MCP Server infranodus

Official

Integrate InfraNodus knowledge graph and text network analysis into LLM workflows.

How to install ↓ Compare GitHub source repository ↗

Category: Other #101 of 230
Stars: ★ 102 Popular
Transport: stdio (local process) · Streamable HTTP
Runtime: Node.js 18+
Credentials: API key / credential required
License: MIT
Last commit: 22 days ago
Tools: 30

56FMRS · C

InfraNodus MCP Server offers a rich set of text network analysis tools, seamlessly integrating knowledge graph capabilities into LLM workflows. Its powerful features, such as content gap detection and SEO analysis, make it particularly valuable for content creators and researchers. However, users should be mindful of API quotas and privacy considerations.

Strongest · Documentation 15/20 Weakest · Reliability 9/20

Reliability

9/20

Security and permissions

9/20

Maintenance

9/20

Documentation

15/20

Setup experience

14/20

Why each score

Reliability 9/20: Evidence: README lists 30 tools, stdio/npx/node startup, build/inspect commands, and a progress-notification design; the happy path appears plausible. Deductions: no server manifest, package.json, or source listing; no CI workflow or committed tests; build instructions are ambiguous (relationship between build:inspect and build unclear); tool names/parameters cannot be verified against implementation, and error handling/edge cases are undocumented. Under the static calibration this cannot exceed 12; score 9.
Security and permissions 9/20: Evidence: API key is passed via environment variables and examples contain only placeholders, no real secrets; no malware, credential theft, or covert exfiltration patterns are present. Deductions: README does not describe data flow, privacy, or retention; the API key appears to grant broad account access without least-privilege guidance; several tools persist/save graphs by default (e.g., generate_ontology_graph, memory_add_relations) without explicit confirmation or side-effect disclosure; no security policy or vulnerability reporting channel. Risks are visible but permissions/confirmation/scoping are incomplete; score 9.
Maintenance 9/20: Evidence: repository is not archived, has an MIT license, README references an npm package and ongoing development; open-issues count is low. Deductions: no commit/release history, dependency-update evidence, CI status, issue-response evidence, or security-response channel; stars are only a discovery signal and not scored. Activity cannot be confirmed and governance/versioning gaps remain; score 9.
Documentation 15/20: Evidence: README is broad: hosted/npx/local/Smithery install paths, macOS/Windows config examples, descriptions of 30 tools, partial API parameters, progress notifications, development commands, troubleshooting, and resource links. Deductions: only 4 tools have formal parameter documentation; most tools lack detailed schemas/limits; cost and data-privacy disclosure are incomplete; README contains typos/ambiguities (yourusername, build vs build:inspect). Layering and examples are strong but limitation disclosure is incomplete; score 15.
Setup experience 14/20: Evidence: README provides a one-step hosted URL, npx config examples for Claude Desktop/Cursor/Claude Code, local build steps, Windows/macOS paths, and Smithery alternative; Node.js 18+ prerequisite is stated. Deductions: no CI/tests or other verifiable execution evidence, so static calibration caps setup at 15; build instructions are confusing (build:inspect vs build), the clone URL is a placeholder, hosted OAuth flow details are missing, and package versions are unpinned. Steps are mostly clear but still manual/ambiguous; score 14.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessUses the networkChanges third-party account data

Best for

Researchers needing knowledge graphs and network analysis
Content creators and SEO professionals
Developers looking to enhance LLM workflows with structured context
Analysts seeking to extract structured insights from text

Not for

Users requiring fully offline usage without API key (limited free quota)
Those seeking lightweight simple text summarization
Users who don't need graph structures or network analysis

Required permissions

Requires a valid InfraNodus API key
Can read provided text or URL content
Can create, retrieve, and modify knowledge graphs in the user's account
May call external AI models (via InfraNodus API)

Risks and side effects

Risk of API key misuse or leakage
Dependence on external API availability and quota limits
Paywall: API key needed after free quota
Hosted server may store text data, privacy concerns

Setup

Before you start

Runtime：Node.js 18+

INFRANODUS_API_KEY requiredsecret API key for your InfraNodus account, obtained at https://infranodus.com/api-access; it can be left empty for about 70 free requests, but a valid key is needed afterwards.

Create an account on InfraNodus and get an API key (14-day free trial available).
For remote/web apps, use the server URL https://mcp.infranodus.com and authenticate via OAuth.
For local install, use npx command npx -y infranodus-mcp-server with environment variable INFRANODUS_API_KEY.
Add configuration to a supported client (e.g., Claude Desktop or Cursor).

claude_desktop_config.json

{
  "mcpServers": {
    "infranodus": {
      "command": "npx",
      "args": [
        "-y",
        "infranodus-mcp-server"
      ],
      "env": {
        "INFRANODUS_API_KEY": "YOUR_INFRANODUS_API_KEY"
      }
    }
  }
}

Shown for Claude Desktop. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json

{
  "servers": {
    "infranodus": {
      "command": "npx",
      "args": [
        "-y",
        "infranodus-mcp-server"
      ],
      "env": {
        "INFRANODUS_API_KEY": "YOUR_INFRANODUS_API_KEY"
      }
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal

claude mcp add infranodus -e INFRANODUS_API_KEY=YOUR_INFRANODUS_API_KEY -- npx -y infranodus-mcp-server

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

After installing, the infranodus server's tools (e.g. generate_knowledge_graph, analyze_text) should appear in your MCP client's tool list; asking "use InfraNodus to analyze this text and show me the main topics" and getting graph-based topic results confirms the connection works.

Troubleshooting

Check that the server path or command in config is correct
Verify the API key is valid and not expired
Ensure Node.js is in system PATH
Fully restart the client application
For build errors, run `rm -rf node_modules package-lock.json && npm install && npm run build`

Things to try

Once connected, you can ask your AI assistant things like:

Use InfraNodus to analyze this text and show me the main topical clusters
Generate a knowledge graph from this document and find its content gaps
Retrieve my existing graph called 'Research Notes' from InfraNodus and analyze its structure
Compare my article with Google search results and generate an SEO report of missing keywords

Tools 30

generate_knowledge_graph read-only

Convert any text into a visual knowledge graph, extract topics, concepts, and relationships, identify structural patterns and clusters, with AI-powered topic naming and entity detection.

analyze_existing_graph_by_name read-only

Retrieve and analyze existing graphs from your InfraNodus account, access previously saved analyses, and export graph data with full statistics.

analyze_text read-only

Analyze a text, URL, or YouTube transcript, extract and analyze a graph, returning topics, clusters, statements, graph structure, and AI summary.

generate_content_gaps read-only

Detect missing connections in discourse, identify underexplored topics, generate research questions, and suggest content development opportunities.

generate_topical_clusters read-only

Generate topics and clusters of keywords from text using knowledge graph analysis, with AI-generated cluster summaries useful for SEO topical authority.

generate_contextual_hint read-only

Generate a topical overview of a text and provide insights for LLMs to generate better responses, useful for prompt augmentation.

generate_research_questions read-only

Generate research questions that bridge content gaps from text, URL, or an existing graph.

generate_research_ideas read-only

Generate innovative research ideas based on content gaps identified in the text, providing actionable suggestions.

Show 22 more tools

optimize_text_structure read-only

Analyze the level of bias and coherence in text using knowledge graph analysis, and suggest improvements to balance discourse or deepen analysis.

optimize_reasoning read-only

Apply bias/coherence analysis to the model's own reasoning trace, steering it toward optimal diversity and coherence.

generate_responses_from_graph read-only

Generate responses based on an existing InfraNodus graph, using any AI model and prompt.

develop_conceptual_bridges read-only

Analyze text and develop latent ideas based on concepts connecting the text to broader discourse, discovering hidden themes.

develop_latent_topics read-only

Extract underdeveloped topics with ideas on how to develop them, identifying areas needing more elaboration.

develop_text_tool read-only

Comprehensive text analysis combining content gap ideas, latent topics, and conceptual bridges, with sequential analyses and progress tracking.

create_knowledge_graph writes

Create a knowledge graph in InfraNodus from text and provide a link to it.

generate_ontology_graph writes

Use AI to generate a reasoning ontology graph (entities and relations) from a topic, prompt, or text, optionally saving it.

analyze_llm_results writes

Ask an LLM to describe a topic and turn its response into a knowledge graph, revealing how the model frames it and its biases.

overlap_between_texts read-only

Create knowledge graphs from two or more texts and find the overlap (similarities) between them.

merged_graph_from_texts read-only

Build a graph of all provided texts and URLs, showing topical clusters and gaps across the merged content.

difference_between_texts read-only

Compare knowledge graphs from two or more texts and find what's present in others but not in the first.

analyze_google_search_results read-only

Generate a graph with keywords and topics for Google search results, understanding current informational supply.

analyze_youtube_results read-only

Generate a graph from YouTube results (search, comments, channel, playlist, subtitles), understanding discourse topics and gaps.

analyze_related_search_queries read-only

Generate a graph from Google suggested search queries, understanding current informational demand.

search_queries_vs_search_results read-only

Generate a graph of keyword combinations people search for but that don't readily appear in results, finding demand-supply gaps.

generate_seo_report read-only

Analyze content for SEO optimization by comparing with Google search results and queries, identifying content gaps and opportunities.

memory_add_relations writes

Add relations to InfraNodus memory from text, automatically detecting entities or using [[wikilinks]].

memory_get_relations read-only

Retrieve relations from InfraNodus memory for specific entities, supporting entity-specific searches or full context retrieval.

retrieve_from_knowledge_base read-only

Retrieve context from an existing InfraNodus knowledge graph using GraphRAG, with natural language queries.

search read-only

Search through existing InfraNodus graphs, also public graphs of a user, compatible with ChatGPT Deep Research.

fetch read-only

Fetch a specific search result for a graph, usable in ChatGPT Deep Research.

Use cases

Integrating existing knowledge graphs into AI conversations

Analyzing text structure to discover topical clusters and content gaps

Generating SEO reports and content optimization suggestions

Creating new knowledge graphs to augment LLM responses

Retrieving context from knowledge bases using GraphRAG

Supported clients

Claude Desktop

Cursor

Listed from the project's documentation, not tested by this site.

Overview

InfraNodus MCP Server is an official MCP server that enables LLM workflows and AI assistants to analyze text using advanced network science algorithms, generate knowledge graphs, detect content gaps, and identify key topics and concepts. It transforms unstructured text into structured insights using graph theory and network analysis.

Similar servers

Hevy MCP 77 · B

Manage your Hevy workout data from AI assistants via MCP.

★ 509 · Tools 26 Compare with this →

Firecrawl MCP Server 75 · B

Firecrawl's official MCP server for web search, scraping, and structured extraction for AI agents

★ 7.6k · Tools 11 Compare with this →

BioMCP 75 · B

One binary. One grammar. Evidence from the biomedical sources you already trust.

★ 654 · Tools 11 Compare with this →

Compartment 75 · B

Encrypted, fully offline long-term memory for AI agents

★ 579 · Tools 14 Compare with this →

Compare with other MCP servers

Source revision 9ef686b37c86 Data synced 2026-10-12 Read the FMRS scoring method