Best for
- Seismologists
- Earthquake researchers
- AI assistants needing rapid catalog analysis
C
CLIO Seismic
Community
Earthquake-sequence analysis for saved catalogs
- Category
- Other #131 of 230
- Stars
- ★ 30 Popular
- Transport
- stdio (local process)
- Runtime
- Python 3.10+
- Credentials
- No credential needed
- License
- BSD-3-Clause
- Last commit
- Tools
- 2
52FMRS · D
An MCP server for earthquake-catalog analysis, offering two tools that return statistics and visualizations. It is not for sequence classification or raw waveform processing. Requires catalog files and may depend on plotting libraries.
Strongest · Maintenance 12/20 Weakest · Reliability 8/20
Why each score
- Reliability 8/20
- The manifest declares two tools (analyze_sequence, plot_sequence), one resource, and one prompt with concrete, well-scoped descriptions (explicitly stats-only, no classification). However, no server-specific source, tests, or CI evidence for the seismic server is present, so tool behavior cannot be verified; static calibration caps this below 12 without committed tests. Version inconsistencies (manifest 2.2.3 vs pypi 2.10.6 vs README CLI 2.4.3) and contradictory server counts (22/23/24) further weaken contract trust. Deducted for missing execution/test evidence and version mismatches.
- Security and permissions 12/20
- No red-line issues: no credential handling, no declared network egress, no dangerous defaults; the server appears read-only over saved catalogs writing a local PNG. But input validation (catalog paths), output path boundaries, and dependency scoping for this server are not evidenced; the README's pip-audit claim cannot be verified for seismic coverage. No red line, so not 0-4, but incomplete data-flow and permission disclosure yields 12.
- Maintenance 12/20
- Active project: BSD-3-Clause, NSF-sponsored, CI/codecov badges, Zulip community, 39 open issues, clear institutional ownership (GRC at IIT). However, no release/changelog evidence specific to the seismic server, and the version story is inconsistent across manifest, PyPI identifier, and README (2.2.3 / 2.10.6 / 2.4.3); only 26 stars. Deducted for versioning governance gaps and lack of server-specific maintenance evidence.
- Documentation 9/20
- The README provides install, client configs (Cursor/Claude Code/VS Code/Claude Desktop), troubleshooting, and a server table, but it is shared across 20+ servers; seismic-specific documentation is one line. Tool parameters, the expected 'saved catalog' format, output locations, and limits are undocumented. Internal contradictions (22 vs 23 vs 24 servers; mismatched version numbers) also reduce trust. Deducted for missing per-server parameter/limit docs.
- Setup experience 11/20
- Setup is low-friction and consistent: uv tool install clio-kit, then clio-kit mcp-server seismic, matching the manifest's packageArguments (mcp-server seismic), with JSON client config examples provided. Deducted because examples are not seismic-specific (hdf5/pandas/slurm only), the README's pinned version (2.4.3) conflicts with the manifest's pypi 2.10.6, and there is no verifiable execution evidence, so calibration caps setup below 15.
Static review · not runListed 2026-09-08
Read the FMRS scoring method →Fit and risk
What it can accessReads local filesWrites / deletes local files
Not for
- Analyzing raw waveform data (use the SAC MCP instead) or single-event analysis
- Real-time data streaming
- Automated sequence classification (the tool is descriptive only)
Required permissions
- Local file system access to read catalog files and write PNG outputs
Risks and side effects
- Input catalog format must match expected; errors may occur otherwise
- b-value fitting quality depends on catalog completeness and parameter choices
- Plotting may require disk space and dependencies
Setup
Before you start
Runtime：Python 3.10+
- Install clio-kit via
uv tool install 'clio-kit==2.4.3'(or the latest version).\n2. Add the server to your MCP client configuration with commandclio-kitand args["mcp-server", "seismic"](e.g., in claude_desktop_config.json).
Check that it works
After installing, confirm that analyze_sequence and plot_sequence appear in the client's tool list, or read the seismic://capabilities resource to confirm the server is running.
Troubleshooting
- If the server is not found, ensure you run `clio-kit mcp-server seismic` and that clio-kit is installed.
- Check that the catalog file path is correct and the format is supported.
- If plot generation fails, verify matplotlib and related dependencies are installed.
Things to try
Once connected, you can ask your AI assistant things like:
- Analyze my saved earthquake catalog and compute the completeness magnitude Mc and the Gutenberg-Richter b-value with uncertainty
- Compute descriptive statistics for this earthquake sequence, including the largest event, the Bath-law magnitude gap, and the Omori post-event rate decay
- Render the three-panel earthquake-sequence figure for this saved catalog: epicenter map, magnitude-frequency distribution, and cumulative count
- Plot the sequence and pass mc and b_value so the G-R fit line is drawn on the magnitude-frequency panel
Tools 2
analyze_sequence read-only
Compute descriptive statistics for a saved earthquake catalog (e.g., Mc, b-value), without classifying the sequence.
plot_sequence writes
Render a three-panel figure from a saved earthquake catalog and return the PNG file path.
No matching tools
Use cases
Analyze a catalog to determine completeness magnitude and b-value
Visualize the epicenter distribution, magnitude-frequency, and cumulative events
Provide statistical descriptions for further sequence classification
Supported clients
Claude Desktop
Cursor
Claude Code
VS Code
Listed from the project's documentation, not tested by this site.
Overview
This MCP server analyzes saved earthquake catalogs. It provides two tools: analyze_sequence, which computes descriptive statistics such as completeness magnitude, Gutenberg-Richter b-value with uncertainty, largest event, Bath-law magnitude gap, spatial extent, and Omori decay; and plot_sequence, which generates a three-panel figure with an epicenter map, a magnitude-frequency distribution, and a cumulative event count over time. Designed for seismological research, the server works with saved catalogs only and returns statistics or plot paths.
Similar servers
Hevy MCP
77 · B
Manage your Hevy workout data from AI assistants via MCP.
Firecrawl MCP Server
75 · B
Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents
BioMCP
75 · B
One binary. One grammar. Evidence from the biomedical sources you already trust.
Compartment
75 · B
Encrypted, fully offline long-term memory for AI agents
More servers from this repository
Source revision 93e41d70d6c2 Data synced 2026-10-19 Read the FMRS scoring method