CLIO Geojson

io.github.iowarpPublished by GitHub account iowarpv2.2.3Updated Nov 10, 2026

MCP server for inspecting, validating, and summarizing GeoJSON documents (stdlib only)

VerifiedSTDIODesktop onlyLocation & LifestyleData & Analytics

Overview

AI-generated overview

A local MCP server for inspecting, validating and summarizing GeoJSON documents, built on the Python standard library.

What you can do
  • Inspect GeoJSON documents and report their structure.
  • Validate GeoJSON content and flag problems.
  • Summarize the contents of a GeoJSON file.
  • The manifest lists no individual tools, so exact operations come from the server itself once connected.
When to use it
Useful when an assistant needs to check or describe GeoJSON files, for example before mapping or analysis, without writing custom parsing scripts.
Requirements
Runs as a local process over stdio, installed from the PyPI package clio-kit; no authentication, environment variables or headers are declared. The README's installer routes use uv or Node.js 22.20.0+ for the skills CLI.
Before you install
The README describes a broader scientific-computing toolkit whose other servers submit cluster jobs, install packages and fetch web content; only enable the components you need. No credentials or write actions are declared for this server.

Installation

In SourceWeft

  1. Open CLIO Geojson in the dashboard and add it to a workspace.
  2. 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

CLIO Kit

[License: BSD-3-Clause] [PyPI version] [Python] [FastMCP] [CI] [Coverage]

[MCP Servers] [Ruff] [Type Checked] [Package Manager] [Security Audit]

CLIO Kit is the IoWarp meta-marketplace for scientific computing. It brings together MCP servers, workflow skills, plugins, agent definitions, and community contributions—including plugins from external marketplaces—and enables AI agents to interact with HPC resources, scientific data formats, and research datasets.

Choose individual MCPs, skills, agents and hooks—or a plugin that bundles what your workflow needs. A plugin can include any of these components; it does not need all four.

Website | IOWarp

Documentation · For agents: read here.

Chat with us on Zulip or join us

Developed by [GRC Logo] Gnosis Research Center


❌ Without CLIO Kit

Working with scientific data and HPC resources requires manual scripting and tool-specific knowledge:

  • ❌ Write custom scripts for every HDF5/Parquet file exploration
  • ❌ Manually craft Slurm job submission scripts
  • ❌ Switch between multiple tools for data analysis
  • ❌ No AI assistance for scientific workflows
  • ❌ Repetitive coding for common research tasks

✅ With CLIO Kit

Install workflow bundles, use skills to guide your agent, and discover community tools:

  • ✅ "Analyze the temperature dataset in this HDF5 file" - HDF5 MCP does it
  • ✅ "Submit this simulation to Slurm with 32 cores" - Slurm MCP handles it
  • ✅ "Find papers on neural networks from ArXiv" - ArXiv MCP searches
  • ✅ "Plot the results from this CSV file" - Plot MCP visualizes
  • ✅ "Optimize memory usage for this pandas DataFrame" - Pandas MCP optimizes
  • ✅ Workflow guidance - Skills explain tool sequences; optional agents help plan and review results
  • ✅ Community contributions - Discover external plugins and marketplace collections

MCP servers · Skills · Plugins · Agents · Hooks · Community marketplaces

CLIO Kit is part of the IoWarp platform's tooling ecosystem for AI agents. Its meta-marketplace brings tools and reusable workflows together for scientific computing—from exploring HDF5 datasets and managing Slurm jobs to analyzing results and finding research papers. Built by researchers, for researchers, at Illinois Institute of Technology with NSF support.

Part of IoWarp Platform: CLIO Kit is the platform's meta-marketplace and tooling layer, bringing together MCP servers, skills, workflow plugins, agent definitions, and community marketplace collections.

One launcher for MCP servers. Individual components or workflow bundles. BSD-3-Clause licensed, with automated checks and real installation, MCP, and HPC workflow tests. See the validation guide for tested coverage and environment requirements.

🚀 Quick Installation

bash
git clone https://github.com/iowarp/clio-kit.gitcd clio-kit

Recommended: Ask your agent:

text
Read setup.md and set up CLIO Kit for me.

Manual setup: Install this checkout's launcher, then choose an option below. For the no-clone release route (2.11.0 or newer), see selective installation.

bash
uv tool install --force --reinstall --editable ".[verification]"

Claude Code

Install a workflow plugin (bundle) with its MCP servers and skills:

bash
claude plugin marketplace add "$PWD"claude plugin install clio-hpc@clio-kitclaude mcp list

Restart Claude Code after installation and confirm the servers connect. First launches download dependencies; see startup recovery if a server exceeds the client's connection timeout.

Or install an individual MCP or a skill collection:

bash
claude plugin install clio-hdf5@clio-kit                  # HDF5 serverclaude plugin install clio-scientific-io-skills@clio-kit  # Scientific I/O skills

Claude Code uses plugin install for component packages too. CLIO Kit lists those separately from workflow plugins; see components and plugins.

Codex and Other Agents

Install a workflow's skills and MCP configuration together:

bash
clio-kit plugin install clio-scientific-io --client codex --project /path/to/project

Also supports opencode, cursor, antigravity, vscode and claude-code. This sets up project components; native agents and hooks need client-specific adapters. See client installation and limits.

Install a bundle or one skill into your project:

bash
# Bundleclio-kit skill install --bundle clio-scientific-io --target /path/to/project/.agents/skills# Individual skillclio-kit skill install dataset-explore --target /path/to/project/.agents/skills

Configure the required MCP servers using setup.md. Use your agent’s supported skill directory.

Install Skills with npm

Requires Node.js 22.20.0+. From your working project:

bash
# All skillsnpx [email protected] add /path/to/clio-kit --skill '*' --agent codex --copy# Individual skillnpx [email protected] add /path/to/clio-kit --skill dataset-explore --agent codex --copy

Replace codex with claude-code or antigravity. MCP servers require separate configuration.

Choose either the Python or npm installer for each skill. See the skills CLI guide for selecting skills, updates and removal.

One Command for Any Server

bash
# From the CLIO Kit checkout, install the CLI in a persistent tool environmentuv tool install --force --reinstall --editable .# If uv's executable directory is not on PATH:uv tool update-shell
# List all 28 available MCP serversclio-kit mcp-servers
# Run an individual serverclio-kit mcp-server hdf5clio-kit mcp-server pandasclio-kit mcp-server slurm
# Build a server's environment without starting it (safe to repeat)clio-kit mcp-server --prepare hdf5

Once 2.11.0 is published, install it with uv tool install 'clio-kit>=2.11.0' (2.11.0 or newer; earlier releases lack the skill, plugin and doctor commands). uv tool install creates a persistent, isolated environment; use uvx --from 'clio-kit>=2.11.0' clio-kit ... for a temporary, one-shot invocation.

The release separates the small launcher from component downloads: one MCP fetches only that server, one skill fetches only its files, and a workflow selects its components. Server dependencies stay isolated and locked. See selective installation for release, checkout and native plugin routes. The --branch option is for development, not an immutable release installation.

The wheel also includes machine-readable tool contracts for JARVIS, Slurm, Spack and Scientific Catalog, with SHA-256 digests for downstream verification:

bash
clio-kit mcp-contractsclio-kit mcp-contract clio-kit-jarvis-user-v3.7.2clio-kit mcp-contract clio-kit-slurm-user-v3.1clio-kit mcp-contract clio-kit-spack-user-v2.3clio-kit mcp-contract clio-kit-scientific-catalog-user-v1.1

Workflow Bundles

These are broad workflow plugins. Each combines its MCP servers and skills.

BundlePurposeMCP servers
clio-hpcBuild software and run cluster jobsspack, lmod, jarvis, slurm, node-hardware
clio-performanceDiagnose slow jobs and inspect logsdarshan, chronolog, parallel-sort
clio-scientific-ioExplore scientific data fileshdf5, adios, parquet, compression
clio-analysisAnalyze results, create figures and open live 3D viewspandas, plot, paraview
clio-geoscienceWork with maps, a 3D globe, terrain, waveforms and NASA Earthdatageo, terrain, seismology, earthdata
clio-fabricationSlice a model for a 3D printer and check its layersslicer
clio-electronicsSimulate a circuit and plot its waveformsspice
clio-homeRead your home's sensors, control devices and write automationshome-assistant
clio-researchFind papers, read them, and find datasetsarxiv, ndp, pdf, scientific-catalog, web

Some servers require additional system software. See setup and prerequisites. See plugin composition for primary bundles and task plugins that combine components across them.

For a complete dataset-report workflow—HDF5, Pandas, Plot, a skill, evidence review and a verification hook:

bash
claude plugin install clio-dataset-report@clio-kit

See dataset reports for inputs and verification limits.

Skills and Agents

Skills provide workflow instructions and guidance for interpreting results. Claude Code users can install skills or agent definitions separately:

bash
claude plugin install clio-skills@clio-kitclaude plugin install clio-agents@clio-kit

The shared installer supports Codex, Claude Code, OpenCode, Cursor, Antigravity and VS Code. Codex, Claude Code and OpenCode also have adapters for the scientific agents and Dataset Report hooks. See client support.

Add the optional Clio Coder coding and research skills, including Materio procedures:

bash
clio-kit skill install --bundle clio-coder --target .agents/skills# Or through Claude Code:claude plugin install clio-coder-skills@clio-kit

Individual skills also work: clio-kit skill install clio-kit-scientific-debugging --target .agents/skills. Adapted Clio Coder skills use the clio-kit- prefix to distinguish them from upstream originals. See Clio Coder integration for upstream packages and native plugin support.

Agentic Search

clio-agentic-search is a standalone hybrid retrieval service in this repository, not an MCP server. It indexes documents and serves lexical, vector, graph and metadata retrieval over a FastAPI API (/query, /jobs/index, /documents, /health, /metrics). Run it from a checkout with uv run clio serve inside clio-agentic-search/; the clio-kit launcher does not ship it.

Contribute Servers, Skills or Plugins

Contribute a package folder under plugins/, skills/, agents/ or hooks/; website builds and CI update the catalogues automatically. See the folder contribution guide.

Add skills here, or list a plugin maintained in your own repository:

bash
clio-kit plugin init my-pluginclio-kit plugin validate my-pluginclio-kit plugin submit my-plugin --repo owner/name

submit generates a community entry for a pull request. External servers can use any language; servers hosted inside CLIO currently support Python, Node.js and Go.

Add an optional Claude Code hook with clio-kit plugin init my-plugin --hook. See the hook guide.

See the contribution guide and community guide for requirements and submission details.

Install in Cursor

Add to .cursor/mcp.json in your project, or ~/.cursor/mcp.json:

json
{  "mcpServers": {    "clio-hdf5": { "command": "clio-kit", "args": ["mcp-server", "hdf5"] },    "clio-adios": { "command": "clio-kit", "args": ["mcp-server", "adios"] },    "clio-parquet": { "command": "clio-kit", "args": ["mcp-server", "parquet"] },    "clio-compression": { "command": "clio-kit", "args": ["mcp-server", "compression"] }  }}

Install the workflow skills from your project:

bash
clio-kit skill install --bundle clio-scientific-io --target .cursor/skills

See Cursor MCP docs and skills docs.

Install in Claude Code

From the CLIO Kit checkout, install the workflow plugin with its MCPs and skills:

bash
claude plugin marketplace add "$PWD"claude plugin install clio-scientific-io@clio-kitclaude mcp list

Skills-only and agent plugins:

bash
claude plugin install clio-skills@clio-kit    # scientific workflow skills, no MCP serversclaude plugin install clio-agents@clio-kit    # workflow planner and evidence reviewer

See setup.md for details.

Install in VS Code

Add to .vscode/mcp.json for GitHub Copilot:

json
{  "servers": {    "clio-hdf5": { "type": "stdio", "command": "clio-kit", "args": ["mcp-server", "hdf5"] },    "clio-adios": { "type": "stdio", "command": "clio-kit", "args": ["mcp-server", "adios"] },    "clio-parquet": { "type": "stdio", "command": "clio-kit", "args": ["mcp-server", "parquet"] },    "clio-compression": { "type": "stdio", "command": "clio-kit", "args": ["mcp-server", "compression"] }  }}

Install the workflow skills from your project:

bash
clio-kit skill install --bundle clio-scientific-io --target .github/skills

Start the servers with MCP: List Servers. The Codex extension uses the Codex configuration below. See VS Code MCP docs and skills docs.

Install in Claude Desktop

Edit claude_desktop_config.json through Settings → Developer → Edit Config:

json
{  "mcpServers": {    "clio-hdf5": { "command": "clio-kit", "args": ["mcp-server", "hdf5"] },    "clio-adios": { "command": "clio-kit", "args": ["mcp-server", "adios"] },    "clio-parquet": { "command": "clio-kit", "args": ["mcp-server", "parquet"] },    "clio-compression": { "command": "clio-kit", "args": ["mcp-server", "compression"] }  }}

Restart Claude Desktop. This config adds MCP servers only; CLIO's native skill and agent plugins target Claude Code. See Claude Desktop MCP docs.

Install in Codex

Add the MCP servers for Codex CLI or its IDE extension:

bash
codex mcp add clio-hdf5 -- clio-kit mcp-server hdf5codex mcp add clio-adios -- clio-kit mcp-server adioscodex mcp add clio-parquet -- clio-kit mcp-server parquetcodex mcp add clio-compression -- clio-kit mcp-server compressioncodex mcp list

Install the workflow skills from your project:

bash
clio-kit skill install --bundle clio-scientific-io --target .agents/skills

Check /mcp and /skills in Codex. To install a complete supported workflow, use clio-kit plugin install clio-dataset-report --client codex --project .; review its hooks with /hooks before running it. See Codex MCP docs and skills docs.

Install in Antigravity

Open MCP Servers → Manage MCP Servers → View raw config and add:

json
{  "mcpServers": {    "clio-hdf5": { "command": "clio-kit", "args": ["mcp-server", "hdf5"] },    "clio-adios": { "command": "clio-kit", "args": ["mcp-server", "adios"] },    "clio-parquet": { "command": "clio-kit", "args": ["mcp-server", "parquet"] },    "clio-compression": { "command": "clio-kit", "args": ["mcp-server", "compression"] }  }}

Install the workflow skills from your project:

bash
clio-kit skill install --bundle clio-scientific-io --target .agents/skills

Reload the MCP configuration. For Antigravity CLI, start the first session from this project with agy --new-project so its local skills and MCP configuration are loaded. Reopen it with agy --project <project-name-or-id>. Reuse .agents/skills if already installed for Codex. CLIO does not yet ship a native Antigravity plugin. See Antigravity MCP docs and skills docs.

Available Packages

The version below identifies each MCP server's contract and runtime release, independently of the containing clio-kit wheel version. JARVIS 3.7 and SLURM 3.0 have contracts redesigned for agent use. Spack is at 2.3, while the other contracts retain their existing 2.x identities until a focused upgrade.

The Spack install contract makes concretization explicit: reuse=true passes spack install --reuse, while reuse=false passes spack install --fresh. Agents should discover first, install only when needed, then pass the exact spack_locate result to JARVIS for runtime loading. A find with no installed match is normal typed data (count=0, packages=[]); locate reports the distinct not_installed semantic, while real Spack failures remain errors.

📦 Package📌 Ver🔧 System📋 Description⚡ Install Command
adios2.3.2Data I/ORead data using ADIOS2 engineclio-kit mcp-server adios
arxiv2.2.8ResearchFetch research papers from ArXivclio-kit mcp-server arxiv
chronolog2.0.6LoggingLog and retrieve data from ChronoLogclio-kit mcp-server chronolog
compression2.2.8UtilitiesFile compression with gzipclio-kit mcp-server compression
darshan2.2.8PerformanceI/O performance trace analysisclio-kit mcp-server darshan
earthdata1.0.0Earth ScienceSearch and download NASA Earthdata datasets (runs earthdata-mcp-server 0.6.0)clio-kit mcp-server earthdata
geo2.4.0GeospatialRender GeoJSON vector layers with basemapsclio-kit mcp-server geo
hdf52.3.1Data I/OHPC-optimized scientific data with 27 tools, AI insights, caching, streamingclio-kit mcp-server hdf5
home-assistant1.0.0HomeYour Home Assistant's sensors, devices and automations (runs ha-mcp 9.2.0)clio-kit mcp-server home-assistant
jarvis3.7.7WorkflowDurable pipeline, bounded package discovery, progress, artifact, and service-runtime managementclio-kit mcp-server jarvis
lmod3.0.4EnvironmentEnvironment module managementclio-kit mcp-server lmod
ndp2.2.9Data ProtocolSearch and discover datasets across CKAN instancesclio-kit mcp-server ndp
node-hardware2.3.3SystemSystem hardware informationclio-kit mcp-server node-hardware
pandas2.4.1Data AnalysisCSV data loading and filteringclio-kit mcp-server pandas
parallel-sort2.3.3ComputingLarge file sortingclio-kit mcp-server parallel-sort
paraview3.1.0VisualizationLive 3D views of scientific data, here or over SSHclio-kit mcp-server paraview
parquet2.3.1Data I/ORead Parquet file columnsclio-kit mcp-server parquet
pdf1.0.0ResearchRead papers in an interactive PDF viewer (runs the MCP Apps PDF server 2.0.4)clio-kit mcp-server pdf
plot2.2.8VisualizationGenerate plots from CSV dataclio-kit mcp-server plot
seismology2.3.4SeismologyAnalyze SAC waveforms and archivesclio-kit mcp-server seismology
scientific-catalog1.1.7DiscoveryOperator-owned scientific dataset discoveryclio-kit mcp-server scientific-catalog
slicer1.0.03D PrintingSlice models with the installed PrusaSlicer or OrcaSlicer and view toolpaths layer by layerclio-kit mcp-server slicer
slurm3.1.1HPCJob submission and managementclio-kit mcp-server slurm
spack2.3.4Package ManagementStructured package discovery, installation, and locationclio-kit mcp-server spack
spice1.0.0ElectronicsSimulate circuits with ngspice or LTspice and plot waveforms (runs ltspice-mcp 0.8.0)clio-kit mcp-server spice
terrain2.2.8GeospatialAnalyze DEMs and terrain point cloudsclio-kit mcp-server terrain
web2.1.6WebWeb search and URL fetch, with queryable, cancellable fetch tasks; DOI and document conversion need a remote serviceclio-kit mcp-server web

📖 Usage Examples

HDF5: Scientific Data Analysis

"What datasets are in climate_simulation.h5? Show me the temperature field structure and read the first 100 timesteps."

Tools used: open_file, analyze_dataset_structure, read_partial_dataset, list_attributes

Slurm: HPC Job Management

"Submit simulation.py to Slurm with 32 cores, 64GB memory, 24-hour runtime. Monitor progress and retrieve output when complete."

Tools used: slurm_submit, slurm_list, slurm_describe

ArXiv: Research Discovery

"Find the latest papers on diffusion models from ArXiv, get details on the top 3, and export citations to BibTeX."

Tools used: search_arxiv, get_paper_details, export_to_bibtex, download_paper_pdf

Pandas: Data Processing

"Load sales_data.csv, clean missing values, compute statistics by region, and save as Parquet."

Tools used: load_data, handle_missing_data, groupby_operations, save_data

Plot: Data Visualization

"Create a line plot showing temperature trends over time from weather.csv with proper axis labels."

Tools used: line_plot, data_info


🚨 Troubleshooting

Server Not Found Error

If clio-kit mcp-server <server-name> fails:

bash
# Verify server name is correctclio-kit mcp-servers
# Common names: hdf5, pandas, slurm, arxiv (not hdf5-mcp, pandas-mcp)
Import Errors or Missing Dependencies

For development or local testing:

bash
cd mcp-servers/hdf5uv sync --all-extras --devuv run hdf5-mcp
uv or clio-kit Command Not Found

Install uv package manager:

bash
# Linux/macOScurl -LsSf https://astral.sh/uv/install.sh | sh
# Windowspowershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
# Or via pippip install uv

Then install CLIO Kit persistently and expose uv's tool directory:

bash
uv tool install --force --reinstall --editable .uv tool update-shell

Open a new shell after update-shell, then check it resolved:

bash
clio-kit mcp-servers

Team

Sponsored By

[NSF Logo] NSF (National Science Foundation) - Supporting scientific computing research and AI integration initiatives

we welcome more sponsorships. please contact the Principal Investigator

Ways to Contribute

  • Submit Issues: Report bugs or request features via GitHub Issues
  • Build MCP Servers: Contribute Python, Node.js or Go servers (guide)
  • Write Skills: Share reusable scientific workflows (guide)
  • Share Plugins or Marketplaces: List tools maintained in your own repository (guide)
  • Improve Documentation: Help make guides clearer
  • Share Use Cases: Tell us how you're using CLIO Kit in your research

Full Guide: CONTRIBUTING.md

Community & Support


Source: README.md at commit 4b5e6e3

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v2.2.3LatestSep 16, 2026

Score

50% 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