Dfxm Geo Mcp
io.github.borgi-sPublished by GitHub account borgi-sv0.1.0Updated Oct 24, 2026
MCP server for the dfxm-geo dark-field X-ray microscopy forward model
Overview
Local MCP server that lets an assistant drive the dfxm-geo dark-field X-ray microscopy forward model: validate configs, find reflections, and run preview-scale,
- What you can do
- Validate and scaffold dfxm-geo simulation configuration files, and enumerate reachable reflections with a g·b visibility ranking that returns structured scores plus a self-contained HTML report. Run analytic forward simulations that save a PNG and a self-contained HTML page, and open an interactive φ-rocking-curve viewer with a frame scrubber and live plot. Start Monte Carlo fidelity jobs and poll their status and results through separate job tools.
- When to use it
- Useful when working with dark-field X-ray microscopy simulations and you want an assistant to check or generate configs, pick reflections, and produce quick preview-scale forward or rocking-curve results without leaving the chat.
- Requirements
- Runs locally over stdio as a PyPI package, launched with uvx or after pip install; needs Python and network access on first run, which pulls a heavy scientific stack (numba/scipy) and warms a JIT cache for about 10 seconds. Desktop client only; no authentication or environment variables declared.
Installation
In SourceWeft
- Open Dfxm Geo Mcp in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
dfxm-geo-mcp
An MCP server that lets an AI client drive the dfxm-geo dark-field X-ray microscopy forward model: validate and scaffold configs, enumerate reachable reflections, and render preview-scale simulations.
[Claude Desktop rendering a DFXM image from a plain-English request]
Run
Claude Desktop (claude_desktop_config.json):
Or: pip install dfxm-geo-mcp then dfxm-geo-mcp.
First run pulls a heavy scientific stack (numba/scipy) and warms a JIT cache (~10 s once). No fake demo mode — the sims are real.
Tools
validate_config · find_reflections · predict_visibility (g·b reflection-visibility ranking; structured scores plus a self-contained .html) · scaffold_config · run_forward (analytic preview; saves a PNG and a self-contained .html) · run_rocking (interactive φ-rocking-curve viewer: a single self-contained .html with a frame scrubber + live rocking-curve plot) · start_bootstrap / get_job_status / get_job_result (MC fidelity).
Both run_forward and run_rocking write self-contained HTML (image(s) embedded, all CSS/JS inline, no external origins) that opens full-size in any browser and is surfaced by file-showing clients.
Architecture
A protocol-agnostic ops layer wrapping dfxm-geo, under a thin FastMCP adapter. See docs/superpowers/specs/.
Roadmap (v2)
run_identify · remote HTTP transport · .mcpb bundle.
Source: README.md at commit d5d473f
Tools
0Version history
1- v0.1.0LatestSep 16, 2026
Score
40% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Declare a license in the repository or the registry entry.