Open Primitive
26 US federal data domains as 23 MCP tools. Ed25519 signed responses. Free, no API key.
README
Open Primitive Protocol (OPP)
The data layer of the agent internet.
OPP defines how data providers make their data agent-consumable, verifiable, and discoverable. Three components: provider manifest, response envelope, query interface.
The Problem
Agents get data naked. No provenance. No freshness guarantee. No confidence score. No way to verify the source. The agent internet is missing its data envelope.
The Protocol
| Component | What it does |
|---|---|
Manifest (/.well-known/opp.json) |
Declares what data a provider serves, how fresh it is, how to verify it |
| Response Envelope | Every response carries domain, source, freshness, confidence, citation, Ed25519 signature |
| Query Interface | Standardized HTTP GET endpoints with predictable parameters |
Conformance Levels
- Level 1 (Basic): Manifest + envelope with domain/source/freshness
- Level 2 (Cited): Level 1 + confidence scores + citations
- Level 3 (Verified): Level 2 + Ed25519 cryptographic proof
Reference Implementation
Live at api.openprimitive.com. 16 US federal data domains across 11 agencies. Level 3 compliant — every response is signed.
curl https://api.openprimitive.com/v1/drugs?name=aspirin
# Returns OPP envelope with proof.type: "DataIntegrityProof"
Quick Start
Use data from an OPP provider:
const res = await fetch('https://api.openprimitive.com/v1/drugs?name=aspirin');
const data = await res.json();
console.log(data.citations.statement);
// "According to FDA FAERS, aspirin has 601,477 reported adverse events"
Implement OPP for your own data:
// 1. Create /.well-known/opp.json (see spec)
// 2. Wrap responses in the OPP envelope
// 3. Optionally sign with Ed25519
Specification
Full spec: openprimitive.com/protocol.html
Detailed spec: api.openprimitive.com/spec.html
SDK
sdk/opp-client.js— Client library for consuming OPP providerssdk/opp-provider.js— Helper for implementing OPPsdk/opp-validator.js— Validate OPP conformance
MCP Server
13 tools for Claude, Cursor, and MCP-compatible agents:
npx open-primitive-mcp
Links
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.