Syndu is one platform with three access surfaces: direct access for report-shell consumption, API access for application-side scoring, and MCP access for agent collaboration. They sit under the same workspace, quota, and subscription control plane, but differ in delivery contract.
Direct access is the live report-shell mode. Analysts, automation systems, AI agents, and scraping stacks can work from the canonical report pages directly, with signed-in usage metered to the workspace by default. Customers can still widen that contract through IP, subnet, CIDR-range, and web-key provisioning when they want anonymous traffic or a broader network to resolve into the same workspace.
The API mode narrows Syndu into workspace-scoped, key-authenticated endpoints for customers that want a programmable response instead of a full report shell, including fraud and merchant-risk systems that also need writeback.
The MCP mode turns Syndu into a hosted tool and hive-mind surface for agent workflows. Agents can read from the evidence graph, call the risk model, and contribute findings back into governed workspace memory for cyber, fraud, and abuse operations.
The same control plane, subscription state, and customer workspace govern all three modes. The platform difference is in the delivery contract, not in the ownership model: API and MCP are always workspace-bound, and direct access now behaves that way for identified users too, while anonymous network coverage remains an explicit add-on choice rather than the default assumption.
Best when humans, browser automation, or retrieval agents want the full report shell and all supporting drill paths.
Best when applications need a compact scoring object with matched dimensions, risk levels, and report links.
Best when agents need investigation tools, risk explanation, and workspace memory on top of Syndu's evidence graph.
Syndu gives computer-using agents outside-in risk context and a governed memory loop. This index maps the supporting docs: plugin install, MCP workflows, the Risk API, pricing, privacy, and the evidence depth behind the system.
Syndu exposes a dimensional risk surface across network entities and geography: ip address, subnet, ISP, ASN, organization, city, region, and country. That same dimensional graph powers the Risk API, MCP tools, and the memory loop that preserves the resulting decisions.
Syndu is an external context layer for monitoring, hygiene review, agent workflows, and decision support. It complements SoC and SIEM processes rather than replacing them, while sharing the same evidence and memory model used elsewhere on the platform.
Syndu is also a decision surface for fraud, payments, merchant-risk, and trust workflows. The same outside-in evidence graph, Risk API, and governed memory loop help teams score, review, and preserve conclusions around risky identifiers.
The platform supports three access surfaces at scale: direct report access for large-scale browser or agent consumption, the Risk API for application-native scoring, and the MCP server for collaborative agent workflows.
Score risky IPs in real time, report lightweight business feedback, and push structured identifier outcomes back into workspace memory from the same authenticated API surface. Syndu keeps the contract simple: `score` is the metered read path, while `rate` and `report` are authenticated writeback endpoints that do not consume score quota. The score response now also carries a live community-signal block so applications can see whether analysts are converging on the same entity right now.
Registration unlocks the workspace control plane, plan selection, credential provisioning, and the subscription flow across web, API, and MCP access.
