io.github.MarcellM01/tinysearch

tinysuite-search

Self-hosted web research for MCP agents.

236 6 tools GitHub PyPI

No known CVEs

MIT license

Actively maintained

Last commit 0d ago

Works with most clients

Transport: stdio, sse, http

6 tools · ~194 tok

Grade A · 0.1% of 200K ctx

MCPpedia last refreshed this data 19h ago

Edit this pageView history

io.github.MarcellM01/tinysearch is an MCP server that self-hosted web research for MCP agents. Its tool list has not been published yet over stdio, sse and http, requires no API key, and scores 90/100 on MCPpedia's security, maintenance and efficiency rubric.

Other

Step 1

Install in your client

Config is the same across clients - only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "tinysearch": {
      "url": "http://localhost:8000/mcp"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/io-github-marcellm01-tinysearch)](https://mcppedia.org/s/io-github-marcellm01-tinysearch)

Read me

What io.github.MarcellM01/tinysearch does

Self-hosted web research for MCP agents.

Test This Server

This server supports HTTP transport. Be the first to test it - help the community know if it works.

Loading README…

Scored, not listed

Why this score

Five weighted categories - click any category to see the underlying evidence.

Score breakdown

90/100across 5 weighted dimensions

How we score →

0255075100

−10

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked tinysuite-search against OSV.dev.

Inventory

Tools (6)

Click any tool to inspect its schema.

~194 tokens total

Community

Reviews

Be the first to review

Have you used this server?

Share your experience - it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is io.github.MarcellM01/tinysearch safe to use?: io.github.MarcellM01/tinysearch has no known CVEs as of the latest MCPpedia security scan. Authentication requirements were not detected automatically - check the project's documentation before connecting in a shared environment. Licensed under MIT.
How do I install io.github.MarcellM01/tinysearch?: io.github.MarcellM01/tinysearch supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What can io.github.MarcellM01/tinysearch do?: io.github.MarcellM01/tinysearch provides 6 tools: chunk_semantic_dedupe_enabled, chunk_semantic_dedupe_threshold, Documentation, Development, Entrypoints and 1 more. See the full tools list on the server page for descriptions and parameters.
What AI clients work with io.github.MarcellM01/tinysearch?: io.github.MarcellM01/tinysearch is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is io.github.MarcellM01/tinysearch actively maintained?: io.github.MarcellM01/tinysearch is actively maintained - last commit was 0 days ago. It has 236 GitHub stars.

Similar servers

Others in other

View all →

io.github.vshulcz/deja-vu95

deja-vu: local memory over the session histories of forty-three coding agents.

1.5k 6

MCP Wordpress Remote95

MCP WordPress Remote proxy server

188 10

Argo95

专门为 agent 打造的 agent 搜索工具，具备多语言搜索能力，覆盖中文/英文/学术/代码/购物/金融/新闻/百科。

242 1

Football Docs94

Searchable football data provider documentation for AI coding agents. Like Context7 for football data.

226 8

MCP Security Weekly

Get CVE alerts and security updates for io.github.MarcellM01/tinysearch and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Highlights

No vendor in the loop. No TinySearch account, no required API key, no per-request billing, no analytics service or hosted scraped-data cache. DDGS search and local ONNX embeddings are the defaults.

Source-grounded by construction. A claim in your agent's answer traces back to one specific passage instead of stopping at "the vendor's model said this."

Selection happens before the model. Local BM25 and embedding rerank pick pages and passages within an evidence budget you control.

Five small MCP tools. search, scrape_urls, browser_navigate, browser_act and get_current_datetime, with batching so one call can cover independent subquestions.

A real browser when a page needs one. The browser tools reuse the scraper's Chromium, act only on elements the model has seen, and can't execute code.

Private by default. Nothing about what was searched is recorded unless you turn activity recording on, and OpenTelemetry export never carries queries, URLs or page text.

Bring your own stack when needed. SearXNG, Brave, OpenAI-compatible e

Frequently Asked Questions

Is io.github.MarcellM01/tinysearch safe to use?

io.github.MarcellM01/tinysearch has no known CVEs as of the latest MCPpedia security scan. Authentication requirements were not detected automatically - check the project's documentation before connecting in a shared environment. Licensed under MIT.

How do I install io.github.MarcellM01/tinysearch?

io.github.MarcellM01/tinysearch supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What can io.github.MarcellM01/tinysearch do?

io.github.MarcellM01/tinysearch provides 6 tools: chunk_semantic_dedupe_enabled, chunk_semantic_dedupe_threshold, Documentation, Development, Entrypoints and 1 more. See the full tools list on the server page for descriptions and parameters.

What AI clients work with io.github.MarcellM01/tinysearch?

io.github.MarcellM01/tinysearch is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is io.github.MarcellM01/tinysearch actively maintained?

io.github.MarcellM01/tinysearch is actively maintained - last commit was 0 days ago. It has 236 GitHub stars.

TinySearch

Spend tokens on answers, not webpages.

Part of TinySuite. Comes built in to TinyWebUI, and works with any MCP client.

TinySearch returning source-grounded web evidence to an AI agent

Read the documentation → tinysuite.dev/docs/tinysearch

TinySearch is the web-research layer of TinySuite, a set of small, local-first tools that make agents spend tokens on useful work rather than overhead. It searches the web, reads the best pages, removes low-value content, and returns compact evidence with source URLs, so your model receives the useful passages instead of paying to process entire webpages.

It is retrieval, not summarization: every returned chunk is the original page text, unedited and still attached to its URL, so what you cite is what the page actually said. In a benchmark against a plain search-then-fetch agent reading the same pages, it sent 64% fewer tokens to the model (docs/token-savings.md).

Highlights

No vendor in the loop. No TinySearch account, no required API key, no per-request billing, no analytics service or hosted scraped-data cache. DDGS search and local ONNX embeddings are the defaults.
Source-grounded by construction. A claim in your agent's answer traces back to one specific passage instead of stopping at "the vendor's model said this."
Selection happens before the model. Local BM25 and embedding rerank pick pages and passages within an evidence budget you control.
Five small MCP tools. search, scrape_urls, browser_navigate, browser_act and get_current_datetime, with batching so one call can cover independent subquestions.
A real browser when a page needs one. The browser tools reuse the scraper's Chromium, act only on elements the model has seen, and can't execute code.
Private by default. Nothing about what was searched is recorded unless you turn activity recording on, and OpenTelemetry export never carries queries, URLs or page text.
Bring your own stack when needed. SearXNG, Brave, OpenAI-compatible e

... View full README on GitHub