The agent-native knowledge API
The knowledge base your app and your AI agents share
Define a schema — FoxNose instantly generates the embeddings, the hybrid search index, and a Knowledge MCP server, all on one endpoint. Plug in Claude, ChatGPT, Cursor, or any agent framework — no Pinecone+Postgres glue, no hand-written tool catalog.
For support agents, product copilots, and internal knowledge assistants.
Works with any LLM, agent framework, or application
Building an AI agent over real data is a stack problem, not a model problem
Most teams shipping a vertical agent end up maintaining a vector DB, a primary store, a full-text index, an embedding pipeline, sync scripts, and a hand-written MCP server with tool definitions that drift every time the schema changes. FoxNose collapses all of it.
Five services, five bills, sync scripts to keep them consistent, and an MCP tool catalog that drifts.
Define a schema, get REST endpoints, a hybrid search index, and a Knowledge MCP — same auth, same data, no parallel surface to maintain.
Knowledge MCP, hybrid search, and multi-tenant isolation — built in
Knowledge MCP, auto-generated
The moment you define a schema, an MCP server is live at your API endpoint — 5 fixed tools, JSON Schema introspection, no glue code. Plug Claude, Cursor, or any agent directly into your data.
Hybrid Search API
Vector similarity, full-text matching, and structured filters fused server-side. Surfaced to the agent as a single search tool — no fan-out logic.
Auto-Embeddings
Mark fields as vectorizable. Embeddings generate on save. No embedding pipeline, no external API in your dataflow.
Multi-Tenant by Design
Collections + per-API connected scopes + per-Collection allowed methods. A Collection invisible to a key over REST is invisible over MCP too. Same model end to end.
Schema Versioning
Pin agents to a schema version, migrate the underlying schema, roll forward when prompts are ready. No "schema change broke production at 3am" surprises.
Audit Log & RBAC
30-day immutable event record. Granular roles for content, environments, and Flux APIs. Debug what your AI retrieved and when.
One knowledge base, many AI use cases
Build RAG pipelines, power AI-native content, give agents persistent memory, or use it as the knowledge backend for any AI product.
Build RAG Apps
Production RAG pipeline without managing vector databases, embedding APIs, or sync scripts. Python and JavaScript SDKs included.
Headless CMS for AI
A headless CMS with built-in vector search, auto-embeddings, and LangChain integration. A Contentful alternative with AI native search.
AI Agent Memory
Persistent knowledge base for AI agents. Read-write API, schema versioning, and native LangChain agent tools. A Pinecone alternative that simplifies the stack.
LLM Database
The knowledge backend for AI applications. Structured storage with built-in search, auto-embeddings, and multi-tenant isolation.
One API from schema to search
Define your data model, store records, and query with hybrid search. Auto-embeddings and indexing happen behind the scenes.
# mcp config — Claude Code, Cursor & other HTTP MCP clients
# (stdio-only clients such as Claude Desktop connect via mcp-proxy)
{
"mcpServers": {
"foxnose-support": {
"type": "http",
"url": "https://<env_key>.fxns.io/support/_mcp",
"headers": {
"Authorization": "Simple <public_key>:<private_key>"
}
}
}
}
# → 5 tools instantly available:
# discover_resources · describe_resource · query_records · get_record · search_records
# Same auth as REST. Same data. No tool catalog to hand-write. Define a schema in the dashboard. A Knowledge MCP server appears at /<prefix>/_mcp over Streamable HTTP — auto-generated, no server to deploy. Works with Claude Code, Claude Desktop, OpenAI Responses API, Cursor, Cline, Continue, and any MCP-aware client. How it works →
From signup to your first MCP query
Sign up. Define a schema. Connect a Flux API. Drop the MCP server URL into Claude or Cursor. That's the whole setup.