Graphomics Developer Documentation
Graphomics builds the verified data layer for biological AI: curated knowledge graphs that ground an agent in source-linked biology instead of hallucinated output, and a platform that runs validated bioinformatics on your data behind your access controls, with every result written back as provenance.
These docs are for developers, bioinformaticians, and AI engineers who want to call Graphomics from their own environment — a Claude Code session, an agent framework, a notebook, or a service.
The fastest path in is MCP. Every core capability is exposed as agent-callable MCP tools, so you can wire Graphomics into an AI agent without building a client. Prefer REST? The knowledge graph is also a plain HTTP API. See the Quickstart.
The platform
Graphomics has two products that work over a network of knowledge graphs.
| Product | What it does | Reach it via |
|---|---|---|
| Operon | Your organization's private research platform: a grounded research agent, analysis steps and validated Nextflow pipelines, campaigns, and a decision record behind every result. | Your deployment |
| MapForge | Builds and extends knowledge graphs from biological data sources — inspect → map → review → emit, with a human approval gate. It builds MicroMap and each customer's Company Graph. | MCP tools · CLI |
MicroMap is the default knowledge graph every Operon deployment is connected to — a curated microbiome graph (taxa, diseases, metabolites, drugs, pathways, papers) built with MapForge, with a REST API, MCP tools, and a queryable graph schema. These docs cover calling MicroMap and MapForge from your own tools.
Why ground on Graphomics
- Curated, not scraped. The graph is built by MapForge with a human review gate — you're grounding on vetted associations, not model guesses.
- Validated execution. Operon runs analysis steps and Nextflow pipelines from an approved list, planned and approved before costly runs, with every run recorded.
- The loop closes. Analyses write back into the graph as confidence-scored, organization-scoped Assertions linked to the Decisions that produced them. Grounding and results live in the same provenance-tracked substrate. See Provenance & write-back.
- Behind your wall. Access is credentialed and organization-scoped; multi-tenant isolation is enforced at the platform layer.
Get started
- Get access — Graphomics is provisioned per organization; request access and you'll receive credentials and your endpoints.
- Connect over MCP — point your agent at the Graphomics MCP server and start calling tools.
- Call the REST API — query the knowledge graph directly over HTTP.
Reference
- API reference — base URL, authentication, conventions, and the full endpoint catalog.
- MCP tool reference — every agent-callable tool across the knowledge graph and MapForge.
- Schema reference — knowledge-graph labels, relationships, and the provenance contracts.