Is the potatosearch MCP server actively maintained?

The potatosearch MCP server was last committed 1d ago and has 1 contributor. Issue health: 50% of issues resolved. AgentRank freshness score reflects real-time maintenance activity.

potatosearch MCP Server

Name: jacobsee/potatosearch
Rating: 3.1 (1 reviews)
Author: jacobsee

jacobsee/potatosearch

Score: 51.4 Rank #77 MCP Server

Are you the maintainer of jacobsee/potatosearch? Claim this listing →

Vector document search system & MCP server for potato hardware and real people

Add AgentRank to Claude Code Discover and compare tools like jacobsee/potatosearch — your AI finds the right one automatically

Get API Access →

claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

jacobsee/potatosearch is a Python MCP server licensed under AGPL-3.0. Vector document search system & MCP server for potato hardware and real people

Ranked #77 out of 124 indexed tools.

Actively maintained with commits in the last week.

Ecosystem

Python AGPL-3.0

Score Breakdown

Stars 15% 1

1 stars → early stage

Freshness 25% 1d ago

Last commit 1d ago → actively maintained

Issue Health 25% 50%

No issues filed → no history to score

Contributors 10% 1

1 contributor → solo project

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A

PyPI Downloads N/A

Forks 0

Description Good

License AGPL-3.0

Weights: Freshness 25% · Issue Health 25% · Dependents 25% · Stars 15% · Contributors 10% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Contributors medium impact

Single-contributor projects carry bus-factor risk — welcoming contributors boosts confidence

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

Markdown

[![AgentRank](https://agentrank-ai.com/api/badge/tool/jacobsee--potatosearch)](https://agentrank-ai.com/tool/jacobsee--potatosearch/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)

HTML

<a href="https://agentrank-ai.com/tool/jacobsee--potatosearch/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/badge/tool/jacobsee--potatosearch" alt="AgentRank"></a>

Embed Widget docs →

HTML

<script src="https://agentrank-ai.com/embed.js" data-tool="jacobsee/potatosearch"></script>

Details

Stars: 1
Forks: 0
Open Issues: 0
Closed Issues: 0
Contributors: 1
Dependents: —
Language: Python
License: AGPL-3.0
Last Commit: 1d ago

Matched Queries

"mcp server""mcp-server"

From the README

# potatosearch

Vector document search system & MCP server for potato hardware and real people - just deploy, ingest, and use.

Respects your system resources by only embedding vectors and lightweight locators back to the original source files, instead of duplicating all content into the vector database. Additionally supports IVF-PQ indexing for further reducing footprint and speeding up searches.

Currently supports ZIM archives, PDF, Microsoft Office, and ODF formats for ingestion.

## Why?

Standard vector databases store the embedding vector **and** the full source text together. If your source corpus is, for example, a few hundred GB of compressed text, the vector DB decompresses and duplicates everything, quickly ballooning to multiple terabytes. If you avoid this by using them in bring-your-own vector mode, you have to manage it all yourself.

potatosearch stores only:

- The embedding vector (compressed via FAISS Product Quantization)
- A document locator: `(backend_name, locat

Read full README on GitHub →