Neonia: The Cloud Backend for AI Agents
A cloud-hosted MCP gateway that solves context window bloat and tool rigidity through remote execution. Connects via streamable HTTP to expose JQ filtering for processing large JSON payloads without loading them into context, dynamic tool discovery so agents can search and bind capabilities on demand, and a dual memory system using neonia_sys_memory_note and neonia_sys_memory_search for persistent state across sessions. The repo includes working examples in LangGraph, SmolAgents, Vercel AI SDK, and Rig that demonstrate extracting values from multi-megabyte files while saving tens of thousands of tokens per request. Reach for this when you need stateful agents that remember preferences or when processing API responses that would otherwise blow your context budget.
- tools
- 5
- auth
- Secret needed
- transport
- HTTP
- last updated
- May 15, 2026
Tools
5 toolsPublic tool metadata for what this MCP can expose to an agent.
neonia_data_jq_filterWasm-powered JQ Filter tool that runs queries on the remote server and returns only the filtered result.
Wasm-powered JQ Filter tool that runs queries on the remote server and returns only the filtered result.
No parameter schema in public metadata yet.
neonia_web_json_fetchRetrieves remote JSON and stores it on the Gateway, returning a lightweight pointer.
Retrieves remote JSON and stores it on the Gateway, returning a lightweight pointer.
No parameter schema in public metadata yet.
neonia_sys_memory_noteWrites rules, custom personas or user preferences to Neonia's Dual Memory Architecture.
Writes rules, custom personas or user preferences to Neonia's Dual Memory Architecture.
No parameter schema in public metadata yet.
neonia_sys_memory_searchReads and recalls stored memory notes and lessons across sessions.
Reads and recalls stored memory notes and lessons across sessions.
No parameter schema in public metadata yet.
neonia_sys_memory_lessonSaves architectural lessons, bug fixes or operational rules in a cause-and-effect structure.
Saves architectural lessons, bug fixes or operational rules in a cause-and-effect structure.
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageReadme
Neonia Agent MCP Examples
A collection of autonomous agent examples demonstrating how to integrate the Neonia Model Context Protocol (MCP) Gateway using the official Streamable HTTP transport standard.
About These Examples
This repository will continuously grow with new patterns demonstrating deterministic, high-performance AI agents.
Our first major showcases focus on solving two critical problems in modern agent architectures: Context Window Bloat and Tool Rigidity.
1. Solving Tool Rigidity (Auto-Pilot Discovery)
Agents are traditionally hard-coded with a static list of tools. If a user asks for something outside that list, the agent hallucinates or fails. The auto-discovery-url-to-markdown examples demonstrate how to give your agents true autonomy. By connecting to the Neonia Gateway, the agent can dynamically search for missing capabilities, read the tool's schema, and execute it on the fly without human intervention.
2. Solving Context Bloat (Zero-Bloat Data Processing)
Details
- Repository
- github.com/neonia-io/agent-mcp-examples
- Website
- neonia.io
- Categories
- AI & LLM Tools, Data & Analytics
- Transport
- HTTP
- Auth
- Required
- Registry
- MCP registry, active
Related AI & LLM Tools MCP servers
View all
Levea Mcp Serverbrajendrak00068/agentic-ai-video-productionAutonomous AI video editor over MCP: viral clips, captions, reframe, chroma key, MP4 export0stars
PromptScancorporatelad/prompt-injection-firewallPrompt injection detection API for AI agents. Scan untrusted text before passing it to an LLM.0stars
MCP Knowledge Graphshaneholloman/mcp-knowledge-graphProvides a local knowledge graph memory store for AI models with master and named databases accessible via MCP tools.857stars
Agentmailrooms Mcpclauxel/agent-mail-rooms-mcpA paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage0starsGeminiupgradeqa Mcpclauxel/gemini-upgrade-qa-mcpRemote MCP for Gemini upgrade evals, prompt regressions, output diffs, and eval receipts.0starsByterovermemory Mcpclauxel/byterover-team-memory-mcpA paid remote MCP for OpenAI Codex memory MCP, built to return verdicts, receipts, usage logs, and a0stars