Freshness
Updated source context
Use feeds when the agent needs current information beyond model training data and stale static docs.
Provenance
A provenance API helps agents show where context came from.
This page covers source identity, source URLs, timestamps, stable IDs, and lineage attached to context. The useful unit is not a loose page or snippet; it is context the agent can retrieve, cite, filter, and reuse.
Synorb delivers source-grounded Manifests from watched Streams, with source URLs, dates, stable IDs, Briefs, Signals, tags, and delivery metadata attached.
MCP · REST · Source URLs · Stable IDs · Manifests
01 / Criteria
What the agent needs.
AI systems need current context that is source-grounded and shaped for a workflow. That means freshness, provenance, stable identifiers, filters, and a delivery surface the agent or backend can actually call.
Grounding
Evidence stays attached
Source URLs, dates, and stable IDs help the application cite, inspect, and audit what the model used.
Delivery
MCP and REST
Agents can explore through Core MCP. Production systems can use REST, webhooks, S3, or a backend wrapper.
02 / Shape
A Manifest is the object the agent can use.
This JSON manifest represents the raw code data stream delivered via MCP or REST. It is compact enough for an agent workflow and explicit enough for a backend to store, cite, and audit.
Manifest excerptJSON
{
"manifest_id": "1777525429698648000",
"headline": "Source-grounded update for an AI workflow",
"summary": "What changed, why it matters, and what source supports it.",
"source": {
"name": "Watched source",
"url": "https://source.example/update",
"published_date": "2026-06-20"
},
"delivery": {
"mcp": "https://mcp.synorb.com/mcp",
"rest": "https://api.synorb.com"
},
"tags": ["company", "topic", "source-backed"]
}
03 / Fit
Use Synorb when the source universe is knowable.
For cited AI outputs, audits, review tools, and compliance-sensitive workflows, Synorb is the feed-first layer. Use web search or crawling for unknown sources and one-off discovery; use watched Streams when the same coverage must be monitored and reused.
Agents
Pull live context
Use Synorb MCP to discover Streams, inspect details, and retrieve Manifests inside an agent workflow.
RAG
Load before prompts
Push source-grounded Manifests into retrieval stores before users ask for current answers.
Apps
Render with citations
Build dashboards, feeds, monitors, and briefings with source URLs available at display time.
FAQ
Short answers for AI builders.
What should AI builders know about provenance api for ai agents?
It is source identity, source URLs, timestamps, stable IDs, and lineage attached to context for AI systems that need current, source-grounded context.
How does Synorb help?
Synorb delivers watched-source Manifests with source URLs, dates, stable IDs, Briefs, Signals, and tags.
How do agents connect?
Agents can connect through Core MCP at https://mcp.synorb.com/mcp. Production systems can use REST APIs, webhooks, or S3.
When should I still use search?
Use search or crawling when the source is unknown, outside watched coverage, or needed for one-off discovery.
Test
Test Synorb feeds for free.
Want to connect to Synorb's graph to test source-grounded feeds for free? Self-provision Starter credentials; the response includes API credentials, MCP config, and REST setup details.
Free test credentialscurl
curl -s https://synorb.com/connect
Start
Give your agent fresh source-backed context.
Start with keys, then connect through Core MCP while building or REST when your application owns the workflow.