// MCP TOOL REFERENCE

HEISTA TOOLS

69 tools from the Heista MCP Server, categorised by risk level.

View the Heista policy → Token cost: 29,371 tokens →
// ALL 69 HEISTA TOOLS
READ 55 tools
Read adformula_intelligence Browse proven ad formula blueprints — structural patterns clustered from 3-10+ winning ads that independent... Read check_balance Check the calling user's Heista API credit balance, month-to-date usage broken down by operation, lifetime ... Read decode_ad Decode a specific video ad URL into its full structural formula — beat-by-beat breakdown, hook classificati... Read dispatch_desk_researcher Dispatch to the DESK RESEARCHER — source-grounded synthesis on a topic landscape. Use for: "what is known a... Read dispatch_desk_researcher_async Dispatch to the DESK RESEARCHER — source-grounded synthesis on a topic landscape. Use for: "what is known a... Read dispatch_market_analyst Dispatch to the MARKET ANALYST — entity-deep teardown of a named brand or vendor. Use for: "what is brand X... Read dispatch_market_analyst_async Dispatch to the MARKET ANALYST — entity-deep teardown of a named brand or vendor. Use for: "what is brand X... Read dispatch_qualitative_researcher Dispatch to the QUALITATIVE RESEARCHER — thematic synthesis from unstructured text (interviews, reviews, fo... Read dispatch_qualitative_researcher_async Dispatch to the QUALITATIVE RESEARCHER — thematic synthesis from unstructured text (interviews, reviews, fo... Read dispatch_quantitative_researcher Dispatch to the QUANTITATIVE RESEARCHER — numerical analysis with full methodology context. Use for: briefs... Read dispatch_quantitative_researcher_async Dispatch to the QUANTITATIVE RESEARCHER — numerical analysis with full methodology context. Use for: briefs... Read dispatch_social_listening_researcher Dispatch to the SOCIAL LISTENING RESEARCHER — multi-platform community-signal interpretation. Use for: "wha... Read dispatch_social_listening_researcher_async Dispatch to the SOCIAL LISTENING RESEARCHER — multi-platform community-signal interpretation. Use for: "wha... Read dispatch_trend_researcher Dispatch to the TREND RESEARCHER — recency-dominant trajectory investigation. Use for: "is X a real trend /... Read dispatch_trend_researcher_async Dispatch to the TREND RESEARCHER — recency-dominant trajectory investigation. Use for: "is X a real trend /... Read fetch_url Drill into a specific URL after search surfaces it. Returns the extracted text content plus metadata. Inter... Read get_ad_formula_preset Get one ad formulas preset by id, including its full body payload (framework, agent config, etc.). Call the... Read get_brand Get a brand's full canonical record — name, domain, voice (tone_of_voice), story, visual identity (logo, pr... Read get_creative_agent_preset Get one creative agents preset by id, including its full body payload (framework, agent config, etc.). Call... Read get_creative_director_playbook_preset Get one creative director playbooks preset by id, including its full body payload (framework, agent config,... Read get_decode Retrieve the full decode bundle for a previously-submitted ad, or poll the status of a running decode job. ... Read get_decoded_ad_preset Get one decoded ads preset by id, including its full body payload (framework, agent config, etc.). Call the... Read get_dispatch_result Get the current status of a specialist dispatch job started via dispatch_<specialist>_async. Returns { stat... Read get_hook_intelligence Browse proven hook patterns from Heista's corpus of decoded winning Meta/TikTok ads. Takes optional filters... Read get_image_ad_scan_preset Get one static ads preset by id, including its full body payload (framework, agent config, etc.). Call the ... Read get_powersource Retrieve the full creative intelligence profile for a previously-submitted PowerSource scan, or poll the st... Read get_saved_asset Fetch one saved asset by id. Returns the full row including category, format, tags, body_text/html, signed ... Read get_saved_assets_batch Fetch up to 50 saved assets by id in one round-trip. Use when an agent needs to pull a pre-selected set — e... Read get_saved_visual_idea_preset Get one saved visual ideas preset by id, including its full body payload (framework, agent config, etc.). C... Read get_strategy Read a creative strategy in full by its powersource_id. Returns the same brand-merged bundle shape as get_p... Read get_visual_preset_preset Get one visuals preset by id, including its full body payload (framework, agent config, etc.). Call the mat... Read get_visual_style_preset Get one visual styles preset by id, including its full body payload (framework, agent config, etc.). Call t... Read list_ad_formula_presets Cluster-level structural formulas derived from decoded ads. Heista-curated; served as a generation paramete... Read list_brand_assets List images for a brand. Filter by PowerSource (this scan only, via powersource_id), by on-pack product_nam... Read list_brand_documents List indexed brand documents for a brand. Each row carries the indexed signals (doc_type, summary, key_topi... Read list_brands List every brand in this workspace. Use this BEFORE creating a PowerSource to avoid creating duplicate bran... Read list_creative_agent_presets Reusable creative agents the Heist can pick as a handoff target — picked from the UI, callable as an MCP to... Read list_creative_director_playbook_presets Seven-section creative-mechanism lenses the Creative Director chat picks at session start. The picked playb... Read list_decoded_ad_presets Structural references for script-led Heists. Workspace decodes (your video_sources scans joined with their ... Read list_image_ad_scan_presets Static-ad references for image-led Heists. Workspace static scans + Heista-curated image ad heists. Read-on... Read list_saved_assets List saved assets in the workspace. Filter by category (STRATEGY, IDEAS, COPY, VISUALS, MOTION, BRIEFS), by... Read list_saved_visual_idea_presets Visual ideas you saved from prior generations. Workspace-only. Read-only, free. Filter scope with only_work... Read list_skills List skills available in the Heista skill library. Returns name, description, domain (shared / image / vide... Read list_strategies List all PowerSource strategies (scans) for a brand. A brand has many strategies — one per scanned URL. Pro... Read list_strategy_audiences List audience archetypes for a strategy (PowerSource). Returns the Buyer Decoder archetype (source="buyer_p... Read list_strategy_tones List tone profiles for a strategy. Today returns at most one entry — the tone_of_voice synthesized by the T... Read list_visual_preset_presets Heista-curated visual heists (style DNA + photography presets). Official-only today; workspace-saved preset... Read list_visual_style_presets Saved style configs picked into image-led Heists. Workspace = org-owned styles. Official = canonical Heista... Read load_skill Load the full SKILL.md body for one skill by canonical dot-notation name (e.g. "research.foundation", "rese... Read load_skill_reference Load one reference file from a register-type skill's references/ folder (e.g. "m1-narrative.md" from "share... Read perplexity_search Web-grounded search via Perplexity Sonar Pro. Returns synthesized answer text plus a structured sources[] a... Read read_brand_document Read one indexed brand document. Returns the indexed metadata (doc_type, summary, key_topics, entities, key... Read search General-purpose web grounding via parallel.ai (Vercel AI Gateway). Returns synthesized text excerpts plus s... Read search_community Community-discourse search via parallel.ai with optional platform filtering. Returns synthesized text excer... Read search_research Structured fact-check + numerical research via Perplexity Sonar Reasoning Pro (Gateway-routed). Returns syn...
WRITE 9 tools
Write add_brand_asset Upload an image to a brand by URL. The pipeline downloads it, runs the vision tagger (classifies type, dete... Write call_creative_worlds Heista's creative direction engine — same engine the Creative Director specialist runs internally, exposed ... Write create_powersource_docs Build a complete creative intelligence profile from internal brand documents — creative briefs, brand guide... Write create_powersource_full Build the highest-fidelity creative intelligence profile by combining a brand's public website URL with the... Write create_powersource_url Build a complete creative intelligence profile of a brand from a single website URL. Takes a website URL (h... Write decoder_intelligence Browse individual decoded ads from Heista's corpus of real winning Meta/TikTok creative. Takes optional fil... Write favorite_saved_asset Toggle the favorite flag on a saved asset. Pass is_favorite=true to favorite, false to unfavorite. favorite... Write generate_adscript Generate direct-response video ad scripts by fusing a proven structural source (decoded ad or formula) with... Write save_asset Persist a new saved asset to the workspace. category MUST be one of STRATEGY, IDEAS, COPY, VISUALS, MOTION ...
DESTRUCTIVE 2 tools
Destructive delete_brand_asset Delete one brand asset by asset_id. Removes the brand_assets row and (when the asset was uploaded rather th... Destructive delete_saved_asset Delete one saved asset by id. Destructive — confirm with the user before calling. OAuth callers can only de...
EXECUTE 3 tools
Execute chat_with_creative_worlds Multi-turn conversation with Heista's creative direction engine — a real chat where the agent decides each ... Execute dispatch_head_of_research Run a full research workflow via the Head of Research agent. The Head decomposes your brief into specialist... Execute retag_brand_asset Re-run the vision tagger on one brand asset. Reads the stored object when present (uploaded assets) or the ...
// FAQ
How many tools does the Heista MCP server have? +

The Heista MCP server exposes 69 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Heista tools? +

Route the Heista server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Heista tools fall into? +

Heista tools are categorised as Read (55), Write (9), Destructive (2), Execute (3). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.