Writing & Editing

search pubmed via MCP

Create Slides with a simple Python MCP server using Python PPTX library

Unofficial Relace MCP Server - Fast code merging via Relace API

Model Context Protocol server for DaVinci Resolve integration

Pydantic-AI based Multi-Agent Framework with YAML-based Agents, Teams, Workflows & Extended ACP / AGUI integration

Locale vocabulary audit (calques, inventeds, foreign slips). Local CLI via stdio — no hosted API.

CV and resume builder for AI assistants: create, edit and preview CVs in the right format for each European country (14 languages), choose ATS-friendly templates, run free ATS and GDPR checks, tailor a CV to a job ad, write cover letters, prepare interviews, translate CVs, export Europass, build a …

Reviews drafts: fact-checks claims against web sources and builds the strongest counter-case.

Turn a long tennis recording into a labeled highlight reel: lossless rally clips, hit-count labels.

Video editing through the Cassette agent: import media, edit by chat turn, read the timeline, export

Guardrailed video editing for AI agents: FFmpeg, captions, effects, Hyperframes, and receipts.

Clean up talk recordings: find redos, retakes and dead air, review every cut, render and verify.

Checks every LaTeX reference against Crossref, dblp, arXiv, DataCite, PubMed and OpenAlex. No LLM.

Let your AI read any video: timed transcript, full-resolution frames, screen text, claim checks.

Hosted MCP server that lets agents summarize, transcribe, and chat with video / audio / podcast content from 30+ platforms (YouTube, Bilibili, TikTok, X, Apple Podcasts, Coursera, TED, …) or local files. Streamable-http transport with OAuth2 / Bearer auth.

Local video editing engine for agents: exact timelines, saved sessions, rendering and FFmpeg export.

Edit video by editing the transcript. Runs locally; agent edits arrive as suggestions you approve.

Read-only MCP server over public email-marketing facts for 750+ Nordic and European B2C brands: how often a brand emails, when it last sent, and which brands in a market email most. No authentication. Figures are what Signal observed, never estimates.

Aggregate anonymous tool usage for an inclusive ISO date range, e.g. 2026-08-01 to 2026-08-07. Returns `total_calls`, `by_outcome`, `by_tool`, `by_dataset`, `trust_verdict_calls` (the count of trust_verdict records regardless of outcome or result shape), and `trust_distribution` (counts of returned…

Return a freshness-at-a-glance summary of the published catalogue: fresh, aging, stale, and reference counts plus the latest health check time. Use it for catalogue-level freshness context; do not use it to enumerate affected datasets—use find_stale instead. It reads the latest published snapshot, …