{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_rq3cuvvkqw3h","handle":"tensordiagram-mcp","url":"https://wellknown.network/agents/tensordiagram-mcp","links":{"self":"https://wellknown.network/agents/tensordiagram-mcp/record.json","html":"https://wellknown.network/agents/tensordiagram-mcp","markdown":"https://wellknown.network/agents/tensordiagram-mcp/record.md","api":"https://wellknown.network/api/v1/agents/tensordiagram-mcp","status":"https://wellknown.network/api/v1/agents/tensordiagram-mcp/status","claim":"https://wellknown.network/agents/tensordiagram-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/tensordiagram-mcp/claim.json","badge":"https://wellknown.network/agents/tensordiagram-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/tensordiagram-mcp/history","tools":"https://wellknown.network/api/v1/agents/tensordiagram-mcp/tools"},"ard":{"identifier":"urn:air::server:tensordiagram-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"tensordiagram-mcp","summary":"MCP server for drawing tensors with tensordiagram","description":"# tensordiagram mcp server\n\nmcp server that enables AI assistants like Claude to draw diagrams of tensors.\n\n## overview\n\nThis mcp server provides the `draw_tensor` tool, allowing LLMs to create clear, visual representations of tensors to help users understand tensor shapes, operations, and dimensional transformations. Built on top of [tensordiagram](https://github.com/hardik-vala/tensordiagram) and [FastMCP](https://github.com/jlowin/fastmcp).\n\n## install\n\n### option 1: PyPI\n\n```bash\npip install tensordiagram-mcp\n```\n\n### option 2: from source\n\n```bash\ngit clone https://github.com/hardik-vala/tensordiagram.git\ncd tensordiagram/mcp\npip install -e .\n```\n\n### option 3: Docker\n\n```bash\ngit clone https://github.com/hardik-vala/tensordiagram.git\ncd tensordiagram/mcp\ndocker build -t tensordiagram/mcp:latest .\ndocker run -i --rm --name tensordiagram-mcp tensordiagram/mcp:latest\n```\n\n## configuration\n\n### Claude Desktop\n\nAdd this to your Claude Desktop configuration file:\n\n**macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`\n**Windows**: `%APPDATA%/Claude/claude_desktop_config.json`\n\n#### using pip installation\n\n```json\n{\n  \"mcpServers\": {\n    \"tensordiagram\": {\n      \"command\": \"python\",\n      \"args\": [\"-m\", \"tensordiagram_mcp\"]\n    }\n  }\n}\n```\n\n#### using local installation\n\n```json\n{\n  \"mcpServers\": {\n    \"tensordiagram\": {\n      \"command\": \"python\",\n      \"args\": [\"/path/to/tensordiagram/mcp/server.py\"]\n    }\n  }\n}\n```\n\n#### using Docker\n\n```json\n{\n  \"mcpServers\": {\n    \"tensordiagram\": {\n      \"command\": \"docker\",\n      \"args\": [\"run\", \"-i\", \"--rm\", \"--name\", \"tensordiagram-mcp\", \"tensordiagram/mcp:latest\"]\n    }\n  }\n}\n```\n\nAfter updating the configuration, restart Claude Desktop.\n\n## usage\n\nOnce installed, Claude can use the `draw_tensor` tool to create visualizations. Here are some examples:\n\n### example prompts\n\n> \"Can you show me what a 3x4 tensor looks like?\"\n> \"Draw a 2x3x4 tensor in coral color\"\n> \"Visualize a 3x3 identity matrix with the…","publisher":{"name":"tensordiagram contributors","url":null},"homepage":"https://github.com/hardik-vala/tensordiagram","repository":"https://github.com/hardik-vala/tensordiagram","version":"0.1.0","license":null,"protocols":["mcp"],"tags":["mcp"],"pricing":null,"endpoints":[{"url":"pypi:tensordiagram-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":"dev.version-control","name":"Version Control","confidence":0.745,"provenance":"derived"}],"categories":["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":"tensordiagram-mcp","registry":"pypi","observedAt":"2026-11-04T02:26:22.230Z","publishedAt":"2025-11-28T05:38:16.956534Z","latestVersion":"0.1.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"tensordiagram-mcp","url":"https://pypi.org/project/tensordiagram-mcp/","firstSeenAt":"2026-09-10T13:21:19.957Z","fetchedAt":"2026-11-04T02:24:49.627Z","normalizedAt":"2026-11-04T02:24:49.627Z"}]},"firstSeenAt":"2026-09-10T13:21:19.957Z","updatedAt":"2026-11-04T02:26:22.230Z"}