// SCAN REPORT

CLIO Adios

204 tools. 80 can modify or destroy data without limits.

6 destructive tools with no built-in limits. Policy required.

Last updated: 22 Jul 2026

80 can modify or destroy data

124 read-only

204 tools total

Community server · catalogue entry checked 22/07/2026

How to control CLIO Adios ↓

TOOL MAP

What CLIO Adios exposes to your agents

Read (124) Write / Execute (74) Destructive / Financial (6)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous CLIO Adios tools

Destructive · High cancel_slurm_job Cancelling a Slurm job is an irreversible action — a terminated job loses its execution state, queued work, and any in-progress computation cannot be resumed from where it was stopped. Destructive · High destroy_pipeline The verb 'destroy' combined with 'clean up files' clearly indicates irreversible removal of data and computational environment state. Destructive · High jm_remove_repo This tool deletes repository data from JarvisManager. Destructive · Critical jm_reset The tool performs a destructive operation that cannot be undone.

80 of CLIO Adios's 204 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control CLIO Adios

PolicyLayer is an MCP gateway — it sits between your AI agents and CLIO Adios, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "cancel_slurm_job": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "append_pkg": {
    "limits": [
      {
        "counter": "append_pkg_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "aggregate_column_tool": {
    "limits": [
      {
        "counter": "aggregate_column_tool_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register CLIO Adios — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON CLIO ADIOS →

Instant setup, no code required.

FULL CATALOGUE

All 204 CLIO Adios tools

DESTRUCTIVE 6 tools

Destructive cancel_slurm_job Cancel a running or pending Slurm job. Destructive destroy_pipeline Destroy a pipeline environment and clean up files. Destructive jm_remove_repo Remove a repository from JarvisManager. Destructive jm_reset Reset JarvisManager (destroy all pipelines and data). Destructive remove_pkg Delete a package only when JARVIS-CD provides destructive removal semantics. Destructive slurm_cancel Request cancellation after exact scheduler-native ID confirmation.

EXECUTE 20 tools

Execute allocate_slurm_nodes Allocate Slurm nodes for an interactive session using salloc. Execute build_pipeline_env Rebuild a pipeline Execute generate_isosurface Create an isosurface visualization of the active source at the given isovalue. Execute heatmap_plot Create a correlation heatmap from numeric columns in CSV or Excel data. Execute hypothesis_testing Run statistical hypothesis tests (t-test, chi-square, ANOVA, normality, Mann-Whitney) with p-values and effect Execute jarvis_run jarvis_run Execute jm_cd Change current Jarvis pipeline context. Execute jm_graph_build Build or rebuild the resource graph with a net sleep interval. Execute module_load Load one or more environment modules into the current session. Execute module_swap Swap one module for another atomically. Execute module_unload Unload one or more currently loaded modules from the environment. Execute parallel_sort_large_file Sort large log files using parallel processing with chunked approach. Execute reset_camera Reset the camera to show all data in the viewport. Execute rotate_camera Rotate the camera by azimuth and elevation angles in degrees. Execute run_pipeline Execute a Jarvis-CD pipeline end-to-end. Execute show_screenshot_preview Capture a screenshot with inline preview using temporary files. Execute stop_chronolog Release the story handle and disconnect from ChronoLog. Execute submit_array_job Submit a Slurm array job for parallel task execution. Execute submit_slurm_job Submit a job script to the Slurm scheduler with resource requirements. Execute warp_by_vector Apply a 'Warp By Vector' filter to the active source.

WRITE 54 tools

Write append_pkg Append a package to a Jarvis-CD pipeline. Write apply_field_coloring Color the active visualization by a specific data field. Write apply_filter_preset Apply predefined filter presets like Write bar_plot Create a bar chart from CSV or Excel data with categorical grouping. Write compress_file_tool Compress a file using gzip. Returns original/compressed sizes and compression ratio. Write configure_pkg Configure a package in a Jarvis-CD pipeline. Write configure_volume_display Toggle volume rendering visibility for the active source. Write create_data_slice create_data_slice Write create_geometric_shape Create a geometric source (Sphere, Cone, Cylinder, Plane, or Box). Write create_pipeline Create a new Jarvis-CD pipeline environment. Write decompress_file_tool Decompress a gzip-compressed (.gz) file back to its original form. Write edit_volume_opacity Edit the opacity transfer function for a scalar field. Write export_to_bibtex Export search results to BibTeX format for citation management. Write export_to_csv Export log entries to CSV format with structured columns. Write export_to_json Export log processing results to JSON format. Write export_to_text Export log entries to plain text format. Write generate_flow_streamlines generate_flow_streamlines Write generate_io_summary_report Generate a comprehensive I/O summary report with findings and recommendations. Write generate_summary_report Generate a summary report of log processing results with statistics. Write handle_missing_data Detect, impute, or remove missing values using strategies like mean/median/mode fill, forward/backward fill, o Write histogram_plot Create a histogram from CSV or Excel data showing value distribution. Write jarvis_add_step jarvis_add_step Write jarvis_create_pipeline Create a new JARVIS pipeline, optionally seeding execution intent. Write jarvis_edit_step Edit or remove one pipeline step with explicit conditional arguments. Write jm_add_repo Add a repository to JarvisManager. Write jm_bootstrap_from Bootstrap Jarvis config from a machine template. Write jm_construct_pkg Construct a package skeleton in JarvisManager. Write jm_create_config Initialize JarvisManager config directories. Write jm_graph_modify Modify the resource graph using a net sleep interval. Write jm_promote_repo Promote a repository in JarvisManager. Write jm_save_config Save current JarvisManager configuration. Write jm_set_hostfile Set hostfile path for JarvisManager. Write line_plot Create a line plot from CSV or Excel data with customizable styling. Write merge_datasets Join two datasets using inner, outer, left, or right joins on specified key columns. Write module_restore Restore a previously saved module collection. Write module_save Save currently loaded modules as a named collection. Write pivot_table Create pivot tables with configurable row index, column headers, value columns, and aggregation function. Write plot_timeseries Create a multi-series line chart PNG from one or more y columns of a CSV or Excel file, auto-detecting a time, Write record_interaction Log a user message and LLM response to the active ChronoLog story. Write refresh_hdf5_resources Re-scan client roots and update available HDF5 resources. Write save_contour_as_stl Save the active contour or surface as an STL file in the data directory. Write save_data Save data to CSV, Excel, JSON, Parquet, or HDF5 with auto-detected format and optional index inclusion. Write scatter_plot Create a scatter plot from CSV or Excel data for correlation analysis. Write set_active_source Set the active pipeline object by its registered name. Write set_color_map Set a custom color transfer function for volume rendering. Write set_color_map_preset Apply a predefined color map preset (e.g., Viridis, Plasma, Cool to Warm). Write set_representation_type Set the representation type for the active source (Surface, Wireframe, Points, etc.). Write slurm_submit Submit a job or array through the compact Slurm user contract. Write spack_install spack_install Write start_chronolog Connect to ChronoLog, create a chronicle, and acquire a story handle. Write time_series_operations Resample, compute rolling statistics, create lag features, or difference a time series. Write toggle_visibility Toggle visibility for the active source. Write unlink_pkg Unlink a package from a pipeline (preserve files). Write update_pipeline Re-apply environment and configuration to every package in a pipeline.

READ 124 tools

Read aggregate_column_tool Compute aggregate statistics (min, max, mean, etc.) on a Parquet column. Read analyze_file_access_patterns Analyze file access patterns including read/write types and sequential vs random access. Read analyze_log_statistics Generate statistics for log files including temporal patterns and log levels. Read analyze_mpiio_operations Analyze MPI-IO operations including collective vs independent operations. Read analyze_posix_operations Analyze POSIX I/O operations including read/write system calls and their frequency. Read analyze_sequence analyze_sequence Read bounding_box bounding_box Read check_job_status Check the status of a Slurm job by its ID. Read clean_data Remove duplicates, detect outliers via IQR/Z-score, and optimize data types in a single pass. Read compare_darshan_logs Compare two Darshan log files to identify performance differences between runs. Read compute_surface_area Compute the surface area of the active dataset (must be a surface mesh). Read compute_trace_statistics compute_trace_statistics Read correlation_analysis Compute correlation matrices (Pearson, Spearman, or Kendall) with significance testing and strong-correlation Read data_info Get schema, column types, and summary statistics for a CSV or Excel file. Read deallocate_slurm_nodes Release a Slurm node allocation by canceling it. Read dem_terrain dem_terrain Read detect_log_patterns Detect patterns in log files including anomalies and error clusters. Read download_multiple_pdfs Download multiple PDFs concurrently with rate limiting. Read download_paper_pdf Download the PDF of a paper from ArXiv. Read export_pipeline Export a structured snapshot of a Jarvis-CD pipeline. Read feature_bbox feature_bbox Read filter_by_keyword Filter log entries by keywords with support for multiple keywords and logical operations. Read filter_by_log_level Filter log entries by log level (ERROR, WARN, INFO, DEBUG, etc.). Read filter_by_time_range Filter log entries by time range using start and end timestamps. Read filter_data Filter rows using comparison, membership, pattern-matching, and null-check operators across multiple columns. Read filter_logs Filter log entries based on multiple conditions with logical operations. Read filter_points_by_radius filter_points_by_radius Read find_similar_papers Find papers similar to a reference paper based on categories and keywords. Read geocode geocode Read get_active_source_names_by_type List pipeline source names, optionally filtered by type. Read get_allocation_status Check the status of a Slurm node allocation. Read get_available_arrays List available data arrays in the active source. Read get_column_preview_tool Preview values from a specific column with pagination. Read get_cpu_info Get CPU specifications, core counts, frequencies, and per-core usage. Read get_dataset_details Retrieve detailed metadata for a specific dataset by ID or name. Read get_disk_info Get disk partitions, usage statistics, and I/O counters. Read get_gpu_info Get GPU model, memory, temperature, and utilization via nvidia-smi/rocm-smi. Read get_histogram Compute histogram data for a field in the active source. Read get_io_performance_metrics Extract I/O performance metrics including bandwidth, IOPS, and request sizes. Read get_job_details Get detailed information about a specific Slurm job. Read get_job_output Retrieve stdout or stderr output from a Slurm job. Read get_job_summary Get job-level summary from a Darshan log including runtime, process count, and I/O volume. Read get_memory_info Get RAM and swap capacity, usage percentages, and availability. Read get_network_info Get network interfaces, IP addresses, and I/O statistics. Read get_node_info Get information about Slurm cluster nodes and their resources. Read get_paper_details Get detailed information about a specific ArXiv paper by ID. Read get_pdf_url Get the direct PDF URL for a paper without downloading. Read get_performance_info Get real-time CPU, memory, disk, and network performance metrics. Read get_pipeline Get the current visualization pipeline structure. Read get_pkg_config Retrieve the configuration of a specific package in a pipeline. Read get_process_info Get running processes with CPU, memory, and status details. Read get_queue_info Get Slurm queue status and partition information. Read get_recent_papers Get recent papers from a specific ArXiv category. Read get_remote_node_info Collect hardware info from a remote node via SSH. Supports component filtering. Read get_sensor_info Get temperature, fan speed, and battery sensor readings. Read get_slurm_info Get Slurm cluster configuration, partitions, and resource availability. Read get_system_info Get OS details, hostname, uptime, and active users. Read get_timeline_analysis Generate timeline analysis showing I/O activity over time and temporal patterns. Read groupby_operations Group data by columns and apply aggregations (sum, mean, count, min, max, std, median) with optional pre-filte Read health_check Verify server health and hardware monitoring capability status. Read identify_io_bottlenecks Identify I/O performance bottlenecks by analyzing access patterns and operations. Read inspect_archive inspect_archive Read inspect_attributes Reads global or variable-specific attributes from a BP5 file. The Read inspect_geojson inspect_geojson Read inspect_variables Inspects variables in a BP5 file, returning type, shape, and steps. Optionally filters by variable name. Read inspect_variables_at_step Inspects a specific variable at a given step in a BP5 file. All parameters are required. Read jarvis_describe jarvis_describe Read jarvis_get_execution Query a selectable JARVIS-owned execution view in one locked load. Read jm_bootstrap_list List available bootstrap machine templates. Read jm_get_repo Get repository info from JarvisManager. Read jm_graph_show Print the current resource graph frames. Read jm_list_pipelines List all existing Jarvis pipelines. Read jm_list_repos List all Jarvis repositories. Read jm_load_config Load existing JarvisManager configuration. Read list_available_hdf5_files List all registered HDF5 files with resource URIs for Claude Code @ mentions. Read list_bp5 Lists all BP5 files in a given directory. The Read list_commands List all available commands in this ParaView MCP server. Read list_organizations List organizations available in the National Data Platform. Read list_slurm_jobs List Slurm jobs with optional filtering by user and state. Read load_darshan_log Load and parse a Darshan log file to extract I/O performance metrics and metadata. Read load_data Load and parse data from CSV, Excel, JSON, Parquet, or HDF5 files with optional column selection and row limit Read load_pipeline Load an existing Jarvis-CD pipeline environment. Read load_scientific_data Load scientific datasets (VTK, EXODUS, CSV, RAW, BP5) into ParaView with automatic format detection. Read module_avail Search for available modules, optionally filtered by name pattern. Read module_list List all currently loaded environment modules. Read module_savelist List all saved module collections. Read module_show Display detailed information about a specific module. Read module_spider Search the entire module tree comprehensively for matching modules. Read optimize_memory Analyze and reduce DataFrame memory usage through automatic dtype optimization and chunked-processing recommen Read plot_over_line plot_over_line Read plot_sequence plot_sequence Read plot_traces plot_traces Read pointcloud_read pointcloud_read Read points_in_polygons points_in_polygons Read profile_csv Quickly profile a CSV file: row/column counts, per-column dtype, null counts, and min/max/mean for numeric col Read profile_data Generate a full dataset profile: shape, types, missing values, distributions, quality checks, and optional cor Read query_arcgis_features query_arcgis_features Read read_slice_tool Read a row slice from a Parquet file with optional column projection and filtering. Read read_variable_at_step Reads a named variable at a specific step from a BP5 file. All parameters are required. Read render_feature_map render_feature_map Read retrieve_interaction Retrieve logged records from a chronicle and story, with optional time filtering. Read scientific_dataset_describe Resolve a stable dataset id and an explicit JARVIS-ready descriptor handoff. Read scientific_dataset_search Search titles, summaries, tags, and exact intrinsic format metadata. Read search_arxiv Search ArXiv for papers by category or topic. Read search_by_abstract Search ArXiv papers by abstract keywords. Read search_by_subject Search ArXiv papers by subject classification. Read search_by_title Search ArXiv papers by title keywords. Read search_datasets Search for datasets in the NDP using term-based or field-specific criteria. Read search_date_range Search ArXiv papers within a specific date range. Read search_papers_by_author Search ArXiv papers by author name. Read slurm_cluster Return a coherent Slurm partition, queue, and optional node snapshot. Read slurm_describe Return a unified description of one scheduler-native Slurm job. Read slurm_list List Slurm jobs through a stable, normalized result schema. Read sort_log_by_timestamp Sort log file lines by timestamps in YYYY-MM-DD HH:MM:SS format. Read spack_environment Return a filtered environment delta without exposing a fake load operation. Read spack_find Return structured installed-package records. Read spack_locate Return one exact package identity and prefix or a protocol error. Read stage_resource stage_resource Read statistical_summary Compute descriptive statistics, distribution analysis, and outlier detection for numerical and categorical col Read summarize_geojson Return {summary, feature_count, geometry_types, bbox, property_keys, sample_features}. Read summarize_tool Return Parquet schema, row count, and file size. Read take_viewport_screenshot Capture a screenshot of the current ParaView viewport and save it as a timestamped PNG. Read validate_data Validate columns against rules for min/max range, data type, nullability, uniqueness, and regex patterns. Read validate_geojson validate_geojson

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about CLIO Adios

Can an AI agent delete data through the CLIO Adios MCP server? +

Yes. The CLIO Adios server exposes 6 destructive tools including cancel_slurm_job, destroy_pipeline, jm_remove_repo. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through CLIO Adios? +

The CLIO Adios server has 54 write tools including append_pkg, apply_field_coloring, apply_filter_preset. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach CLIO Adios.

How many tools does the CLIO Adios MCP server expose? +

204 tools across 4 categories: Destructive, Execute, Read, Write. 124 are read-only. 80 can modify, create, or delete data.

How do I enforce a policy on CLIO Adios? +

Register the CLIO Adios MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every CLIO Adios tool call.

Deterministic rules across all 204 CLIO Adios tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CLIO ADIOS →

Instant setup, no code required.

204 CLIO Adios tools catalogued and risk-classified — across an index of 46,500+ MCP servers.

// WHERE THIS COMES FROM

These policies come from CLIO Adios's registry record.

The record behind this page: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.

Teams ship this data inside their own products. See what a licence covers →