Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Useful for any developer or researcher who wants their local or hosted agent to do real web research with grounded sources (not 'here is what the LLM guessed') without depending on a hosted search API. The MCP surface is the right shape — search, crawl, rerank, extract, return a source-grounded prompt — so the calling agent sees a single tool call instead of a five-step shell pipeline. SearXNG by
Who should use it
Who should skip it
Consider MarcellM01/TinySearch lower priority if you already have a working solution in this category.
About this signal
MarcellM01/TinySearch is tracked by RepoRadar as a self-hosted web research mcp for in the MCP Servers section. It was first seen on 2026-07-04 and last updated on 2026-07-04. The current verdict is 'try now' with a Silver tier and easy setup difficulty. MarcellM01/TinySearch leads on workflow potential (9.1) and setup ease (8.8); its lowest signal is maturity (5.6), so factor that in before investing setup time. This page summarizes the evidence RepoRadar has captured from captured source metadata. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned MarcellM01/TinySearch a composite score of 7.6 out of 10, placing it in the Silver tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 1.0 and never affects the composite score or tier. The risk label of 'low' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
Risk label is still being reviewed from the captured evidence. Treat the item as unknown-risk until you review the linked source, permissions, setup path, and data access.