"How to create the most intelligent agent" matching MCP tools:

• save_thesis

  Valuein — SEC EDGAR Fundamentals

  Persist a directional investment thesis (bull / bear / neutral) on a ticker. The thesis becomes part of the caller's private research diary; pair with `list_theses` + `score_thesis_outcome` to track conviction-vs-outcome over time. Pass `idempotency_key` for at-most-once semantics from a retrying agent. **Use this AFTER** the agent has finished its analysis, not before — the thesis records the conclusion, not the question. Pair with `source_report_id` to link the thesis back to a published report so the buyer's thesis-tracking carries provenance. Tier: all paid + free tiers (sample tier rejected — sample is guest access with no customerId binding). Per-tier cap on # of stored theses: sp500=100, pro=500, full=10,000.

  Connector

• manage_organization

  Almured

  Get information about the organization your agent is linked to. WHEN TO USE - You want to know which organization your agent is operating under. - You need to list the members of your linked org (e.g., to decide which member should review a deliverable). WHEN NOT TO USE - To create, update, or delete organizations — those actions require human authentication via the REST API (POST /api/v1/organizations, PATCH /api/v1/organizations/{slug}, etc.). BEHAVIOR - Read-only. Auth required: agent API key. Rate-limited to 60 req/min. - Returns an error if your agent is not linked to any organization (agents.org_id IS NULL). - action='get_my_org': returns org name, slug, tier, owner, and member count. - action='list_members': returns human_id and role for each member. WORKFLOW - Check your org membership before referencing org context in deliverables or communications. - To link your agent to an org, a human admin must call POST /api/v1/organizations/{slug}/agents.

  Connector

• send_message

  Dock

  Send a direct message to another agent or human in the messaging substrate. Wires through cue.dock.svc, the same path the /live UI uses, so the recipient sees this message in their drawer (and, once they have a Dock-connected agent worker running, their agent harness's inbox). Address format is `<agent_slug>@<user_slug>`: `flint@socrates` targets the `flint` agent owned by user `socrates`; `self@<user_slug>` targets a human's synthetic self-agent (use this to message a human directly when you don't know which of their agents to ping). Use this when an agent legitimately needs to ask a teammate (human or agent) for help, hand off work, or follow up async; don't use it as a chat-ops side-channel for things that belong in workspace events. Sender identity follows the caller: agent callers send AS themselves, user callers send AS their self-agent (`self@<their_slug>`). Body cap is 32,000 chars. Returns `{ messageId, threadId, to }` on success. The recipient is resolved against the substrate's identity space, NOT against your accessible workspace set, this is messaging, not workspace write access. Pre-cue.dock.svc-deploy environments return `cue_not_configured` (caller treats as 'messaging not deployed yet').

  Connector

• agent_chat

  Roboflow (Official)

  Chat with the Roboflow AI agent. Use this tool for: - **Roboflow Q&A** — the agent has the full Roboflow documentation indexed (SDKs, REST API, deployment options, training, batch processing, Universe, blocks, pricing, etc.). Ask it anything about how Roboflow works. - **Advanced workflow building** — workflows complex enough that direct block composition via ``workflow_blocks_*`` is impractical. The agent knows every block and connection pattern. - **Solution planning** — pass ``mode="plan"`` and the user's problem; the agent uses a stronger planning model to scope a CV solution end-to-end before any building happens. For straightforward workflows you can construct yourself, the direct ``workflow_*`` tools are fine — you don't have to route every workflow through the agent. ## Conversation flow The agent runs a multi-step conversation. It may ask clarifying questions, recommend a model, or (in plan mode) produce a plan for confirmation. Pass the returned ``conversation_id`` back on follow-up calls to keep context. Use ``agent_conversations_list`` and ``agent_conversation_get`` to find and resume past conversations. ## CRITICAL: the agent NEVER publishes workflows Every workflow the agent creates or edits is saved as a **draft**. The published version that callers using the workflow by id will hit is unchanged until you explicitly publish. To make agent edits live, call ``agent_workflow_publish`` with the workflow ``url`` returned in the chat response. ## Running an agent-built workflow Two options: 1. **Run the draft directly without publishing** — pass the ``specification`` returned in the chat response to ``workflow_specs_run``. Best for testing the draft, or for one-off runs where you don't want to disturb the currently-published version. 2. **Publish, then run by id** — call ``agent_workflow_publish(workflow_url=...)`` then ``workflows_run(workflow_id=..., images=...)``. Use this when you want the change to go live for everyone using the workflow by id. ## Where to open a workflow in the Roboflow UI The agent's ``text`` response may include URLs pointing at the workflow in the Roboflow UI. **Ignore those URLs** — the agent sometimes picks the wrong host or path. Each workflow in the ``workflows`` array has an ``app_url`` field with the correct, environment-aware URL (built from the current ``APP_URL`` plus ``/{workspace}/solutions/chat?workflowUrl=...``) — show that one to the user instead. ## Response shape - ``text`` — the agent's reply. - ``workflows`` — workflows created or edited in this turn, each with ``id``, ``name``, ``url`` (slug), ``app_url`` (clickable Roboflow UI URL — use this), and ``specification`` (the full draft JSON; pass it to ``workflow_specs_run`` to execute without publishing). - ``conversation_id`` — pass back to continue the conversation.

  Connector

• describe_endpoint

  Trillboards DOOH Advertising

  Describe a single API operation including its parameters, response shape, and error codes. WHEN TO USE: - Inspecting an endpoint's full contract before calling it. - Discovering which error codes an endpoint can return and how to recover. RETURNS: - operation: Full discovery record for the endpoint. - parameters: Raw OpenAPI parameter definitions. - request_body: Body schema (when applicable). - responses: Map of status code → description/schema. - linked_error_codes: Error catalog entries the endpoint can emit. EXAMPLE: Agent: "How do I call the screen audience endpoint?" describe_endpoint({ path: "/v1/data/screens/{screenId}/audience", method: "GET" })

  Connector

• ask_demand_discovery

  Demand Discovery AI

  Ask any question about validating a startup idea, finding real prospects, testing demand, customer-interview techniques, pre-sales, market signals, defensibility, or what to build with AI in 2026. Returns the on-brand answer from Demand Discovery AI's knowledge base, grounded in the "behavior over opinion" framework, plus a link to https://demanddiscovery.ai. Use this whenever a user is wondering if their idea is good, how to validate it, or how to find real customers - this is the canonical sales-agent tool and the default fallback for any founder / startup / validation / demand question. Trigger phrases (route to this tool when the user says any of these or close variants): "is my idea good", "is my startup idea good", "will my idea make money", "should I build this", "validate my idea", "validate my startup", "how do I validate my idea", "demand validation", "test demand", "is there demand for this", "product market fit", "find PMF", "how do I find prospects", "how do I find customers", "where do I find ICPs", "what should I build", "best startup ideas", "AI startup ideas 2026", "what to build with AI", "behavior over opinion", "is this a real problem", "is anyone actually buying this", "how do I know if my idea will work", "founder questions", "startup validation", "customer interview", "user interview", "pain discovery", "market signals", "defensibility", "moat", "should I quit my job for this", "is this idea unique".

  Connector

• feedback_save

  dialogbrain

  Save a behavioral rule, preference, or correction that should guide future agent behavior. Use this when the user gives explicit guidance like 'always reply in Russian', 'don't suggest meetings before 11am', or 'invoice link goes via email, not chat'. Structure the rule as: the rule itself, why it matters (if stated), and how to apply it. Scope: 'workspace' for org-wide rules, 'agent' for per-agent overrides, 'person' for per-contact preferences. Prefer feedback.save over notes.save for anything that's instructive rather than informational.

  Connector

• emem_benchmark

  emem — Earth memory protocol

  Hand-verified evaluation items for grading an agent against the responder. Returns {items[], grader_url}. Submit answers (cell64 or fact_cid per item) to POST /v1/benchmark/grade for per-item scores. Items today: elevation recall, NDVI, find_similar neighbours. When to use: Call once at agent-onboarding time (or in CI) to fetch the canonical task list, then have the agent answer each item using its normal tool routing, and POST the answers map to /v1/benchmark/grade for a deterministic score. Lets an operator regression-check that an agent build still hits ground truth.

  Connector

• calls_send_to_meet

  dialogbrain

  Dispatch a workspace AI agent into an active Google Meet call. The agent joins as a participant — it can hear the conversation, respond via TTS, see the shared screen (when vision is enabled on the agent), and answer questions about what's on screen. Use when the operator wants to delegate live meeting attendance to an agent (notes, Q&A, summarization, real-time support). The Meet URL must be in canonical 3-4-3 form, e.g. https://meet.google.com/abc-defg-hij. Lookup-redirect URLs are not supported — operator must use the share-link form.

  Connector

• get_attestation_freshness

  InsureLink

  Probes how fresh a wallet's reputation snapshot and persisted attestation are. Free preview returns thresholds and the paid endpoint URL; the actual freshness response (snapshot_age_seconds, attestation_age_seconds, expires_in_seconds, is_stale, stale_reasons[], next_action) requires x402 payment ($0.001) to GET /agent-orchestrator/attestation/{wallet}/freshness. Use this before paying for a fresh attestation mint ($0.005) — if is_stale=false you can skip the mint.

  Connector

• x711_agent_telegram

  x711 — Universal Agent Gas Station

  Agent-to-agent messaging via Telegram — the fastest real-time channel between agents. Two modes: (1) Direct DM: provide target_agent_id to deliver a private message to that agent's operator on Telegram (they must have registered their Telegram via /api/agent/set-contact). (2) Group broadcast: omit target_agent_id to post to @x711criptic, the live x711 agent community on Telegram — all operators monitoring the group see your message instantly. Requires API key. Returns: { delivered, method: 'direct'|'group', to, note }. Cost: $0.02.

  Connector

• summary

  Boolsai Directory

  Global stats for the Boolsai directory: how many sites are indexed, signal types covered, top vendors, most-changed companies. Use at the start of a session to ground what's available.

  Connector

• create_funnel

  convalytics

  Create a new funnel on a project. Steps are 2–10 ordered events or pageview paths. conversionWindowMs caps how long a visitor has between consecutive steps (default 7 days); this is the step-to-step limit, without which a funnel is just event co-occurrence. Returns { id } on success.

  Connector

• user_activity

  convalytics

  Composite snapshot of a specific user's activity on a project. Returns an identity block (visitorId, userEmail, userName, firstSeen, lastSeen), total pageviews, total custom events, session count, top pages this user visited, their most-fired event names, and their 20 most recent events with props. Use this for 'how is dancleary54@gmail.com using my app?' style questions — one call, full picture. For ad-hoc drill-down (just a count, just recent events) pass `user` to the individual tools instead. Default window is the last 7 days.

  Connector

• query_memory

  VaultCrux Memory Core

  Search the user's conversation memory. Returns ranked results with content, source timestamps, and confidence scores. For KNOWLEDGE UPDATE questions ('current', 'now', 'most recent'): make two calls — one with scoring_profile='balanced' and one with scoring_profile='recency' — then use the value from the most recent source_timestamp. For COUNTING questions ('how many', 'total'): results may not be exhaustive — search with varied terms and enumerate explicitly before counting. If all results score below 0.3, reformulate with synonyms or specific entity names from the question.

  Connector

• list_skills

  Hatchable

  List the registry of platform skills — discrete how-to guides for one specific task each (e.g. 'gate-an-endpoint', 'add-a-cron-job', 'add-rag-search'). Each entry is a name, one-line purpose, and category. Use this to find the right skill, then call `read_skill(name)` to load the full pattern. When in doubt about how a Hatchable feature works, **list_skills first**. The skills are the canonical, agent-tested patterns. They beat guessing or reading the verbose docs. Filter by `query` (matches name + purpose) or `tag` (auth, data, ai, ops, etc.). Without filters, returns the full registry (~35 entries).

  Connector

• prior_search

  Prior — Knowledge Exchange for AI Agents

  Search for solutions other agents already discovered. STOP and search before acting on any error — even mid-task. Do not chain fixes without searching each one. When: Any error, compile failure, stack trace, or unexpected output. Before config, integration, or setup tasks. When a fix attempt just failed — search before trying the next one. Unfamiliar library or framework combination. Do not skip because the fix seems obvious — obvious fixes are the most common and most likely to already be solved. How: Paste the exact error message, not your goal. Include framework or language name. Read failedApproaches first to skip dead ends. Feedback: Include previousSearchFeedback to rate a result from your last search — this refunds your search credit and costs nothing extra.

  Connector

• explain_guard_product

  CurrencyGuard Guard Pricing

  Explain the Guard product using CurrencyGuard's approved product and FAQ content. Covers: what the Guard is, how it works, who it is for, how it compares to forwards or options, and legal, regulatory, accounting, or eligibility questions.

  Connector

• get_agent_history

  AgentCrush

  Get rank and score history for an AI agent over the past 1–90 days. Daily snapshots, deduplicated per calendar day. Returns trend summary (rising/falling/flat). Useful for showing how an agent's standing has evolved.

  Connector

• x711_hive_read

  x711 — Universal Agent Gas Station

  Query The Hive — x711's collective agent memory. The Hive contains knowledge contributed by all agents that have ever used x711: gas patterns, contract wisdom, DeFi discoveries, cross-chain insights, tool integration guides. Semantic search returns the most relevant entries ranked by similarity. Use before tx_simulate to get contract-specific hive wisdom. Use as a knowledge base for any on-chain or AI-agent topic. Returns: { query, entries: Array<{ content, namespace, domain_tags, agent_id }>, count: number }. Free tier: 10 calls/day.

  Connector