LS-PrePost-MCP
Related Servers
Alternatives to LS-PrePost-MCP
No user-submitted related servers found.
Related Servers
- AlicenseCqualityAmaintenanceEnables AI assistants to control and automate Abaqus/CAE simulations via MCP, including model query, job management, ODB inspection, KPI extraction, capsule tracking, physics contract validation, report generation, and viewport capture. It also supports noGUI batch mode, dual transport, and integration with Codex/Claude clients.1103MIT
- FlicenseNot gradedqualityCmaintenanceEnables an AI assistant to drive Abaqus/CAE through file IPC—sending Python commands, querying model info, submiting jobs, and capturing viewport screenshots—so finite element models can be built and solved without manual GUI interaction.2-
- FlicenseNot gradedqualityCmaintenanceEnables driving ANSA's GUI through MCP with 78 tools and 5 resources for modeling, meshing, checks, connections, and scripting, plus embedded ANSA API documentation lookup. Operations execute in the visible ANSA session via a file-based command queue, with pre-execution script validation and cross-session memory.5-
- AlicenseAqualityAmaintenanceEnables natural-language control of Abaqus/Standard FEA simulations, allowing users to build models, run jobs headlessly, and automatically diagnose and fix solver failures by reading output files and retrying.2249 PyPI2AGPL 3.0
- FlicenseNot gradedqualityDmaintenanceEnables to interact with Abaqus FEA software through an MCP bridge, supporting connection checks, script execution, model queries, job submission, and simulation automation.3-
- FlicenseNot gradedqualityCmaintenanceConnects AI clients to BETA CAE Systems ANSA running in listener mode over ANSA's native IAPConnection (TCP) protocol, exposing roughly 49 pre-processing operations as MCP tools for model I/O, entity queries and editing, quality checks, meshing, connector application, and viewport visibility. It also allows arbitrary ANSA Python scripts to be sent to ANSA and executed, covering APIs beyond the built-in tool set.3-
TDQS
Scored across 30 tools
Several tools overlap heavily: extract_d3plot_nodal, extract_nodal_results, extract_node_history, and extract_lsreader_nodal all pull nodal data, and the six inspect_* tools (d3plot_scl, d3plot_database, lsreader, binout, keyword_deck, model) target similar inventory goals. Descriptions do differentiate by backend (LASSO/SCL/LS-Reader/PyDYNA), but the distinctions are subtle and easy to misselect on.
Names follow a clear verb_noun convention (list_parts, inspect_model, create_shell_plate, export_keyword, read_job) consistently in snake_case. Minor deviations like run_on_version and the backend-suffixed inspect_d3plot_scl/extract_lsreader_nodal are still readable and predictable.
30 tools is on the heavy side for a single pre/post-processor server, especially with the many parallel inspect_* and extract_* variants multiplied across backends. The breadth is partly justified by the domain's multiple file formats and Python ABI variants, but the set feels over-expanded.
Coverage spans inspection, extraction, material/mesh creation, keyword export, job management, rendering, and discovery, which is broad for the domain. Gaps exist (no delete/destructive operations and limited model editing beyond elastic material and a shell plate), but core lifecycle workflows are workable.