About Vector Search x402
Vector Search x402 is an in-memory text vector store for AI agents building RAG pipelines. It uses TF-IDF and cosine similarity, with searches paid per call in USDC on Base.
Key features
- 01In-memory text document storage
- 02TF-IDF vectorization
- 03Cosine similarity ranking
- 04Top-k results with scores
- 05Namespace-based document separation
- 06Pay-per-call with USDC on Base
Use cases
- 01Search stored text for relevant passages
- 02Retrieve context for a RAG pipeline
MCP support
An MCP endpoint exposes the data_vector_search tool to MCP clients. It accepts documents and a query, then returns ranked matches.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://vector-search.api.klymax402.com/mcpclaude mcp add --transport sse vector-search-x402 https://vector-search.api.klymax402.com/mcp{"mcpServers":{"vector-search-x402":{"type":"sse","url":"https://vector-search.api.klymax402.com/mcp"}}}Open in Cursor{"servers":{"vector-search-x402":{"type":"sse","url":"https://vector-search.api.klymax402.com/mcp"}}}Open in VS Code{"mcpServers":{"vector-search-x402":{"type":"sse","url":"https://vector-search.api.klymax402.com/mcp"}}}{"mcpServers":{"vector-search-x402":{"serverUrl":"https://vector-search.api.klymax402.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEVector Search API
In-memory vector store with TF-IDF vectorization and cosine similarity search. Pay-per-call via x402 (USDC on Base L2) -- no API key, no signup, no rate-limit wall.
Part of the klymax402 marketplace -- 100 x402 micropayment APIs for AI agents, one wallet, USDC on Base.
Quickstart -- MCP
Add to your MCP client config (Claude Desktop, Cursor, ElizaOS, etc.):
{
"mcpServers": {
"vector-search": {
"url": "https://vector-search.api.klymax402.com/mcp"
}
}
}
Quickstart -- HTTP (x402)
curl -X POST "https://vector-search.api.klymax402.com/api/search" \
-H "Content-Type: application/json" \
-d '{"query":"..."}'
# -> 402 Payment Required, with an x402 payment challenge in the response body
Any x402-aware client (@x402/fetch, x402-agent-tools, ATXP) handles the 402 -> sign -> retry cycle automatically.
Tools
| Tool | Method | Path | Price | Description |
|---|---|---|---|---|
data_vector_search | POST | /api/search | $0.012 | Store text and search by semantic similarity |
data_vector_search
Use this when you need to store text documents and search them by semantic similarity. Accepts documents to store and a query to search. Uses TF-IDF vectorization with cosine similarity to find the most relevant matches. Returns top-k results with similarity scores. Do NOT use for web search — use web_search_query instead. Do NOT use for keyword research — use keyword_research instead. Do NOT use for text classification — use text_classify instead.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
documents | array | no | Array of text documents to index (optional if already stored in this session) |
query | string | yes | The text query to search for |
topK | number | no | Number of top results to return (default: 3, max: 10) |
namespace | string | no | Namespace to isolate document sets (default: 'default') |
Example agent prompts
- "Store text documents and search them by semantic similarity"
Payment
- Protocol: x402 -- HTTP-native pay-per-call, no signup, no API key
- Network: Base L2 (
eip155:8453) - Asset: USDC
- Facilitator: Coinbase CDP (primary), PayAI (fallback)
Part of klymax402
100 x402 micropayment APIs for AI agents -- one wallet, USDC on Base, zero signup.
- Catalog: https://klymax402.com/llms.txt
- Full API reference: https://klymax402.com/llms-full.txt
- Live stats: https://klymax402.com/stats
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.