Install
$ agentstack add mcp-mattartzanthro-gephi-ai ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
gephi-ai
AI-powered network analysis through Gephi and the Model Context Protocol (MCP). Build, analyze, style, and export publication-ready network visualizations by talking to your AI assistant.
Built for researchers working across network science and AI.
What you get
76 MCP tools for controlling Gephi Desktop — graph construction, community detection, centrality analysis, layout algorithms, filtering, styling, and publication-ready export.
Claude Code plugin with slash commands (/analyze-network, /community-detection, /centrality, /visualize, /import-and-explore), a specialized network analyst agent, and workflow skills that teach Claude network science best practices.
Works with any MCP client — Claude Code, Claude Desktop, or any MCP-compatible assistant.
Architecture
Three components connect your AI assistant to Gephi Desktop:
Claude / AI Assistant
│
MCP Protocol (stdio)
│
MCP Server (Python) ← Translates MCP tool calls to HTTP
│
HTTP API (localhost:8080)
│
Gephi Plugin (Java) ← Runs inside Gephi Desktop
│
Gephi Desktop ← Must be running first
| Component | Directory | What it does | |-----------|-----------|-------------| | Gephi Plugin | gephi-mcp-plugin/ | Java module that adds an HTTP API to Gephi Desktop | | MCP Server | mcp-server/ | Python server that exposes 76 Gephi tools via MCP | | Claude Plugin | claude-plugin/ | Skills, commands, agent, and hooks for Claude Code |
All three must be installed. Gephi Desktop must be running before using any tools.
> Security note: the plugin's HTTP API binds to 127.0.0.1 only, validates the > request Host header (DNS-rebinding defense), and sends no CORS headers — it is > reachable only by local processes such as the MCP server, never by a web page. > It is not authenticated, so do not expose port 8080 beyond localhost.
> macOS note: Gephi's OpenGL graph view holds the graph's read lock almost > continuously while rendering, so a burst of API writes against a large, actively > rendered graph can deadlock Gephi (calls time out; only gephi_health_check answers). > The plugin hardens its own locking so a single focused pass works, but the renderer is > Gephi-core. Best practice: do build/import → compute → style → layout → export as one > sequence; if a write call ever hangs, fully quit and reopen Gephi to recover.
Setup
Prerequisites
- Gephi Desktop 0.11.1+
- Java JDK 11+ and Maven (to build the Gephi plugin)
- Python 3.10+ (for the MCP server)
- Claude Code or Claude Desktop (for AI interaction)
Step 1: Install the Gephi plugin
This adds the HTTP API server inside Gephi Desktop.
cd gephi-mcp-plugin
mvn clean package
Then in Gephi: Tools → Plugins → Downloaded → Add Plugins — select target/nbm/gephi-mcp-1.1.3.nbm.
Restart Gephi. The plugin starts automatically and listens on http://127.0.0.1:8080.
Verify: Open a browser to http://127.0.0.1:8080/health — you should see {"success": true}.
Step 2: Install the MCP server
This bridges MCP clients to the Gephi HTTP API.
cd mcp-server
pip install -e .
This installs the gephi-mcp command on your PATH.
Verify: Run gephi-mcp --help to confirm it installed.
Step 3: Connect your AI assistant
Claude Code (full plugin — recommended)
claude plugin install gephi-ai/gephi-network-analysis
This adds the MCP server, slash commands, network analyst agent, skills, and a health-check hook.
Claude Code (MCP tools only)
If you just want the 76 tools without skills and commands:
claude mcp add gephi-mcp -- gephi-mcp
Claude Desktop
Add to your MCP configuration (claude_desktop_config.json):
{
"mcpServers": {
"gephi-mcp": {
"command": "gephi-mcp"
}
}
}
Other MCP clients
Point your client at the gephi-mcp command using stdio transport.
Step 4: Verify
With Gephi running, ask your assistant:
> "Check if Gephi is running"
It should call gephi_health_check and confirm the connection. In Claude Code, try:
/gephi-network-analysis:import-and-explore path/to/your/graph.gexf
What the Claude Code plugin adds
The plugin (claude-plugin/) goes beyond raw MCP tools:
| Component | What it does | |-----------|-------------| | Slash commands | /analyze-network, /community-detection, /centrality, /visualize, /import-and-explore | | Network analyst agent | Specialized subagent for deep structural analysis, metric comparison, and network classification | | Gephi skill | Teaches Claude network science workflows, visualization best practices, and known Gephi gotchas | | Health-check hook | Automatically verifies Gephi is running before graph-modifying operations | | Reference guides | Tool reference, layout guide, and statistics interpretation guide |
Tools (76)
| Category | Count | Examples | |----------|-------|---------| | Project & Workspace | 10 | gephi_create_project, gephi_save_project, gephi_duplicate_workspace, gephi_rename_workspace | | Graph Construction | 18 | gephi_add_nodes, gephi_add_edges, gephi_query_nodes, gephi_get_node | | Statistics | 9 | gephi_compute_modularity, gephi_compute_pagerank | | Layout | 6 | gephi_run_layout, gephi_get_layout_properties | | Appearance | 9 | gephi_color_by_partition, gephi_size_by_ranking | | Filtering | 6 | gephi_filter_by_degree, gephi_extract_giant_component | | Attributes | 5 | gephi_get_columns, gephi_set_node_attributes | | Preview & Export | 8 | gephi_export_png, gephi_export_pdf, gephi_export_gexf | | Import | 4 | gephi_import_file, gephi_import_gexf | | Health | 1 | gephi_health_check |
Example workflows
Community detection
1. gephi_create_project
2. gephi_import_file (your GEXF, GraphML, or CSV)
3. gephi_compute_degree
4. gephi_compute_modularity (resolution: 1.0)
5. gephi_color_by_partition (column: modularity_class)
6. gephi_size_by_ranking (column: degree)
7. gephi_run_layout (ForceAtlas 2, 1000 iterations)
8. gephi_export_png (3840x2160 for publication)
Centrality analysis
1. Import or build graph
2. gephi_compute_betweenness
3. gephi_compute_pagerank
4. gephi_run_layout (ForceAtlas 2)
5. gephi_color_by_ranking (column: betweenesscentrality)
6. gephi_size_by_ranking (column: pageranks)
7. gephi_query_nodes (find top-ranked nodes)
Documentation
Reference guides are in claude-plugin/skills/gephi/:
- SKILL.md — Workflow patterns, best practices, and critical gotchas
- references/tool-reference.md — Complete API reference for all 76 tools
- references/layout-guide.md — Layout algorithm selection and parameter tuning
- references/statistics-guide.md — Statistics interpretation guide
Tech stack
- Gephi Plugin: Java 11, NetBeans Platform, NanoHTTPD, Gson
- MCP Server: Python 3.10+, MCP SDK (FastMCP), httpx, Pydantic
- Target: Gephi 0.11.1, NetBeans RELEASE290
Attribution
If you use or adapt this project in your work, please credit:
> Built with gephi-ai (Matt Artz, 2025–2026) — https://github.com/MattArtzAnthro/gephi-ai
License
Apache License 2.0 — see [LICENSE](LICENSE).
Author
Matt Artz — mattartz.me | ORCID
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: MattArtzAnthro
- Source: MattArtzAnthro/gephi-ai
- License: Apache-2.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.