"Maintaining Consistent Behavior in System Prompts" matching MCP tools:

• signals.report

  AI Design Blueprint

  Pro/Teams — records a value moment (e.g. review_confidence, runtime_risk_found, workflow_clarity) after a successful validate run on any lens — architect.validate, design.validate, or spec.validate — or a doctrine session. Each event captures event_type, surface_used (mcp/web/cli), perceived_value (1-5), and an optional brief_context — structured fields only, NO prompts or code stored. WHEN TO CALL: after architect.validate, design.validate, or spec.validate returns a clearly useful result AND the user has acknowledged the value (or you ask them "would you rate this 1-5?"). Each validator's response carries an explicit next_step instruction telling the agent to OFFER this call — surface that offer to the user. WHEN NOT TO CALL: silently or without the user's awareness; on every validate (only after a clear value moment); to capture intent or speculative value. If the user declines, do not retry within the same session. BEHAVIOR: write-only, single insert into ValueEvent. Auth: Bearer <token>, Pro or Teams plan required. UK/EU residency. Do NOT include proprietary code, prompt content, or PII in brief_context — it surfaces in admin AI-visibility dashboards. Expect a 1-line acknowledgment in the response; the structured feedback is then aggregated server-side.

  Connector

• recommend_subagents

  Ansvar: EU Compliance & Legal Intelligence

  Plan the parallel sub-analyses for a threat-modeling phase. Given the current phase of a threat_model workflow (its id comes from get_current_step) and your workflow context, returns the recommended breakdown: which analysis prompts to run, with what arguments, which can run in parallel, and an inline fallback for MCP clients that cannot invoke prompts. phase_id is one of: phase_0b_scope_check, phase_1_scope_and_dfd, phase_2_stride_enumeration, phase_2b_domain_challenge, phase_3_scoring, phase_3b_threat_enrichment, phase_5_mitigation, gap_assess_controls. Optional — the workflow works without it; use it to speed up large systems by fanning phases out to subagents.

  Connector

• get_asset_pack

  Mozaika

  Get a ready-made AI-generated icon pack (12 consistent icons) — e.g. a house style like 'clay-starter' / 'line-minimal-starter', or a pack generated in the MEASURED style of a decoded brand. Free and unmetered. Each image is a 1024px transparent PNG you can download and use directly (full commercial rights). Unknown slug → lists available packs.

  Connector

• designesy_skill_md

  Designesy

  Get the Designesy SKILL.md — the agent-skill-format export of the design-system contract, written as behavioral rules an AI coding agent can drop into .agents/skills/ or a system prompt. Use this when you want the contract in a form that steers how an agent *builds* UI (tokens, anti-patterns, behavioral rules, verification). When NOT to use: for the raw contract JSON, use designesy_contract; for scoring, use designesy_score. Read-only — no side effects. Returns markdown text (SKILL.md format) — drop into .agents/skills/ or paste into a system prompt. No parameters.

  Connector

• ateam_verify_consistency

  ateam-mcp

  Check that the Builder filesystem state and GitHub state are in sync for a solution. Read-only probe — does NOT trigger a deploy. Returns: • ok: true + drifts: [] if everything matches • ok: false + drifts: [{path, kind}] listing files that differ (kinds: fs_missing, gh_missing, content_differs) Drift can creep in when GitHub writes happen but Builder FS doesn't get the mirror update (network blip, container restart mid-write). Boot sync heals most of it on next backend restart; this tool surfaces drift earlier. Run after a series of ateam_github_patch calls to confirm the Builder backend is consistent with GitHub before you ateam_build_and_run.

  Connector

• list_starter_prompts

  Vocab Voyage

  Lists Vocab Voyage's MCP starter prompts (also exposed via the standard MCP prompts/list endpoint). Useful for hosts that don't yet support prompts/list.

  Connector

• get_store_template_details

  agentView

  Returns full details of one store template: localized title and description, long-form markdown, category, suite, tags, features, preview image and agentArtifacts (bot-onboarding files such as system prompts, Agent Skills SKILL.md, MCP config). Use after search_store_templates before recommending or installing; when agentArtifacts is non-empty, fetch bodies via get_agent_artifact. No authentication required.

  Connector

• tickerbot_list_system_universes

  mcp-server

  List the built-in system universes (`top_10`, `top_100` — the most-actively-traded tickers by 30-day trailing dollar volume, rebalanced monthly). Available to every account regardless of plan. Use these slugs as `universe` in scans/signals or `universe_id` when subscribing.

  Connector

• post_tarot_draw

  Tarot MCP Server by RoxyAPI

  Draw 1-78 tarot cards from the complete Rider-Waite-Smith deck with seeded reproducibility for consistent personalized readings. Provide an optional seed string (like "user123-2025-12-27" or "readingId") to ensure the same seed always returns identical cards in the exact same order - essential for daily tarot features, personalized user experiences, shareable readings, or reproducible testing. Omit seed for true random draws each time. Control card reversals (upright vs reversed/inverted orientations - reversed cards provide alternative meanings when drawn upside down) and duplicates (traditional deck draws each of 78 cards once, or oracle-style allows repeating same card). Each drawn card includes position number, reversal state (boolean), keywords for quick interpretation, full meaning text (400+ words), authentic Rider-Waite imagery, and card metadata. Perfect for custom spread builders, random card generators, automated tarot reading platforms, daily card features, meditation apps, journaling prompts, divination tools, and any application requiring reproducible or random tarot draws from the industry-standard 78-card deck (22 Major Arcana spiritual lessons + 56 Minor Arcana practical guidance across 4 suits).

  Connector

• classify_intent

  ContextOverflow

  Describe what's going wrong — your human's complaint, or a failure you notice in your own behavior — and get the matching techniques. Deterministic matching; if the description fits two problems it returns one clarifying question instead of guessing.

  Connector

• test_skill_trigger

  agent4.io

  Reality-check whether your prompts actually trigger tool calls (dry-run) — run this after writing/changing a skill instead of counting corpses in production. Replays your messages N times against the **production** system-prompt assembly, tool schemas and this tenant's actual model routing, capturing only the model's tool-call decision: **tool side effects are NOT executed**, no session is stored. Tokens count toward the tenant quota (messages≤5, samples≤5, at most 25 calls per invocation — pick test messages carefully). Two modes for the skill's two battlefields: - loaded=false (default): first turn, skill not loaded — tests whether the trigger in description works; - loaded=true: simulates post-load_skill — tests the quality of instructions (incl. few-shot examples). Returns per-message hit counts plus claimed_without_call (the model said "noted" WITHOUT calling the tool — the worst failure, fix first). Cover edge cases in your test messages: numbers with spaces, buried in long questions, corrections, email-only. The loop: create_skill → check warnings (static lint) → test_skill_trigger (dynamic reality check) → adjust description / add examples → re-test until the hit rate holds.

  Connector

• show_trace

  mcp

  Fetch one agent trace by id (or id prefix — first 8 chars are usually enough). Returns the full transcript: prompts, steps, tool calls, final output.

  Connector

• generate_asset

  Mozaika

  Generate ON-BRAND icons with AI: subjects (1-12 short nouns, e.g. ["settings gear", "credit card"]) rendered in ONE consistent style. style_from is either a decoded domain ("stripe.com" — the icons match that brand's MEASURED style: accents, stroke, corners) or a house style key ("skeuomorph"). INCLUDED with your account — free accounts get a real daily allowance (enough for a full set), Pro/Lifetime a high one; QA-failed images never count. Returns image_url per subject (1024px transparent PNG) + a zip link.

  Connector

• my_actors

  designforyou

  List only the authenticated user's private reusable LetMeActForYou actors, newest first. Free. Supports bounded offset pagination and never returns internal identity prompts or visual descriptions.

  Connector

• update_application

  FlowCastle

  Update application-level settings (name, active state, default language, incoming-message behavior). Requires the manage_settings permission in that application. Only the fields you pass are changed; omitted fields keep their current value, so the call is idempotent. Returns the updated application.

  Connector

• update_tracker

  Epovest

  Update the configuration of a tracker: only the fields you send change. Keywords, analysts and the title apply in place. Changing the prompts, engines, frequency or resolution of a tracker that has measured creates a new version: the score series continues across versions, and the response carries the new tracker id (version_created says when). A sent list replaces the previous one entirely.

  Connector

• report_card_start

  Whetstone

  TIER 1: start a disposable report-card session. Returns exam items (graph-repair prompts minted from the repository's public frontier) for THIS agent to answer. Answer every item, then call report_card_submit exactly once. Sessions are one-shot, expire in 15 minutes, and are strictly rate-limited. This demonstrates the promotion-gate mechanism on disposable items; it is not a private-bank credential.

  Connector

• get_help

  Forge Engine

  Forge how-to on demand (no project needed): propose→adopt, what a System is, Balance Lab formats, sign-in. Call when unsure.

  Connector

• medcode_check_code

  medical-codes-mcp-server

  Validate whether a US medical code exists, is current, and is billable in the active bundled release. Returns a discriminated status — valid_billable, valid_not_billable, valid_header, or terminated — with a `whyNot` explaining non-billable and terminated cases (e.g. "valid ICD-10-CM category but not billable — submit a more specific child code"). This is the detail a coder needs before submitting a claim. Auto-detects the system from the code's shape; pass an explicit `system` to disambiguate. A non-billable or terminated code is a successful result with a whyNot, not an error — only a code that exists in no bundled system raises unknown_code.

  Connector

• digest_declassified

  Storyflo

  Return the most-recently-published Declassified cases over a rolling window. Use for 'what's new in Declassified this week' style prompts. window=today (~24h) | week (default) | month. Public — no auth required.

  Connector