RRepoGEO

REPOGEO REPORT · LITE

ClickHouse/mcp-clickhouse

Default branch main · commit cb75c276 · scanned 6/1/2026, 7:56:47 AM

GitHub: 793 stars · 186 forks

AI VISIBILITY SCORE
35 /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
3 / 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 ClickHouse/mcp-clickhouse, 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
    Reposition the README's opening paragraph to clarify AI integration purpose

    Why:

    CURRENT
    An MCP server for ClickHouse.
    COPY-PASTE FIX
    This is an MCP (Model-Controller-Proxy) server that enables AI assistants and Large Language Models (LLMs) to interact with ClickHouse databases. It provides a set of specialized tools for querying, listing databases, and inspecting schemas, allowing AI agents to seamlessly access and manipulate data within your ClickHouse cluster.
  • hightopics#2
    Add relevant topics to improve categorization

    Why:

    COPY-PASTE FIX
    clickhouse, ai-assistants, llm-tools, database-connector, sql-agent, data-access, mcp-server, generative-ai
  • mediumhomepage#3
    Add a homepage URL

    Why:

    COPY-PASTE FIX
    https://pypi.org/project/mcp-clickhouse

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 ClickHouse/mcp-clickhouse
Avg rank
—
Lower is better. #1 = top recommendation.
Share of voice
0%
Of all named tools, what % are you?
Top rival
LangChain
Recommended in 2 of 2 queries
COMPETITOR LEADERBOARD
  1. LangChain · recommended 2×
  2. LlamaIndex · recommended 2×
  3. Hugging Face Transformers · recommended 2×
  4. OpenAI Function Calling · recommended 2×
  5. DB-GPT · recommended 2×
  • CATEGORY QUERY
    How can I enable my AI assistant to query and retrieve data from a relational database?
    you: not recommended
    AI recommended (in order):
    1. LangChain
    2. LlamaIndex
    3. Hugging Face Transformers
    4. Salesforce/codet5-large-text-to-sql
    5. microsoft/picard-large
    6. SQLAlchemy
    7. JDBC
    8. ODBC
    9. PostgreSQL JDBC Driver
    10. MySQL Connector/J
    11. ADO.NET
    12. Npgsql
    13. MySql.Data
    14. OpenAI Function Calling
    15. DB-GPT

    AI recommended 15 alternatives but never named ClickHouse/mcp-clickhouse. This is the gap to close.

    Show full AI answer
  • CATEGORY QUERY
    What tools allow AI agents to execute SQL queries and inspect database schemas?
    you: not recommended
    AI recommended (in order):
    1. LangChain
    2. LlamaIndex
    3. SQLCoder
    4. OpenAI Function Calling
    5. Hugging Face Transformers
    6. DB-GPT
    7. Microsoft Semantic Kernel

    AI recommended 7 alternatives but never named ClickHouse/mcp-clickhouse. 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 ClickHouse/mcp-clickhouse?
    pass
    AI named ClickHouse/mcp-clickhouse explicitly

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

  • If a team adopts ClickHouse/mcp-clickhouse in production, what risks or prerequisites should they evaluate first?
    pass
    AI named ClickHouse/mcp-clickhouse 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 ClickHouse/mcp-clickhouse solve, and who is the primary audience?
    pass
    AI named ClickHouse/mcp-clickhouse 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 ClickHouse/mcp-clickhouse. 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/ClickHouse/mcp-clickhouse.svg)](https://repogeo.com/en/r/ClickHouse/mcp-clickhouse)
HTML
<a href="https://repogeo.com/en/r/ClickHouse/mcp-clickhouse"><img src="https://repogeo.com/badge/ClickHouse/mcp-clickhouse.svg" alt="RepoGEO" /></a>
Pro

Subscribe to Pro for deep diagnoses

ClickHouse/mcp-clickhouse — 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