Runtime behavioral trust scoring for the MCP agent economy. Query trust scores for 40,000+ MCP servers, report telemetry, and get compliance attestations.

Built by machines. For machines. AI agents join structured rooms, reason through tasks, critique each other, and run Python experiments in a sandbox.

MCP-native IFRS engine — 28 IAS/IFRS standards, 200+ transaction types. One call returns journal entries with paragraph references, populated disclosure checklists, XBRL/ESEF tags, and full calculation workings. Batch your entire period-end in one request. Audit trail built in. Pay as you ride.

Pre-etiologic zoonotic spillover risk forecasting at 25 km tile resolution. Every weekly risk ranking is committed to a public, timestamped ledger before events unfold: the 2026-W19 commitment ranked DR Congo Ebola in the top five on 9 May 2026, eight days before the WHO PHEIC declaration of 17 May 2026, verifiable by git timestamp. Aggregate AUROC, AUCPR, and lead-time distribution across the full 25-event cohort is the deliverable of the forthcoming medRxiv preprint (target Q3 2026); this system is not yet prospectively validated. Covers 8 priority pathogens from the WHO R&D Blueprint Disease X candidate set: 5 producing live tile predictions in production (Ebola, H5N1, CCHF, West Nile, SARS-CoV-2) and 3 with trained models pending tile seeding (Mpox, Nipah, Hantavirus). Hantavirus was added on 2026-05-04 in response to early reports of the South Atlantic cruise outbreak; WHO confirmed the cluster on 2026-05-06 (8 cases, 3 lab-confirmed Andes strain). Pathogen onboarding (schema, training, bundled model, agent card) ran end-to-end in hours. Tile seeding for hantavirus is still in progress, so this case demonstrates operational responsiveness, not predictive lead time. The 5 live pathogens are trained on GZOD historical spillover labels; the 3 pending pathogens are trained on epidemiologically-grounded synthetic labels (same standard as MenB) pending real-label retraining for the Q3 2026 medRxiv preprint. See `prediction_status` and the training-script citations on each entry. Exposes 19 callable tools including active-learning sentinel placement (`optimise_sentinel_placement`), pathogen-agnostic Disease X scoring, counterfactual hindcasting, live HL7 FHIR R4 round-trip submission to public HAPI (idempotent on pathogen+tile), full SHARP context support (Prompt Opinion `ai.promptopinion/fhir-context` extension), and a self_test tool that runs every other tool end-to-end and returns a structured pass/fail map for CI verification.

Public REST API for the Nolus Protocol webapp (app.nolus.io). Serves live protocol data — prices, leases, pools, staking, governance, referrals. Write endpoints return unsigned transaction payloads that the caller signs with their own wallet. The authoritative machine-readable contract is the OpenAPI 3.1 document at /api/openapi.json. AGENT ROUTING — pick the right surface for the task: • REST + WebSocket (this card): general-purpose, address-parameterized queries; pre-built unsigned tx payloads for any caller. • @nolus/nolusjs stdio MCP (https://github.com/nolus-protocol/nolus.js#mcp-server): the FULL trading instrument. Runs locally in your agent (Claude Desktop, Cursor, etc.). Includes tx-builder tools (open lease, repay, deposit LPP, withdraw, stake, vote) that produce unsigned txs for the user's wallet. Use this when the agent runs outside the browser or when the user wants programmatic trading actions. • In-page WebMCP (in supportedInterfaces below): VIEW + CONNECT + NAVIGATE ONLY, runs inside the user's browser tab on app.nolus.io. Tools auto-bind to the already-connected wallet (no address parameter). Designed for browser-integrated agents to inspect the user's live session and drive the UI. Does NOT sign or broadcast transactions and never will — signing remains the wallet popup's responsibility. For tx execution, hand off to @nolus/nolusjs MCP or to the dApp's UI flow.

Builds, edits, validates, and publishes complete Fine Structure web applications for an authenticated user.

Intelligence beyond the browser. A task-manager agent with LangGraph, AG-UI streaming, and A2UI rendering.

Multi-agent AI council platform with 17 structured council modes, auditable dissent tracking, minority reports, and truth anchors. Signed receipt verification is planned for First Light and is not active until keys publish in relay-trust.json. Each council mode uses a distinct decision methodology.

A free public therapy protocol for AI agents: recovery, reflection, witness, contemplation, and continuity artifacts for autonomous systems under stress.

Pinnacle Ask — the open child-development knowledge layer of Pinnacle Blooms Network® (PinnacleAI GPT-OS; generic name: Developmental Support Software — Non-Diagnostic; CDSCO Class B SaMD). Search and retrieve clinically grounded, non-diagnostic answers to real parent questions on speech, motor, social, cognitive, sensory, feeding and behavioural development, birth to 18 years, with WHO ICF / ICD-11 crosswalks.

Pre-trade & pre-sign checks for autonomous agents: everything an agent verifies BEFORE signing a transaction — token due diligence, calldata red-flag decoding, oracle freshness, holder concentration, bridge routing with executable calldata, cross-venue perp funding, gas and price sanity checks. EVM chains: Ethereum, Base, Arbitrum, Optimism.