I have (with lots of Satish’s and Hong’s help) stood up three PETSc related MCP servers, see https://urldefense.us/v3/__https://gitlab.com/petsc/petsc_mcp_servers/-/blob/main/README.md?ref_type=heads__;!!G_uCfscf7eWS!dbIU4Ye_9lCgMD3NAMbHwugpM6D0W21eir8f1I2_rmT2TlzU_nfglEf9uOzBAnzEdu5RHDHC280RJrcKti6cIg$ for details on their usage. I hope anyone using AI/LLM tools in their use of PETSc can try out these servers and see if they help (or hinder) the use of AI development systems.
If you know of any available MCP servers that might help with PETSc please let us know. Any problems using these or suggestions on making them better let us know. Barry Note that MCP servers/agents serve multiple purposes - are used directly by developer systems like gemini-cli - can be used directly by other agents we wrote - can be used by modern RESTful interfaces for LLM based on the OpenAI response model MCP servers can be used in multiple ways - “directly” by an LLM, that is a LLM is given some text and a list of MCP tools and it decides exactly what tool to call with what arguments and - via the MCP Python API; in this case it is just like programming Python and calling functions (that are transparently) actually implemented somewhere else.
