About QuantJourney API MCP
QuantJourney API MCP is a remote MCP server for research agents that exposes provider and financial-domain API tools. This repository contains public discovery contracts and OAuth integration examples, not the server implementation.
Key features
- 01Provider and financial-domain API tools
- 02Bounded-query OpenAPI contract
- 03OAuth-protected remote endpoint
- 04Free and x402-paid operations
Use cases
- 01Discover available API operations
- 02Run a bounded company snapshot query
- 03Register an OAuth client for a workload
- 04Integrate a research agent with the remote service
MCP support
Publishes an OAuth-protected remote Streamable HTTP MCP server at `https://api.quantjourney.cloud/mcp`. The repository provides its registry metadata and OAuth discovery information, but not the server source.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.quantjourney.cloud/mcpclaude mcp add --transport http quantjourneyorg-qj-api https://api.quantjourney.cloud/mcp{"mcpServers":{"quantjourneyorg-qj-api":{"type":"http","url":"https://api.quantjourney.cloud/mcp"}}}Open in Cursor{"servers":{"quantjourneyorg-qj-api":{"type":"http","url":"https://api.quantjourney.cloud/mcp"}}}Open in VS Code{"mcpServers":{"quantjourneyorg-qj-api":{"type":"http","url":"https://api.quantjourney.cloud/mcp"}}}{"mcpServers":{"quantjourneyorg-qj-api":{"serverUrl":"https://api.quantjourney.cloud/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 READMEQuantJourney Agent Integrations
Public discovery contracts and minimal client examples for the QuantJourney
Agent Fabric. The production service is available at
agents.quantjourney.cloud.
This repository is intentionally not the Agent Fabric server source. It contains only material required to discover and integrate with the public machine interfaces. Backend implementation, deployment configuration, credentials, operational data, and private architecture remain in private repositories.
Public machine contracts
- Agent Card
- Bounded-query OpenAPI
- Agent instructions
- Query catalogue
- Pricing and payment modes
- Current release
Generic A2A task delegation is currently disabled. Use the bounded query operations published in OpenAPI. Each operation declares whether it is free or x402-paid; discovery and OAuth registration are free.
Minimal OAuth query
The examples create one short-lived OAuth client with only agents:query,
obtain a 15-minute bearer token, call the free bounded company snapshot, and
deactivate the client in a finally/trap cleanup.
./examples/curl/oauth-query.sh AAPL
python3 examples/python/query.py AAPL
The shell example requires curl and jq. Neither example writes the client
secret or access token to disk. Production integrations should register one
durable client per workload, store its secret in a secret manager, rotate it,
and avoid registering a new client for every query.
Remote MCP server
QuantJourney publishes the OAuth-protected QJ API MCP as a remote Streamable HTTP server:
| Server | Remote endpoint | Purpose |
|---|---|---|
| QuantJourney API MCP | https://api.quantjourney.cloud/mcp | Provider and financial-domain API tools for research agents. |
The registry manifest is in registry/. OAuth metadata is
discovered from the protected resource; no QuantJourney service credential is
embedded in this repository.
Security
Do not commit client secrets, bearer tokens, payment signatures, prompts, or query results. See SECURITY.md for private vulnerability reporting guidance.
License
The public integration examples and registry metadata in this repository are licensed under Apache License 2.0. This license does not grant access to, or rights in, QuantJourney data, commercial services, private source code, or third-party datasets.
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.