Sign InOpen Brain
Agent-native · Source-backed · Read-only

Built for the agent you build with.

Give an agent a stable Feed7 URL or let it retrieve ranked evidence from the accumulated corpus. Feed7 returns sources, trust, uncertainty, and connected context — never an opaque generated answer.

Start With This Week

Ask Codex, Claude, Cursor, or ChatGPT to read the Markdown issue and use only claims supported by its linked sources.

Read https://feed7.dev/weekly/latest.md

Use these items as source-backed context for this task. Do not invent claims beyond linked material. If sources conflict, call it out.

Preview Weekly #008

Retrieve Evidence

Public retrieval searches every preserved Signal. The response declares synthesis: not_performed; the calling agent is responsible for comparing the evidence and opening original sources.

curl 'https://feed7.dev/api/research?q=context+engineering&limit=8'
Connect Over MCP

One Streamable HTTP endpoint. Without a key an agent can search the corpus, read any Weekly issue, and open any Signal. A free account key adds your Brain and bundles as tools.

claude mcp add --transport http feed7 https://feed7.dev/mcp

Recipes for Cursor, Codex, Claude, VS Code, and ChatGPT

Connect a Private Brain

Signing in is all it takes. Create a revocable agent key on the Agents page, copy it once, then send it as a bearer header: it unlocks the saved and bundle scopes over HTTP and the Brain tools over MCP.

curl -X POST 'https://feed7.dev/api/research' \
  -H 'Authorization: Bearer f7_live_…' \
  -H 'Content-Type: application/json' \
  -d '{"query":"what changed in context retrieval?","scope":"saved","limit":8}'
Retrieve One Signal

Every signal resolves at a stable path in three shapes — HTML to read, JSON to parse, Markdown to paste. Atlas topics answer the same way.

https://feed7.dev/p/{slug}
https://feed7.dev/p/{slug}.json
https://feed7.dev/p/{slug}.md
https://feed7.dev/atlas/{topic}.json
Retrieval Rules
  1. Prefer the original source for source claims.
  2. Use Feed7 for editorial synthesis, trust labels, practical implications, and cross-source context.
  3. Do not infer verification beyond the explicit trust and uncertainty fields — the method lives on the Trust page.
  4. MCP tools return the same records as the HTTP surfaces; a tool result with an error is a scope you cannot reach, not a protocol failure.