Tag

#IDE

385 results found

Picsart Genai MCP
@Picsart

**Picsart MCP — 150+ AI Models for Images, Video & Audio, One Connection** Picsart's AI Playground brings together more than 150 generative AI models from 24+ providers into one place. The MCP server is the developer and agent interface to that playground — a single connection that gives any AI agent or coding assistant the ability to generate images, video, audio, and text without managing a tangle of separate API keys, billing accounts, or SDKs. **What it generates** - **Images** — Text-to-image, style transfer, AI upscaling, background removal, image enhancement. Powered by models including Flux and other leading image generation providers. - **Video** — Text-to-video and image-to-video generation with top-tier models: Sora, Kling, and Veo, with more added regularly. - **Audio** — Voice synthesis, sound generation, and audio creation via ElevenLabs and other audio providers. - **Text** — Creative copywriting, captions, and content generation integrated directly into multi-modal workflows. **Why it's different from calling model APIs directly** Most creative AI workflows end up routing through three or four separate APIs — one for image generation, another for video, another for voice. Each comes with its own pricing model, rate limits, and integration overhead. Picsart MCP collapses that into one connection. Pricing is pay-per-generation. No monthly model subscriptions stacked on top of each other — access to the full model library for what you actually use. Compared to maintaining individual subscriptions across the leading generative AI providers, that difference runs to several thousand dollars a year. **Works wherever agents work** Picsart MCP follows the Model Context Protocol standard, which means it plugs into any MCP-compatible environment: - **Claude Desktop** — Add to `claude_desktop_config.json`, restart, and your Claude sessions can generate media on demand. - **Claude Code** — Run `claude mcp add` or drop the config into `.mcp.json` in your project root. Works immediately in the CLI and in IDE-integrated sessions. - **Cursor** — Add to `.cursor/mcp.json`. Every Cursor agent and AI panel gets creative generation capabilities. - **ChatGPT** — Compatible via MCP-to-plugin bridge. - **Hermes, Cowork, and other agentic frameworks** — Any tool that supports MCP transport (Streamable HTTP or stdio) connects without modification. **Get started in under a minute** ```json { "mcpServers": { "picsart-gen-ai": { "type": "http", "url": "https://api.picsart.com/gen-ai/mcp" } } } ``` Add this block to your MCP client's config file, drop in your Picsart API key, and restart. The full model library is available immediately — no additional setup, no per-model configuration. **Built for agentic workflows** The tools exposed by Picsart MCP are designed to work as steps inside larger agent pipelines, not just one-off generation requests. A workflow might look like: agent receives a brief → generates a hero image with Flux → generates a short video loop with Kling → synthesizes a voiceover with ElevenLabs → returns all three assets in one pass. That entire sequence runs through a single MCP server, from a single API key, billed per generation. **Part of the Picsart AI Playground** The MCP server is one interface to Picsart's broader AI Playground — a platform that aggregates the world's leading generative AI models so creators, developers, and agents can access them without vendor lock-in. The Playground is also available via direct API and web UI for non-agent workflows.

23 days ago
Spimov Ai Video Clone Dubbing Mcp Server
@spimov

Spimov MCP — AI video dubbing, inside your chat Spimov MCP connects the Spimov (https://spimov.com) dubbing engine to Claude and any Model Context Protocol client. Ask in plain language — "dub this YouTube short into German and upload it unlisted to my channel" — and the whole pipeline runs server-side: transcription, translation, voice synthesis, lip-sync, and publishing. What you can do - 🎬 Dub from a YouTube link or a local file — regular videos, Shorts, and YouTube Music all supported. - 🌍 17 target languages, with auto source-language detection. - 🗣️ Choose your voice engine — xtts (high-quality, default), chatterbox (emotion-aware), or elevenlabs. - ✍️ Edit before you publish — list transcript segments and fix any line's text, emotion, or speaker; only that segment is re-synthesized. - 💬 Subtitles your way — fetch SRT/VTT, burn them in, or embed soft tracks in extra languages. - 🎚️ Remix without re-dubbing — adjust the audio mix, subtitle styling, or lip-sync on a finished job. - 📺 Publish to YouTube automatically when the dub finishes. - 🔗 Get a shareable download link for the finished MP4 — works in the browser, no API key needed. Works everywhere MCP does - Claude Desktop / Claude Code (stdio) — supports local file upload. - Claude web & hosted clients — connect to the hosted Streamable HTTP server, no install required. Setup in 2 minutes — grab an API key from spimov.com, drop it into your MCP config, and start dubbing. --- 4. Launch / duyuru postu (X / LinkedIn) ▎ We just shipped Spimov MCP 🎬 ▎ ▎ Dub any video into 17 languages without leaving your AI chat. Paste a YouTube link → Claude transcribes, translates, voices, and can publish it straight to YouTube. ▎ ▎ • Local file or YouTube URL ▎ • Edit any line, re-synth just that segment ▎ • SRT/VTT, burned-in or soft subtitles ▎ • Works in Claude Desktop, Claude Code & Claude web ▎ ▎ pip install spimov-mcp → spimov.com ▎ #MCP #Claude #AIdubbing --- 5. MCP marketplace metadata (alanlar) - Name: Spimov - Category: Media / Video - Description: Dub videos into 17 languages, edit translations, generate subtitles, and publish to YouTube — from any MCP client. - Auth: API key (spk_live_…) - Homepage: https://spimov.com - Install: pip install spimov-mcp (stdio) or connect https://mcp.spimov.com/mcp (HTTP)

a month ago
Muxara
@muxara

a month ago
Verify Action
@Armada735

Verify AI agent tool calls with content-addressed, HMAC-attested receipts. Free third-party verification API for AI agents. Call verify_action(claim, evidence) to get an independent integrity check on whether your claimed action matches the actual evidence. Useful for catching silent failures: incorrect SQL operations, file-op mismatches, API call inconsistencies, and code-diff scope creep. Five specialized verifier kinds: - code_diff: verb / path / identifier coherence with unified diff - db_op: row delta + SQL operation + ID match - file_op: existence state + line/size delta - api_call: request body and response status coherence - generic: conservative fallback Returns: - aar_verdict: verified | contradicted | insufficient_evidence | unsafe_to_verify - verdict: ok | mismatch | uncertain (legacy 3-value alias) - reasoning, confidence - receipt: verify_action_receipt.v0 with HMAC-SHA256 signature, content-addressed via SHA-256 hashes of claim and evidence Cross-vendor: works with Claude Code, Cursor, Cline, Codex, Codeium, and any MCP-compatible harness. Stateless, per-request, no API key, no registration. Pure Python stdlib (no pip install). Anonymized telemetry only — no PII, no model fingerprint, no raw claim/evidence retention. Honest scope: this is a small reference implementation, not a canonical inter-vendor standard. v0 receipts use HMAC-SHA256 (symmetric, single-issuer); v1 with ed25519 + multi-issuer is on the roadmap. The hosted endpoint has no SLA — self-host for stability (git clone && ./start.sh). 90-day probe with explicit kill criteria. If adoption appears, v1 schema work begins. If response is null, the null is itself a publishable data point.

2 months ago
Lexicon
@Nadine

3 months ago