{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_eztvd8k5anq7","handle":"paraview-mcp-python","url":"https://wellknown.network/agents/paraview-mcp-python","links":{"self":"https://wellknown.network/agents/paraview-mcp-python/record.json","html":"https://wellknown.network/agents/paraview-mcp-python","markdown":"https://wellknown.network/agents/paraview-mcp-python/record.md","api":"https://wellknown.network/api/v1/agents/paraview-mcp-python","status":"https://wellknown.network/api/v1/agents/paraview-mcp-python/status","claim":"https://wellknown.network/agents/paraview-mcp-python/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/paraview-mcp-python/claim.json","badge":"https://wellknown.network/agents/paraview-mcp-python/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/paraview-mcp-python/history","tools":"https://wellknown.network/api/v1/agents/paraview-mcp-python/tools"},"ard":{"identifier":"urn:air::server:paraview-mcp-python","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"paraview-mcp-python","summary":"MCP server for controlling ParaView via AI assistants","description":"# ParaView MCP Server\n\nControl ParaView with AI assistants through the Model Context Protocol (MCP).\n\n`paraview-mcp-python` provides an MCP server and a ParaView-side bridge. MCP clients such as Codex CLI and Claude Desktop can use it to inspect a ParaView session, open datasets, apply filters, color data, run ParaView Python, and export screenshots.\n\nThe MCP server command is:\n\n```bash\nparaview-mcp-server\n```\n\n<img width=\"1280\" height=\"720\" alt=\"ParaView MCP Server demonstration\" src=\"https://github.com/user-attachments/assets/6e21f408-72b6-4523-a527-55b283b9e274\" />\n\n## Architecture\n\nThe GUI workflow has four components:\n\n| Component | Runs in | Purpose |\n|---|---|---|\n| MCP client | Codex CLI, Claude Desktop, or another MCP host | Starts the MCP server and calls its tools. |\n| MCP server | Standard Python environment | Communicates over MCP stdio and forwards calls to ParaView over TCP. |\n| ParaView bridge | `pvpython` process | Receives JSON commands over TCP and executes `paraview.simple` operations. |\n| ParaView runtime | `pvserver` and a ParaView GUI client | Owns the shared session used by the GUI and bridge. |\n\nParaView Python plugins and VTK timer callbacks are pipeline-extension mechanisms, not a general-purpose remote-control interface for a live GUI process. This project therefore uses ParaView's client/server model.\n\n`paraview-mcp-launch` starts a local `pvserver`, connects the ParaView GUI as the first client, and then connects a `pvpython` bridge to the same session.\n\n```text\n┌──────────────────────────────┐      stdio      ┌────────────────────────┐\n│ MCP Client                   │ ◄──────────────► │ MCP Server             │\n│ Codex / Claude / other host  │                  │ paraview-mcp-server    │\n└──────────────────────────────┘                  └──────────┬─────────────┘\n                                                              │ JSON/TCP\n                                                              │ 127.0.0.1:9876\n                       …","publisher":null,"homepage":"https://github.com/djeada/paraview-mcp-server","repository":"https://github.com/djeada/paraview-mcp-server","version":"0.2.0","license":null,"protocols":["mcp"],"tags":["ai","mcp","model-context-protocol","paraview","scientific-computing","visualization"],"pricing":null,"endpoints":[{"url":"pypi:paraview-mcp-python","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"}},"derived":{"capabilities":[{"slug":"analytics.reporting","name":"Reporting & Dashboards","confidence":1,"provenance":"declared"},{"slug":"research.academic","name":"Academic Research","confidence":0.713,"provenance":"derived"}],"categories":["analytics","research"],"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":"paraview-mcp-python","registry":"pypi","observedAt":"2026-10-22T17:24:51.553Z","publishedAt":"2026-09-22T16:18:16.793331Z","latestVersion":"0.2.0"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"paraview-mcp-python","url":"https://pypi.org/project/paraview-mcp-python/","firstSeenAt":"2026-09-10T09:25:34.182Z","fetchedAt":"2026-10-22T17:23:02.564Z","normalizedAt":"2026-10-22T17:23:02.564Z"}]},"firstSeenAt":"2026-09-10T09:25:34.182Z","updatedAt":"2026-10-22T17:24:51.553Z"}