RRepoGEO

REPOGEO REPORT · LITE

shaneholloman/mcp-knowledge-graph

Default branch main · commit 9f6268c4 · scanned 6/14/2026, 6:21:58 PM

GitHub: 865 stars · 103 forks

AI VISIBILITY SCORE
28 /100
Critical
Category recall
0 / 2
Not recommended in any query
Rule findings
1 pass · 1 warn · 0 fail
Objective metadata checks
AI knows your name
2 / 3
Direct prompts that named your repo
HOW TO READ THIS REPORT

Action plan is what to do next — copy-pasteable changes prioritized by impact. Category visibility is the real GEO test: when a user asks an AI a brand-free question that should surface shaneholloman/mcp-knowledge-graph, does the AI actually recommend you — or your competitors? Objective checks verify the metadata signals AI engines weight first. Self-mention check detects whether AI even knows you exist by name.

Action plan — copy-paste fixes

3 prioritized changes generated by gemini-2.5-flash. Mark items done after you ship the fix.

OVERALL DIRECTION
  • highreadme#1
    Clarify "MCP" acronym and project's core purpose in README's opening

    Why:

    CURRENT
    # MCP Knowledge Graph

**Persistent memory for AI models through a local knowledge graph.**
    COPY-PASTE FIX
    # Memory Control Plane (MCP) Knowledge Graph

**A Memory Control Plane (MCP) server enabling persistent memory for AI models like Claude through a local knowledge graph.**
  • mediumhomepage#2
    Add a homepage URL to the repository

    Why:

    CURRENT
    (none)
    COPY-PASTE FIX
    [Your project's website or relevant documentation URL]
  • lowtopics#3
    Add more specific topics for conversational AI and local long-term memory

    Why:

    CURRENT
    ai-memory, claude-ai, knowledge-graph, mcp, memory-server, typescript
    COPY-PASTE FIX
    ai-memory, claude-ai, knowledge-graph, mcp, memory-server, typescript, conversational-ai, long-term-memory, local-ai

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

Category visibility — the real GEO test

Brand-free queries asked to google/gemini-2.5-flash. Did AI recommend you, or someone else?

Same questions for every model — switch tabs to compare answers and rankings.

Recall
0 / 2
0% of queries surface shaneholloman/mcp-knowledge-graph
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
Neo4j
Recommended in 1 of 2 queries
COMPETITOR LEADERBOARD
  1. Neo4j · recommended 1×
  2. LangChain · recommended 1×
  3. LlamaIndex · recommended 1×
  4. TypeDB · recommended 1×
  5. RDFox · recommended 1×
  • CATEGORY QUERY
    How to give AI models persistent memory using a local knowledge graph?
    you: not recommended
    AI recommended (in order):
    1. Neo4j
    2. LangChain
    3. LlamaIndex
    4. TypeDB
    5. RDFox
    6. GraphDB
    7. DGL (Deep Graph Library)
    8. PyG (PyTorch Geometric)
    9. Memgraph

    AI recommended 9 alternatives but never named shaneholloman/mcp-knowledge-graph. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    Looking for a TypeScript solution to provide conversational AI with long-term memory locally.
    you: not recommended
    AI recommended (in order):
    1. LangChain.js (langchain-ai/langchainjs)
    2. ChromaDB (chroma-core/chroma)
    3. Pinecone (pinecone-io/pinecone-ts-client)
    4. LlamaIndex.TS (run-llama/LlamaIndexTS)
    5. LanceDB (lancedb/lancedb)
    6. Faiss.js (ivangabriele/faiss-js)
    7. NeDB (louischatriot/nedb)
    8. LowDB (typicode/lowdb)
    9. Weaviate (weaviate/weaviate)
    10. Qdrant (qdrant/qdrant)

    AI recommended 10 alternatives but never named shaneholloman/mcp-knowledge-graph. This is the gap to close.

    Show full AI answer

Objective checks

Rule-based audits of metadata signals AI engines weight most.

  • Metadata completeness
    warn

    Suggestion:

  • README presence
    pass

Self-mention check

Does AI even know your repo exists when asked about it directly?

  • Compared to common alternatives in this category, what is the core differentiator of shaneholloman/mcp-knowledge-graph?
    pass
    AI did not name shaneholloman/mcp-knowledge-graph — likely talking about a different project

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • If a team adopts shaneholloman/mcp-knowledge-graph in production, what risks or prerequisites should they evaluate first?
    pass
    AI named shaneholloman/mcp-knowledge-graph explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

  • In one sentence, what problem does the repo shaneholloman/mcp-knowledge-graph solve, and who is the primary audience?
    pass
    AI named shaneholloman/mcp-knowledge-graph explicitly

    AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

Embed your GEO score

Drop this badge into the README of shaneholloman/mcp-knowledge-graph. It auto-updates whenever the report is rescanned and links back to the latest report — easy public proof that you care about AI discoverability.

RepoGEO badge previewLive preview
MARKDOWN (README)
[![RepoGEO](https://repogeo.com/badge/shaneholloman/mcp-knowledge-graph.svg)](https://repogeo.com/en/r/shaneholloman/mcp-knowledge-graph)
HTML
<a href="https://repogeo.com/en/r/shaneholloman/mcp-knowledge-graph"><img src="https://repogeo.com/badge/shaneholloman/mcp-knowledge-graph.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

shaneholloman/mcp-knowledge-graph — Lite scans stay free; this card itemizes Pro deep limits vs Lite.

  • Deep reports10 / month
  • Brand-free category queries5 vs 2 in Lite
  • Prioritized action items8 vs 3 in Lite