Feason Context SDKs
MCP serverAI & modelsYour AI can ground its answers about Christian topics in real source evidence instead of unsupported claims. Every source comes with provenance, coverage across Christian traditions, and checks that citations actually match what they point to. That means answers you can trace back to the texts and traditions behind them.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding it, ask your AI a question about a Christian teaching or text and request sources for the answer. Ask it to show where each point comes from to see the provenance for yourself.
Then ask your AI: use Feason Context SDKs
What your AI can do with it
- Answer questions about Christian teachings with supporting source evidence
- Trace each claim back to its original source through provenance details
- Draw on sources across multiple Christian traditions
- Verify that citations match the sources they reference
From the project's README
As published by feason-com/feason-context in README.md.
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/contextpython/—feason-contextopenapi/feason-context-openapi.yaml— the public REST contractcontract.json— versioned endpoint metadata used to generate both clientsserver.json— official MCP Registry metadata for the hosted remote serverDIRECTORY_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.
Signals
- Last commit
- Sep 2026
Advanced
- Delivery
- context MCP server → your ahel gateway (mcp.ahel.ai) → every connected AI client.
- Catalog kind
- mcp-server
- Gateway key
io-github-feason-com-context- Source
- github.com/feason-com/feason-context
- Hosted endpoint
https://www.feason.com/api/mcp