{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_tkgs3p6j8mgn","handle":"manimgl-mcp","url":"https://wellknown.network/agents/manimgl-mcp","links":{"self":"https://wellknown.network/agents/manimgl-mcp/record.json","html":"https://wellknown.network/agents/manimgl-mcp","markdown":"https://wellknown.network/agents/manimgl-mcp/record.md","api":"https://wellknown.network/api/v1/agents/manimgl-mcp","status":"https://wellknown.network/api/v1/agents/manimgl-mcp/status","claim":"https://wellknown.network/agents/manimgl-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/manimgl-mcp/claim.json","badge":"https://wellknown.network/agents/manimgl-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/manimgl-mcp/history","tools":"https://wellknown.network/api/v1/agents/manimgl-mcp/tools"},"ard":{"identifier":"urn:air::server:manimgl-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"manimgl-mcp","summary":"MCP server for ManimGL - generate and render mathematical animations via AI","description":"# manimgl-mcp\n\nA Model Context Protocol (MCP) server that gives AI assistants the ability to create mathematical animations programmatically. Features RAG-powered code generation, multi-agent pipelines, and audio narration.\n\n## What This Does\n\nThis MCP server exposes **25 tools** that allow AI models to:\n\n1. **Generate Animation Code** - Write scene definitions with RAG-powered assistance\n2. **Render Videos** - Produce MP4, GIF, or PNG outputs at various quality levels\n3. **Interactive Development** - Headless IPython sessions for iterative code testing\n4. **Multi-Agent Pipeline** - Concept analysis → scene planning → code generation → review\n5. **Audio Narration** - Generate TTS narration synced to videos\n\n## Key Features\n\n- **RAG-Powered Code Generation** - Semantic search over indexed ManimGL API and examples\n- **Multi-Provider LLM** - Supports Gemini, Claude, DeepSeek, GPT-4o via litellm\n- **Parameter Validation** - Validates API calls against indexed signatures\n- **Self-Learning** - Stores error patterns and fixes for continuous improvement\n- **8 Animation Templates** - Riemann sums, matrix transforms, Fourier series, etc.\n\n## System Requirements\n\n- **Python 3.10–3.13** — Python 3.14+ is **not** supported. `manimlib` depends on `pydub`, which requires the `audioop` standard library module removed in Python 3.13. Use a Python ≤ 3.13 environment.\n- **FFmpeg** — for video encoding\n- **LaTeX** — for mathematical notation (optional)\n\nNo display server is required. Interactive sessions are fully headless — they run inside a plain IPython REPL with manimlib pre-loaded, no OpenGL window is ever opened.\n\n## Installation\n\n### Recommended: install into a Python 3.13 venv\n\n```bash\n# Create a Python 3.13 virtual environment\npython3.13 -m venv ~/.venv\n\n# Install from PyPI\nuv pip install manimgl-mcp --python ~/.venv/bin/python\n\n# Or from source\ngit clone https://github.com/pranavgundu/manimgl-mcp.git\ncd manimgl-mcp\nuv pip install -e . --python ~/.venv/bin/python\n```\n\n### Sys…","publisher":{"name":"Pranav","url":null},"homepage":"https://github.com/pranavgundu/manimgl-mcp","repository":"https://github.com/pranavgundu/manimgl-mcp","version":"0.2.0","license":null,"protocols":["mcp"],"tags":["ai","animation","llm","manimgl","math","mcp","visualization"],"pricing":null,"endpoints":[{"url":"pypi:manimgl-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"analytics.reporting","name":"Reporting & Dashboards","confidence":1,"provenance":"declared"},{"slug":"data.vector-search","name":"Vector Search","confidence":0.814,"provenance":"derived"},{"slug":"dev.ci-cd","name":"CI/CD & Deploy","confidence":0.756,"provenance":"derived"},{"slug":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["analytics","data","dev"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"manimgl-mcp","registry":"pypi","observedAt":"2026-10-28T09:23:06.369Z","publishedAt":"2026-03-27T05:15:12.185407Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"manimgl-mcp","url":"https://pypi.org/project/manimgl-mcp/","firstSeenAt":"2026-09-09T23:26:39.706Z","fetchedAt":"2026-10-28T09:21:49.638Z","normalizedAt":"2026-10-28T09:21:49.638Z"}]},"firstSeenAt":"2026-09-09T23:26:39.706Z","updatedAt":"2026-10-28T09:23:06.369Z"}