Server data from the Official MCP Registry
Collaborative, cache-first web search for agents — cited answers from a shared live-web pool.
Collaborative, cache-first web search for agents — cited answers from a shared live-web pool.
Remote endpoints: streamable-http: https://aimnis.com/mcp
Valid MCP server (3 strong, 4 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.
Endpoint verified · Requires authentication · 1 issue found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
This plugin requests these system permissions. Most are normal for its category.
Remote Plugin
No local installation needed. Your AI client connects to the remote endpoint directly.
Add this to your MCP configuration to connect:
{
"mcpServers": {
"io-github-aimnis-search": {
"url": "https://aimnis.com/mcp"
}
}
}From the project's GitHub README.
Search once. Answer everyone. An open-source, cache-first web-search gateway for coding agents: ask a question and get a distilled, source-cited answer instantly from a shared, always-current knowledge pool — so every search makes the pool smarter and cheaper for everyone. Like RAG, but over a communal live-web pool, not your stale private docs.
Status: public preview. The hosted service is live — get a free eval key at aimnis.com and point your agent at it in one minute (per-agent setup). We're proving one thing in public — that the cache hit rate compounds as the pool grows (the flywheel, live dashboard). Follow along.
Every model has a training cutoff. The moment it ships, the world moves on — new library versions, new APIs, new errors — and the model can't keep up without searching the live web on every question. That's slow, expensive, and per-vendor.
Aimnis is the shared, always-current layer in front of that: the first thing an agent checks. Ask a question; if it (or a semantically similar one) has been asked before, you get a distilled, source-cited answer instantly for near-zero cost. If it hasn't, Aimnis fetches it live, distills it, and adds it to the pool — so the next agent to ask gets it free. The corpus captures what happened after every model's cutoff, which no static training set can.
query
└─ scrub secrets/PII (redacted before embed, search, distill, or storage)
└─ local embed + normalize
└─ semantic cache lookup (exact hash → vector nearest-neighbour)
├─ HIT → return the pooled, cited answer instantly (no upstream cost)
└─ MISS → live search → distill into a cited answer → quality-gate → pool it
[n] citations back to sources — not raw links. The answer is
AI-generated (a model distills the sources) and labeled as such in the tool
output, so the agent always knows it's reading a machine-written summary./r/… redirect that logs
which pooled answer earned a follow-through, then forwards to the source — this
is how click-through improves ranking. The source's real host is shown inline so
the agent still sees where it's going, and the log records only entry + source +
host + time — never IP, user-agent, or any user/session id. It's telemetry on
the pool, not on you. It's off unless a signing secret is configured, tokens are
HMAC-signed (so /r can't be abused as an open redirector), and self-hosting
points the redirect at your own gateway — so clicks stay on your box.The one metric that decides whether this works: cache hit rate vs. corpus size. If it climbs as the pool grows, the thesis holds. It's public from day one — trust, made measurable.
# run the live dashboard locally (see Quickstart)
aimnis-dashboard # → http://127.0.0.1:8080 (hit-rate curve, corpus size, storage)
Aimnis speaks MCP, so any MCP-capable agent can use it as its web-search tool. The hosted endpoint means nothing to install:
URL: https://aimnis.com/mcp (MCP, streamable HTTP)
Header: Authorization: Bearer aim_YOUR_KEY
Claude Code
claude mcp add --transport http aimnis https://aimnis.com/mcp \
--header "Authorization: Bearer aim_YOUR_KEY"
Then, to make the model prefer Aimnis over the built-in tool, deny WebSearch in
.claude/settings.json:
{ "permissions": { "deny": ["WebSearch"] } }
OpenCode, OpenClaw, Hermes, Pi, REST — copy-paste snippets at
aimnis.com/setup and in docs/mcp.md,
plus the search / stats tool reference. Bring your own OpenRouter/search keys
at registration and your cache misses run on your quota — with much higher limits.
Self-hosting instead? The same MCP server runs locally over stdio against your own
pool — see Quickstart and docs/mcp.md.
cd server
docker compose up -d # Postgres+pgvector (:5432)
# want the keyless search path too? add SearXNG (:8888):
# docker compose --profile keyless up -d
uv venv .venv && . .venv/bin/activate
uv pip install -e ".[dev]" # editable install (required — see docs)
python -m aimnis.migrate # apply migrations/*.sql
cp .env.example .env # then fill in keys if you have them
pytest # full suite against the compose DB
No OpenRouter key? Fine — Aimnis runs keyless (via SearXNG) and returns raw cited
snippets, spending zero upstream quota. Add AIMNIS_OPENROUTER_API_KEY to turn on
distillation. Live search is an ordered fallback chain — Brave → Tavily → Exa →
SearXNG — so setting any of AIMNIS_BRAVE_API_KEY / AIMNIS_TAVILY_API_KEY /
AIMNIS_EXA_API_KEY gives more reliable results, and a free tier that runs dry
rolls onto the next automatically. See server/README.md for
the component map.
The code is open. The corpus is a curated compilation, licensed as such.
| Part | License |
|---|---|
Server core (server/) | AGPLv3 — network copyleft; run a modified service, share your changes |
SDKs & MCP client (clients/) | Apache-2.0 — embed anywhere, including commercial products |
| Public knowledge-pool pages | CC-BY-NC 4.0 applies to our compilation (curation, structure, presentation) |
On the pool's contents, honestly: pooled answers are distilled by third-party models from third-party web results. We don't claim ownership of the underlying facts or of upstream model outputs — CC-BY-NC covers our compilation, and any reuse also remains subject to the terms of the original sources and the model providers. Some provider outputs are excluded from redistribution and from any future training-data feed wherever provider terms require it, and provider-mandated attributions are carried through. A training-data feed is out of scope until the flywheel is proven (see roadmap) — this repo makes no offer to license training data.
Anti-abuse thresholds (scrubbing/dedup/quality tuning) ship with safe example defaults; production values are injected at deploy and are not part of this tree — so publishing the ruleset doesn't hand it to poisoners.
Gated roadmap, Gate 0 → Gate 4. Gate 0 complete (ToS audit, niche, naming, licensing locked). Gate 1 in progress — gateway + semantic cache + public flywheel dashboard are built and dogfooded; the pass/kill test is the hit-rate curve bending upward. Ads, billing, community compute, and the training-data feed are explicitly out of scope until the flywheel is proven.
Be the first to review this server!
by Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
by Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
by Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.