Feason Context

Official registry AI and agents

Christian source evidence for AI agents, with provenance, tradition coverage, and citation checks.

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

Remote (streamable-http)
Claude Code
claude mcp add --transport http feason-context 'https://www.feason.com/api/mcp'
JSON configuration (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "feason-context": {
            "type": "http",
            "url": "https://www.feason.com/api/mcp"
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. Feason Context SDKs
  2. Included
  3. TypeScript
  4. Python
  5. Development
  6. Distribution
  7. Security
  8. License

Feason Context SDKs

Typed, dependency-free TypeScript and Python clients for the Feason Context REST API, plus its OpenAPI 3.1 contract.

Feason Context supplies source-grounded Christian research material with exact passages, provenance, stable citations, named tradition coverage, and explicit coverage boundaries. Applications decide how to use the returned evidence.

Included

  • typescript/ — @feason/context
  • python/ — feason-context
  • openapi/feason-context-openapi.yaml — the public REST contract
  • contract.json — versioned endpoint metadata used to generate both clients
  • server.json — official MCP Registry metadata for the hosted remote server
  • DIRECTORY_LISTING.md — reusable, boundary-aware MCP directory copy

The hosted service remains at https://www.feason.com. These clients do not contain the Feason corpus, production credentials, user data, retrieval engine, or server implementation. Tokens are accepted at runtime and are never persisted.

TypeScript

import { FeasonContextClient } from "@feason/context";

const client = new FeasonContextClient({ token: process.env.FEASON_CONTEXT_TOKEN! });
const packet = await client.evidencePacket({ question: "How did early Christians describe grace?" });
console.log(packet);

Python

import os
from feason_context import FeasonContextClient

client = FeasonContextClient(os.environ["FEASON_CONTEXT_TOKEN"])
packet = client.evidence_packet("How did early Christians describe grace?")
print(packet)

Development

node scripts/generate-clients.mjs --check
npm --prefix typescript install
npm --prefix typescript run build
npm --prefix typescript test
python3 -m unittest discover -s python -p 'test_*.py'

Distribution

The SDK package names are reserved in their manifests but are not advertised as publicly installable until their registry records are verified. See PUBLISHING.md for the release preflight and verification sequence.

The hosted MCP service is described separately by server.json. Directory descriptions should preserve Feason's evidence-layer boundaries; see DIRECTORY_LISTING.md.

Security

Do not place API tokens in source, examples, issues, or test fixtures. See SECURITY.md for private vulnerability reporting.

License

MIT. See LICENSE.

Frequently asked questions

What is Feason Context?

Christian source evidence for AI agents, with provenance, tradition coverage, and citation checks.

How do I install Feason Context?

It runs as a remote server. In Claude Code: claude mcp add --transport http feason-context 'https://www.feason.com/api/mcp'. For other clients, paste the JSON configuration from this page into their MCP settings.

Does Feason Context need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is Feason Context open source?

Yes. Its code is on GitHub under the MIT license.

Who maintains Feason Context?

It is published by Feason-com. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.