PFCSAFE
MCP server connecting AI agents to ITASCA engines (PFC, FLAC, 3DEC, MPoint, MassFlow) — run geotechnical & geomechanics simulations through natural conversation
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/yusong652/itasca-mcp/actions/workflows/test.yml) [](https://pypi.org/project/itasca-mcp/) [](https://pepy.tech/project/itasca-mcp) [](https://github.com/yusong652/itasca-mcp/stargazers) [](LICENSE) [](https://www.python.org/)
itasca>model new ;now, with LLM.
itasca-mcp connects AI agents to ITASCA's geomechanics simulation software — PFC, FLAC, 3DEC, MPoint, and MassFlow — through the Model Context Protocol. Browse documentation, run simulations, and execute code, all through natural conversation.
itasca>model solve ;LLM solves.
Tools (10)
5 documentation tools — browse and search the selected engine's commands, Python API, and reference docs. No bridge required.
5 execution tools — interactive REPL, task submission, progress monitoring, interruption, and history. Requires bridge.
Example Prompts
- "Run a biaxial compression test on a dense specimen and plot the stress–strain curve"
- "Build a slope model in FLAC3D and find the factor of safety"
- "Model a tunnel excavation in jointed rock with 3DEC and check block displacements around the opening"
- *"Simulate a land
c0b116b7690eOBSERVED · 2026-10-07Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add itasca-mcp -- None itasca-mcp==0.10.2
Exposed tools (2)
2 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
itasca_query_command | read | Search Itasca command documentation by keywords (like grep). |
itasca_query_python_api | read | Search Itasca Python SDK documentation by keywords (like grep). |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (4 observation(s))
- Network
- declared (9 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (2)
.gitmodules
os.environ["ITASCA_MCP_BRIDGE_URL"] = f"http://127.0.0.1:{port}"Gates applied: no_behavioural_pass.
c0b116b7690efull audit observations/trust-audit/mcp-server/yusong652__pfc.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-07 | c0b116b7690e | SAFE | B | 89 | first audit |
Questions
What is the PFC MCP server?
MCP server connecting AI agents to ITASCA engines (PFC, FLAC, 3DEC, MPoint, MassFlow) — run geotechnical & geomechanics simulations through natural conversation
What tools does PFC expose?
2 in total: 2 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is PFC safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does PFC need?
No credential environment variables were found in its source, so it appears to need none.
How does PFC run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as itasca-mcp.
How current is this page?
The grade is for one exact copy of the source (c0b116b7690e), read on 2026-10-07. The repository is watched and re-audited when it changes.