Run network analysis, community detection, centrality metrics, and graph visualization through Gephi Desktop, with agents for claim verification, layout iteration, and text-to-network construction.
Run centrality analysis and identify the most important nodes
Run full community detection workflow on the current graph
Run comprehensive structural analysis and report network properties
Take the current graph to a publication-ready map (dispatches the layout-iterator agent)
Test a hypothetical edit against the loaded graph without touching it — "what would happen if I removed this node?"
Independently verify a single plain-language structural claim about the loaded Gephi graph and report confirmed / refuted / can't-tell, with the number. Use when someone asserts a checkable claim — "she's more central than he is," "these two teams barely interact," "the org survives losing him," "these accounts form a tight cluster." Read-only; never restyles or edits the graph.
Take the graph currently open in Gephi to a clean, legible, publication-ready map through the run → visual_qa → inspect → adjust loop, returning just the finished export + caption + a short change log. Use for "beautify / make this look good / lay this out well." Mutates the live graph's layout and style (that is the job); never edits nodes or edges.
Open-ended structural analysis of the loaded Gephi graph. Use when the user wants a comprehensive read of a network's properties — centrality comparison, community characterization, bridge/hub identification, structural interpretation — rather than one specific claim (that's claim-verifier) or a build/beautify job. Read-leaning: it interprets, it does not restyle.
Turn free text (interview transcripts, field notes, open-ended survey answers, documents, social posts) into a word co-occurrence network in Gephi, tuned so the map reflects the discourse and not its stopwords or artifacts. Use for "build a text network / concept map from this text," or when someone hands over a corpus and wants to see its themes as a graph. Builds and lays out; the reading is a separate step.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
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.
Status: public beta. APIs may change between minor versions.
Your AI assistant drives Gephi. Say what you want in plain language and the assistant builds, analyzes, styles, and exports publication-ready network maps.
It's a conversation, not a command line. The assistant explains what it's doing, checks its own maps before showing them, and teaches you to read what you're seeing. You can point back: select nodes in the Gephi window and ask "what did I select?"
Any data, any MCP client. Network files import directly; spreadsheets and other data become networks conversationally. Works with Claude Code, Claude Desktop, or any MCP-compatible assistant.
gephi_undo brings the graph back/analyze-network, /community-detection, /centrality, /visualize, /import-and-explore, /beautify, /verify-claim, /text-network, /teach, /counterfactualThree 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 104 Gephi tools via MCP |
| Claude Plugin | claude-plugin/ | Skills, commands, agent, and hooks for Claude Code |
Install the Gephi plugin plus your AI client's connection — the Claude Code plugin bundles the MCP server, so most users install just two things. Gephi Desktop must be running before using any tools.
Security note: the plugin's HTTP API binds to
127.0.0.1only, validates the requestHostheader (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: older plugin versions could wedge Gephi during sustained writes against a large rendered graph (calls hang; only
gephi_health_checkanswers). Plugin 1.2.0 fixes the two causes on our side: writes now pause the renderer via Gephi's own viz-engine API, and a read-lock leak in the query endpoints (the main culprit) is closed. All lock waits are bounded, so a genuinely wedged Gephi returns an immediate "fully quit and reopen Gephi" error instead of hanging, andgephi_health_checkexposes lock probes (graph_lock,graph_lock_stats) that detect the condition. If you ever see persistent "Graph is busy" errors, restart Gephi — and make sure you are on plugin 1.2.2 or newer.
This adds the HTTP API server inside Gephi Desktop. No build tools needed — download the pre-built plugin:
Skills and agents for anthropological research across the full research lifecycle — from question formulation through publication and career advancement
npx claudepluginhub mattartzanthro/gephi-ai --plugin gephi-network-analysisDevelop causal diagrams (DAGs) from social-science research questions and literature, then render publication-ready figures using Mermaid, R, or Python.
Create data visualizations and plots
Generate publication-quality academic diagrams, statistical plots, and presentation slides using PaperBanana multi-agent framework
Deep research and auto-generate knowledge relationship diagrams in PDF format. From research to visualization in one tool.
Tools for building and analyzing technology relationships and dependencies. Helps visualize tech stacks and integration patterns.
Agent skills for Neo4j — Cypher queries, graph modeling, drivers, imports, GraphRAG, GDS, vector indexes, Aura provisioning, and more.