Andi Search MCP server
Real-time web search and page fetch for AI agents from Andi's own index. LLM-ready markdown output.
C67/100grade C
Adoption
New
Little public usage data yet
Reviews
Write oneNobody has reviewed Andi Search yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Andi Search tools
Tool list not cached yet. `describe` through the gateway fetches it live.
Public scan report
scanner v0.1.9 · 2026-09-23 · same rubric, same numbers if you re-run it
1 low
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 380ms (auth required)20/20
- –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
- Auth qualityOAuth resource metadata advertised on 40115/15
- Maintenanceno repository listed3/15
- Maintainer identityno repository or website to verify2/10
Findings (1)
- lowNo source repository listed
maint.no-repo
Overall 67/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON
Install directly
claude mcp add --transport http andi-search https://api.andiai.com/mcp
Andi Search: common questions
- Is Andi Search MCP server safe?
- With care: it is graded C, so read the findings first (67/100). Read the Andi Search safety report
- How do I install Andi Search?
- It runs remotely at api.andiai.com. Add it to Claude Code, Claude Desktop or Cursor with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Andi Search need an API key?
- No key to paste: it signs you in with OAuth when your client connects.
- Is Andi Search maintained?
- The latest release is v1.0.0.
- Is Andi Search up?
- 100% of our last 20 checks got an answer. We check remote servers about four times a day.
- What can I use instead of Andi Search?
- Servers from other publishers that do the same job: Basic Memory MCP server, IWE MCP server and llmtrim MCP server. Compare all Andi Search alternatives.
Alternatives to Andi Search
Same job from other publishers: the closest match first, then the best rated.
- Basic MemoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.not reviewedEstablishedC
- IWEMarkdown knowledge base as agent memory. Runs against the notes directory it is started in.not reviewedEstablishedA
- llmtrimMCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.not reviewedEstablishedA
- Google SurfWeb, academic and code search with graph RAG, data lineage, ontology and cross-project schema links.not reviewedEstablishedB
- PDFAgentic RAG over one PDF or a whole folder: hybrid search, selective page reads, tables, OCR.not reviewedEstablishedA