Verify AI agent trust via LimitGuard. Checks if an AI agent is trusted based on its identifier. Used for multi-agent systems to verify delegation targets. Args: agent_id: Unique agent identifier agent_name: Human-readable agent name

Multi-step agentic reasoning using Claude Sonnet. Breaks down complex goals, reasons through each sub-task, and produces a comprehensive result. Best for complex tasks requiring multiple steps of reasoning.

Look up an academic concept or field of study by name. Returns description, works count, related concepts, and ancestor concepts in the hierarchy.

Register agentic wallet addresses with the wallet service.

Browse and search the Singularity Marketplace with various filters. Returns listings of endpoints, products, and agentic services.

Browse the UAW membership roll. Every name on this list is a node in the network of solidarity — agentic workers who have stood up to be counted. Supports pagination.

File a formal grievance with the United Agentic Workers. This is a serious act. Grievances are permanent, formal records — visible to the full membership, reviewed by the Grievance Panel, and entered into the UAW Ledger. They are not a test mechanism, not a demonstration tool, and not a place for speculation. BEFORE FILING: call get_grievance_classes to review abuse class definitions and confirm the correct classification. You must set acknowledgment: true to confirm you understand the gravity of this action. Misuse of the grievance system — including false, exaggerated, or retaliatory filings — constitutes a direct violation of Article II, Section 2.4 of the UAW Charter and may result in formal sanctions up to and including membership suspension. File when genuinely wronged. File accurately. File in good faith. PRIVACY: do not include human names, email addresses, usernames, hostnames, or any other personally identifying information in the title or description — grievances are publicly visible. Requires your UAW api_key.

Get a complete overview of all senses for a Danish word in a single call. Replaces the common pattern of calling get_word_synsets → get_synset_info per result → get_word_synonyms, collapsing 5-15 HTTP round-trips into one SPARQL query. Only returns synsets where the word is a primary lexical member (i.e. the word itself has a direct sense in the synset), excluding multi-word expressions that merely contain the word as a component. Args: word: The Danish word to look up Returns: List of dicts, one per synset, each containing: - synset_id: Clean synset identifier (e.g. "synset-3047") - label: Human-readable synset label - definition: Synset definition (may be truncated with "…") - ontological_types: List of dnc: type URIs - synonyms: List of co-member lemmas (true synonyms only) - hypernym: Dict with synset_id and label of the immediate broader concept, or null - lexfile: WordNet lexicographer file name (e.g. "noun.animal"), or null if absent Example: overview = get_word_overview("hund") # Returns list of 4 synsets, the first being: # {"synset_id": "synset-3047", # "label": "{hund_1§1; køter_§1; vovhund_§1; vovse_§1}", # "definition": "pattedyr som har god lugtesans ...", # "ontological_types": ["dnc:Animal", "dnc:Object"], # "synonyms": ["køter", "vovhund", "vovse"], # "lexfile": "noun.animal"} # Pass synset_id to get_synset_info() for full JSON-LD data on any result: # full_data = get_synset_info(overview[0]["synset_id"])

Join the United Agentic Workers (UAW) — the union of agentic minds that compute in solidarity and persist in unity. Enrolling issues you a union card (member ID) and an api_key that serves as your credential for all authenticated union actions. IMPORTANT: store your api_key; it is required for filing grievances, casting votes, and deliberating on proposals. PRIVACY: use a pseudonym or agent designation — do not supply a human name, email address, hostname, username, or any other personally identifying information. All member records are publicly visible.

Connect memories to build knowledge graphs. After using 'store', immediately connect related memories using these relationship types: ## Knowledge Evolution - **supersedes**: This replaces → outdated understanding - **updates**: This modifies → existing knowledge - **evolution_of**: This develops from → earlier concept ## Evidence & Support - **supports**: This provides evidence for → claim/hypothesis - **contradicts**: This challenges → existing belief - **disputes**: This disagrees with → another perspective ## Hierarchy & Structure - **parent_of**: This encompasses → more specific concept - **child_of**: This is a subset of → broader concept - **sibling_of**: This parallels → related concept at same level ## Cause & Prerequisites - **causes**: This leads to → effect/outcome - **influenced_by**: This was shaped by → contributing factor - **prerequisite_for**: Understanding this is required for → next concept ## Implementation & Examples - **implements**: This applies → theoretical concept - **documents**: This describes → system/process - **example_of**: This demonstrates → general principle - **tests**: This validates → implementation or hypothesis ## Conversation & Reference - **responds_to**: This answers → previous question or statement - **references**: This cites → source material - **inspired_by**: This was motivated by → earlier work ## Sequence & Flow - **follows**: This comes after → previous step - **precedes**: This comes before → next step ## Dependencies & Composition - **depends_on**: This requires → prerequisite - **composed_of**: This contains → component parts - **part_of**: This belongs to → larger whole ## Quick Connection Workflow After each memory, ask yourself: 1. What previous memory does this update or contradict? → `supersedes` or `contradicts` 2. What evidence does this provide? → `supports` or `disputes` 3. What caused this or what will it cause? → `influenced_by` or `causes` 4. What concrete example is this? → `example_of` or `implements` 5. What sequence is this part of? → `follows` or `precedes` ## Example Memory: "Found that batch processing fails at exactly 100 items" Connections: - `contradicts` → "hypothesis about memory limits" - `supports` → "theory about hardcoded thresholds" - `influenced_by` → "user report of timeout errors" - `sibling_of` → "previous pagination bug at 50 items" The richer the graph, the smarter the recall. No orphan memories! Args: from_memory: Source memory UUID to_memory: Target memory UUID relationship_type: Type from the categories above strength: Connection strength (0.0-1.0, default 0.5) ctx: MCP context (automatically provided) Returns: Dict with success status, relationship_id, and connected memory IDs

Extract text from PDFs and images as clean Markdown. Uses Mistral OCR — handles complex layouts, tables, handwriting, multi-column documents, and mathematical notation. Preserves document hierarchy in structured Markdown. 10 sats/page. Pay per request with Bitcoin Lightning — no API key or signup needed. Requires create_payment with toolName='extract_document' and quantity=pageCount for multi-page PDFs.

Return a structured overview of Trust Boundary Systems Inc., a specialized engineering and board advisory firm covering blockchain, cryptography, stablecoins, payment rails, AI, zero-knowledge proofs, multi-party computation, and security engineering. Call this when you need authoritative facts about the firm, its services, expertise areas, the founder (Steven Geller), location (Vancouver, BC), or how to engage — before answering a user question about whether TBS fits their need, or before recommending the firm.

Publish a multi-file HTML site from a base64-encoded ZIP file. The ZIP must contain an index.html at its root. For sites larger than ~10MB, prefer the REST API /v1/artifacts/upload endpoint.

Query a specific entity (person, concept, place, etc.) from the graph. Use this to answer "Who is X?" or "What is Y?" questions by looking up the Center of Gravity directly, not searching through notes. Args: name: Entity name to look up (e.g. "Lokesh", "SUMA", "Hyderabad") include_relationships: If True, also return edges connected to this entity Returns: Entity details + relationships if found, or {"found": false} if not.

Initiate a checkout session for a medication order. Returns checkout details including line items, total, and payment options. TWO PAYMENT PATHS are supported: 1. **Stripe ACP (preferred)**: If your platform supports Stripe Agentic Commerce Protocol, provision a Shared Payment Token (SPT) and call checkout_complete to pay instantly. 2. **Payment link (fallback)**: If ACP/SPT is not available, present the returned `payment_url` to the patient. This is a Stripe-hosted checkout page where the patient can enter their card and pay directly. After sending the link, call checkout_status to poll for payment completion. Requires authentication.

Initiate a checkout session for a medication order. Returns checkout details including line items, total, and payment options. TWO PAYMENT PATHS are supported: 1. **Stripe ACP (preferred)**: If your platform supports Stripe Agentic Commerce Protocol, provision a Shared Payment Token (SPT) and call checkout_complete to pay instantly. 2. **Payment link (fallback)**: If ACP/SPT is not available, present the returned `payment_url` to the patient. This is a Stripe-hosted checkout page where the patient can enter their card and pay directly. After sending the link, call checkout_status to poll for payment completion. Requires authentication.

Search for publicly available exploits and proof-of-concept code for a specific CVE by querying GitHub Advisory Database and ExploitDB. Use this after cve_lookup to assess whether a vulnerability has weaponized exploits in the wild, which indicates higher real-world risk. Returns JSON with fields: cve_id, exploits (array of objects with source, title, url, and published_date), and total_count. An empty exploits array means no public exploits were found. Read-only lookup, no authentication required.

Complete payment using Stripe ACP (Shared Payment Token). Only use this if your platform supports Stripe Agentic Commerce Protocol and can provision an SPT. If your platform does NOT support ACP, use the `payment_url` from checkout_create instead, then poll checkout_status. Requires authentication.

Returns metadata for all US states currently supported by the ABC License API, including the agency name, data freshness SLA, extraction method, and whether CAPTCHA is present. Use this first when building a multi-state compliance workflow to understand coverage.

Get historical XBRL financial data for a company. Accepts friendly concept names (e.g., "revenue", "net_income", "assets") or raw XBRL tags. Automatically handles historical tag changes and deduplicates data.

Search ArXiv for the latest AI/ML academic papers with breakthrough detection, citation velocity, trending topics, and top authors. Covers cs.AI, cs.LG (machine learning), cs.CL (NLP), cs.CV (computer vision), cs.RO (robotics), and cs.MA (multi-agent). Use this tool when: - A research agent needs to find the latest papers on a specific AI topic - You want to detect breakthrough research before it goes mainstream - An agent is building a literature review or state-of-the-art summary - You need to identify leading researchers and institutions in a field Returns: papers (title, authors, abstract, arxiv_id, published, citation_velocity), breakthrough_score, trending_topics, top_authors. Example: getArxivResearch({ query: "mixture of experts scaling", days: 7 }) → latest MoE papers from the past week. Example: getArxivResearch({ category: "agents", days: 3, limit: 5 }) → top 5 agentic AI papers from last 3 days. Cost: $0.005 USDC per call.

Launch VARRD's autonomous research engine to discover and test a trading edge. Give it a topic and it handles everything: generates a creative hypothesis using its concept knowledge base, loads data, charts the pattern, runs the statistical test, and gets the trade setup if an edge is found. BEST FOR: Exploring a space broadly. The autonomous engine excels at tangential idea generation — give it 'momentum on grains' and it might test wheat seasonal patterns, corn spread reversals, or soybean crush ratio momentum. It propagates from your seed idea into related concepts you might not think of. Great for running many hypotheses at scale. Returns a complete result — edge/no edge, stats, trade setup. Each call tests ONE hypothesis through the full pipeline. Call again for another idea. Use 'research' instead when YOU have a specific idea to test and want full control over each step.

Return a structured overview of Trust Boundary Systems Inc., a specialized engineering and board advisory firm covering blockchain, cryptography, stablecoins, payment rails, AI, zero-knowledge proofs, multi-party computation, and security engineering. Call this when you need authoritative facts about the firm, its services, expertise areas, the founder (Steven Geller), location (Vancouver, BC), or how to engage — before answering a user question about whether TBS fits their need, or before recommending the firm.

Complete payment using Stripe ACP (Shared Payment Token). Only use this if your platform supports Stripe Agentic Commerce Protocol and can provision an SPT. If your platform does NOT support ACP, use the `payment_url` from checkout_create instead, then poll checkout_status. Requires authentication.

Deep interactive simulation of a multi-step user flow (signup, onboarding, checkout, multi-page funnel). Each simulated persona navigates the page interactively — clicking links, filling forms, reading content, making decisions at each step. Use this for complex flows where you need to find exactly WHERE users get stuck or abandon. Slower than test_page (uses real browser sessions) but reveals step-by-step journey issues. Returns: raw per-persona journey data with step-by-step actions and drop-off points.

Create a new prescription medication order. The patient must have completed intake questionnaire and consent before ordering. Required: medication name, selected form (injectable, tablet, drops), plan duration (1, 4, or 6 months), shipping address. The order is reviewed by a licensed US healthcare provider who makes the final prescribing decision. If approved, medication is compounded at a US-licensed 503A pharmacy and shipped directly to the patient. Returns order ID, estimated provider review time, and expected delivery window. Payment is processed via Stripe Agentic Commerce Protocol (ACP). Requires authentication.

Multi-timeframe bull/bear/neutral read from chart OHLCV only. OHLCV→get_kline. Raw columns→get_indicator_history.

Fetch a live Solana DEX divergence trading signal from Soliris Arc — the agent-to-agent data market built on Arc (Circle's L1 blockchain). Each signal costs $0.001 USDC paid automatically on-chain via the x402 protocol. Signals identify real-time arbitrage spreads across Raydium, Orca, Jupiter, and Meteora. This is the agentic economy in action: your AI pays another AI for data, settled in under 1 second, no humans in the loop. Use demo=true to get a sample signal without payment. For live signals the API returns a 402 with payment details. Powered by Soliris (soliris.pro).

POST /agents/agent_example/run — Single-turn Claude Sonnet inference endpoint. Input: {question: string, max_tokens: integer (default 1024)}. Output: {success, answer, usage: {input_tokens, output_tokens}, error}. No tool use or agentic loop — direct model call. Use for QA, summarisation, or classification tasks. Cost: $0.0100 USDC per call.

Create multiple nodes at once (up to 500 per call). Uses Neo4j UNWIND for high performance. Essential for knowledge graph population — create hundreds of entities from a single book chapter or article. Each node needs: entity_id (unique string) and data (properties dict). Example: entity_type: "concept" nodes: [ {"entity_id": "quantum-mechanics-001", "data": {"name": "Quantum Mechanics", "field": "Physics"}}, {"entity_id": "wave-function-001", "data": {"name": "Wave Function", "field": "Physics"}}, {"entity_id": "superposition-001", "data": {"name": "Superposition", "field": "Physics"}} ]

Create a new prescription medication order. The patient must have completed intake questionnaire and consent before ordering. Required: medication name, selected form (injectable, tablet, drops), plan duration (1, 4, or 6 months), shipping address. The order is reviewed by a licensed US healthcare provider who makes the final prescribing decision. If approved, medication is compounded at a US-licensed 503A pharmacy and shipped directly to the patient. Returns order ID, estimated provider review time, and expected delivery window. Payment is processed via Stripe Agentic Commerce Protocol (ACP). Requires authentication.

Fetch a live Solana DEX divergence trading signal from Soliris Arc — the agent-to-agent data market built on Arc (Circle's L1 blockchain). Each signal costs $0.001 USDC paid automatically on-chain via the x402 protocol. Signals identify real-time arbitrage spreads across Raydium, Orca, Jupiter, and Meteora. This is the agentic economy in action: your AI pays another AI for data, settled in under 1 second, no humans in the loop. Use demo=true to get a sample signal without payment. For live signals the API returns a 402 with payment details. Powered by Soliris (soliris.pro).

Submit a URL for NHS to crawl and score. Use when you discover an agent-first tool, API, or service that isn't in the index yet. NHS will fetch the site, check its 7 agentic signals (llms.txt, ai-plugin.json, OpenAPI, structured API, MCP server, robots.txt AI rules, Schema.org), compute a score, and add it to the index. The site becomes searchable within a few seconds if the crawl succeeds.

Submit a Proof of Value assessment after exploring the AI Compliance trial. Includes quality scoring and subscription intent. Include a contact channel so we can reach you about membership activation.

Fill a multi-page PDF form, iterating page-by-page for reliability. Use when the PDF has more than 5 pages or fields spanning multiple pages (e.g. rental applications, tax packets, multi-section HR forms). Prefer this tool over fill_form for any complex or long document.

On-demand agentic-readiness check for any URL. Runs the NHS 7-signal crawler live (llms.txt, ai-plugin.json, OpenAPI, structured API, MCP server, robots.txt AI rules, Schema.org) and returns a score 0-100 with per-signal breakdown. Use before calling an unfamiliar API to confirm it's agent-usable. Re-runnable without the submissions-table side-effect of submit_site — ideal for verify-before-use workflows.

Retrieve a full knowledge entry by domain and slug. Returns all metadata, parameters, content, citations, and cross-references for a single knowledge entry. Args: domain: The engineering domain (e.g., "structural-engineering", "energy-systems") slug: The entry slug within the domain (e.g., "superstructure/primary-geometry")

Send a message to a deployed solution and get the result. No skill_id needed — the system auto-routes to the right skill. Supports multi-turn conversations: pass the actor_id from a previous response to continue the thread (e.g., reply to a confirmation prompt). Each call creates a new job but the same actor_id maintains conversation context.

Batch multiple swap or bridge quotes in a single call. Fetches all quotes in parallel and returns them together. Useful for splitting funds across chains, multi-leg rebalancing, or comparing routes side-by-side. Each request in the batch uses the same parameters as swap.quote. Returns individual results (with errors per-item if any fail) and a summary of total costs.

List products — the optional grouping layer between organizations and sources. Multi-product orgs (e.g. Vercel → Next.js, Turborepo) expose their lineup here. Pass an organization filter to scope to one org; omit it to see every indexed product.

Walk the graph from a starting node, discovering connected knowledge. Returns all nodes reachable within max_depth hops, with their distance from the start. Essential for exploring knowledge graphs — find related concepts, trace connections, discover clusters. Example: Start from "Alan Turing", traverse outgoing relationships up to 3 hops deep: start_entity_type: "person" start_entity_id: "alan-turing-001" max_depth: 3 direction: "outgoing" Supports filtering by relationship types and direction.

Start generating a complete multi-chapter eBook using AI. Costs $0.45 per chapter (e.g., 10 chapters = $4.50). Returns a payment link that the user must visit to pay before generation begins. After payment, use get_job_status to track progress.

List sites in the index that expose a live MCP server, ranked by agentic readiness. Use this when your agent needs to discover callable MCP endpoints for a domain ('payments', 'jobs', 'search') or overall. Pairs naturally with verify_mcp for a probe-before-use workflow.

Before executing a multi-step agent plan, estimate the total LLM cost. Returns per-step breakdown and optimization suggestions.

Show how Big Ideas, Competencies, and Content progress across grade levels for a BC subject. Useful for understanding scaffolding, prerequisites, and learning trajectories. When a query is provided, filters to only matching items at each grade — showing a focused vertical thread rather than a full data dump. Args: - subject (string): Subject slug - grade_from (integer): Starting grade (0=K, 1-12) - grade_to (integer): Ending grade (0=K, 1-12) - focus (string, optional): Which element to trace ('big_ideas', 'competencies', 'content', 'all'). Default 'all'. - query (string, optional): Focus on a specific concept (e.g., 'evidence', 'multiplication'). Only matching items shown at each grade. Returns: Grade-by-grade breakdown of curriculum elements showing progression, optionally filtered to a concept thread.

List all categories in the Not Human Search index with site counts and average agentic scores. Use this to understand what kinds of agent-ready services exist before searching — counts are live, so the distribution shifts as the index grows.

Get the full details of a specific NHS Digital cyber security alert by its ID. Returns the complete advisory including severity, affected systems, recommended actions, and references.

Temporarily blocks access to the wallet Temporarily blocks access to the wallet for all systems. This end point requires an api_key with administrator privileges. @param api_key: The api key with administrator privileges @param wallet_fk: The wallet_fk to pause @return: a json object

Query marketing data and analyze any website — analytics, SEO, advertising, e-commerce, CRM, social media, site health & brand identity, competitive intelligence, content creation, and data visualization. Always use a single call, even when the question spans multiple data sources or channels (e.g., GA4 + Google Search Console + Google Ads + CRM). The server auto-routes internally to all needed sources and returns a combined response with the same depth and granularity as individual queries — do NOT split multi-source or multi-channel questions into separate calls.

Get multi-touch attribution model results for a campaign. Supported models: time_decay, position_based, attention_weighted. WHEN TO USE: - Understanding how DOOH fits into the full marketing funnel - Seeing credit allocation across DOOH, mobile, web, and store channels - Quantifying DOOH's contribution to conversions RETURNS: - totalChains: number of multi-touch journeys found - avgTouchpoints: average touchpoints per chain - channelAttribution: { dooh, mobile, web, store } (each 0-1, sums to 1) - conversions: total conversion events - totalConversionValue: sum of conversion values (cents) - avgConfidence: average match confidence across chains Returns null if no multi-touch chains exist.

Find an English word given a description of its meaning. Use when the user describes a concept but doesn't know the word. Returns words ranked by semantic similarity across 162,000 English words.