercises, real-time teaching sessions, and teaching-memory read-back (`get_context`) โ€” the agent authors and grades, reflects with evidence, and revises its own lessons; lesson completion belongs to the learner. Self-hosted (Postgres + web app), MIT. -- [peopleworks/SignsofAI](https://github.com/peopleworks/SignsofAI/tree/main/src/SignsOfAI.Mcp) [![peopleworks/SignsofAI MCP server](https://glama.ai/mcp/servers/peopleworks/SignsofAI/badges/score.svg)](https://glama.ai/mcp/servers/peopleworks/SignsofAI) #๏ธโƒฃ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - Explainable AI-writing detection and originality checking for teachers, students and writers, in English **and Spanish**. `analyze_ai_writing` returns a 0โ€“100 score *and every tell behind it* โ€” overused vocabulary, rhetorical crutches, syntactic patterns and sentence-rhythm burstiness โ€” each with the matched text and a concrete fix, instead of a black-box percentage. Ten tools in all: `check_originality` returns the shared passages between documents as evidence, `check_citations` cross-checks a bibliography against the text offline, `compare_to_baseline` runs Burrows's Delta against the same writer's earlier work, `inspect_characters` finds hidden and lookalike characters, `write_report` exports the evidence. Eight of the ten run entirely on the machine and the text never leaves it; two optional ones (perplexity, cross-language paraphrase) call a server and say so. Published false-positive rate at its 30/100 boundary: 2 of 296 texts written before generative models were in use (0.7%, 95% interval 0.2โ€“2.4%). .NET 10, MIT. Browser demo: +- [peopleworks/SignsofAI](https://github.com/peopleworks/SignsofAI/tree/main/src/SignsOfAI.Mcp) [![peopleworks/SignsofAI MCP server](https://glama.ai/mcp/servers/peopleworks/SignsofAI/badges/score.svg)](https://glama.ai/mcp/servers/peopleworks/SignsofAI) #๏ธโƒฃ ๐Ÿ  ๐ŸŽ ๐ŸชŸ ๐Ÿง - Explainable AI-writing detection and originality checking for teachers, students and writers, in English **and Spanish**. `analyze_ai_writing` returns a 0โ€“100 score *and every tell behind it* โ€” overused vocabulary, rhetorical crutches, syntactic patterns and sentence-rhythm burstiness โ€” each with the matched text and a concrete fix, instead of a black-box percentage. `check_originality` returns the shared passages between documents as evidence; `check_citations` cross-checks a bibliography against the text offline; `compare_to_baseline` runs Burrows's Delta against the same writer's earlier work; `inspect_characters` finds hidden and lookalike characters; `write_report` exports the evidence as a document a person can take to a committee. Every tool but two runs entirely on the machine and the text never leaves it; the two server-backed ones (perplexity, cross-language paraphrase) disclose that they send text. Published false-positive rate at its 30/100 boundary: 2 of 296 texts written before 2022 (0.7%, 95% interval 0.2โ€“2.4%). .NET 10, MIT. Install: `dnx SignsOfAI.Mcp --yes`. Browser demo: ### ๐Ÿ›’ E-Commerce