CLIO Seismic MCP server

Read from the package source without running it. The installed server may list more.

• analyze_dataset_structure

  Analyze and understand file organization and data patterns with AI insights.

• analyze_file_access_patterns

  Analyze file access patterns including read/write types and sequential vs random access.

• analyze_mpiio_operations

  Analyze MPI-IO operations including collective vs independent operations.

• analyze_posix_operations

  Analyze POSIX I/O operations including read/write system calls and their frequency.

• append_pkg

  Append a package to a Jarvis-CD pipeline.

• bounding_box

  Return the (optionally padded) bounding box of GeoJSON features.

• build_pipeline_env

  Rebuild a pipeline's env.yaml, capturing CMAKE_PREFIX_PATH and PATH.

• close_file

  Close the current HDF5 file.

• compare_darshan_logs

  Compare two Darshan log files to identify performance differences between runs.

• compress_file_tool

  Compress a file using gzip. Returns original/compressed sizes and compression ratio.

• configure_pkg

  Configure a package in a Jarvis-CD pipeline.

• create_pipelinewrite action

  Create a new Jarvis-CD pipeline environment.

• decompress_file_tool

  Decompress a gzip-compressed (.gz) file back to its original form.

• destroy_pipelinewrite action

  Destroy a pipeline environment and clean up files.

• download_multiple_pdfs

  Download multiple PDFs concurrently with rate limiting.

• download_paper_pdf

  Download the PDF of a paper from ArXiv.

• export_dataset

  Export dataset to various formats with user format selection.

• export_to_bibtex

  Export search results to BibTeX format for citation management.

• feature_bbox

  Return ``{"bbox": [min_lon, min_lat, max_lon, max_lat] | None, "feature_count": int}``.

• filter_points_by_radius

  Return the points within radius_km of the center, sorted by distance.

• find_similar_datasets

  Find datasets with similar characteristics to a reference dataset with AI analysis.

• find_similar_papers

  Find papers similar to a reference paper based on categories and keywords.

• generate_io_summary_report

  Generate a comprehensive I/O summary report with findings and recommendations.

• geocode

  Geocode a place name into coordinates via OpenStreetMap Nominatim.

• get_by_path

  Get a dataset or group by path.

• get_chunks

  Get chunk information for a dataset.

• get_dtype

  Get the data type of a dataset.

• get_filename

  Get the current file's path.

• get_io_performance_metrics

  Extract I/O performance metrics including bandwidth, IOPS, and request sizes.

• get_job_summary

  Get job-level summary from a Darshan log including runtime, process count, and I/O volume.

• get_mode

  Get the current file's access mode.

• get_paper_details

  Get detailed information about a specific ArXiv paper by ID.

• get_pdf_url

  Get the direct PDF URL for a paper without downloading.

• get_pkg_config

  Retrieve the configuration of a specific package in a pipeline.

• get_recent_papers

  Get recent papers from a specific ArXiv category.

• get_shape

  Get the shape of a dataset.

• get_size

  Get the size of a dataset.

• get_timeline_analysis

  Generate timeline analysis showing I/O activity over time and temporal patterns.

• hdf5_aggregate_stats

  Parallel statistics computation across multiple datasets.

• hdf5_batch_read

  Read multiple datasets in parallel.

• hdf5_parallel_scan

  Fast multi-file scanning with parallel processing.

• hdf5_stream_data

  Stream large datasets efficiently with memory management.

• identify_io_bottlenecks

  Identify I/O performance bottlenecks by analyzing access patterns and operations.

• inspect_attributes

  Reads global or variable-specific attributes from a BP5 file. The 'variable_name' is optional.

• inspect_geojson

  Return a structural report for a GeoJSON document.

• inspect_variables

  Inspects variables in a BP5 file, returning type, shape, and steps. Optionally filters by variable name.

• inspect_variables_at_step

  Inspects a specific variable at a given step in a BP5 file. All parameters are required.

• jm_add_repo

  Add a repository to JarvisManager.

• jm_bootstrap_from

  Bootstrap Jarvis config from a machine template.

• jm_bootstrap_list

  List available bootstrap machine templates.

• jm_cd

  Change current Jarvis pipeline context.

• jm_construct_pkg

  Construct a package skeleton in JarvisManager.

• jm_create_configwrite action

  Initialize JarvisManager config directories.

• jm_get_repo

  Get repository info from JarvisManager.

• jm_graph_build

  Build or rebuild the resource graph with a net sleep interval.

• jm_graph_modify

  Modify the resource graph using a net sleep interval.

• jm_graph_show

  Print the current resource graph frames.

• jm_list_pipelines

  List all existing Jarvis pipelines.

• jm_list_repos

  List all Jarvis repositories.

• jm_load_config

  Load existing JarvisManager configuration.

• jm_promote_repo

  Promote a repository in JarvisManager.

• jm_remove_repowrite action

  Remove a repository from JarvisManager.

• jm_reset

  Reset JarvisManager (destroy all pipelines and data).

• jm_save_config

  Save current JarvisManager configuration.

• jm_set_hostfile

  Set hostfile path for JarvisManager.

• list_attributes

  List all attributes of an object.

• list_available_hdf5_files

  List all registered HDF5 files with resource URIs for Claude Code @ mentions.

• list_bp5

  Lists all BP5 files in a given directory. The 'directory' parameter must be an absolute path.

• list_keys

  List keys in a group.

• load_darshan_log

  Load and parse a Darshan log file to extract I/O performance metrics and metadata.

• load_pipeline

  Load an existing Jarvis-CD pipeline environment.

• module_list

  List all currently loaded environment modules.

• open_file

  Open an HDF5 file for operations.

• optimize_access_pattern

  Suggest better approaches for data access based on usage patterns.

• points_in_polygons

  Return the points that fall within (optionally buffered) polygons.

• query_arcgis_features

  Query an ArcGIS FeatureServer layer and persist features as GeoJSON.

• read_attribute

  Read an attribute from an object.

• read_full_dataset

  Read an entire dataset with efficient chunked reading for large datasets.

• read_partial_dataset

  Read a portion of a dataset with slicing.

• read_variable_at_step

  Reads a named variable at a specific step from a BP5 file. All parameters are required.

• record_interaction

  Log a user message and LLM response to the active ChronoLog story.

• refresh_hdf5_resources

  Re-scan client roots and update available HDF5 resources.

• remove_pkgwrite action

  Remove a package entirely from a pipeline.

• render_feature_map

  Render GeoJSON layers to a map PNG. See tool description for the layer schema.

• retrieve_interaction

  Retrieve logged records from a chronicle and story, with optional time filtering.

• run_pipelinewrite action

  Execute a Jarvis-CD pipeline end-to-end.

• search_arxiv

  Search ArXiv for papers by category or topic.

• search_by_abstract

  Search ArXiv papers by abstract keywords.

• search_by_subject

  Search ArXiv papers by subject classification.

• search_by_title

  Search ArXiv papers by title keywords.

• search_date_range

  Search ArXiv papers within a specific date range.

• search_papers_by_author

  Search ArXiv papers by author name.

• start_chronolog

  Connect to ChronoLog, create a chronicle, and acquire a story handle.

• stop_chronolog

  Release the story handle and disconnect from ChronoLog.

• suggest_next_exploration

  Suggest interesting data to explore next based on current location with AI recommendations.

• summarize_geojson

  Return ``{summary, feature_count, geometry_types, bbox, property_keys, sample_features}``.

• unlink_pkg

  Unlink a package from a pipeline (preserve files).

• update_pipelinewrite action

  Re-apply environment and configuration to every package in a pipeline.

• validate_geojson

  Return ``{"valid": bool, "errors": list[str]}`` for a GeoJSON document.

• visit

  Visit all nodes recursively.

• Code scan299 source files scanned15/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 11 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10

CLIO Seismic: common questions

Is CLIO Seismic MCP server safe?

Mostly: it is graded B (78/100). Read the CLIO Seismic safety report

How do I install CLIO Seismic?

It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.

Does CLIO Seismic need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is CLIO Seismic maintained?

The last commit was 27 days ago (2026-09-16). The latest release is v2.2.3.