{"mcp":"Streamable HTTP endpoint. POST JSON-RPC 2.0 here (initialize, tools/list, tools/call).","server":{"$schema":"https://static.modelcontextprotocol.io/schemas/2025-07-09/server.schema.json","name":"com.listeningmind/icss","title":"Intent Panel Survey","description":"Intent Panel Survey (IPS) groups consumers who share the same job to be done and the same detailed context into intent groups, and lets you ask those groups surveys and FGDs as many times as you need. Respondents are sampled with ICSS (Intent-Conditioned Silicon Sampling) from intent states observed in search behavior (CEP, nano intent, KBF, constraint, avoidance, consideration, journey stage) instead of demographics, for surveys, FGDs and 1:1 chats. Marketers and researchers use it to test hypotheses before real fieldwork. Data comes from ListeningMind search data (DaaS, SERP) plus stored CEP Finder and Intent KG runs, for Korea, Japan and the US. It also includes a distinctive brand asset (DBA) recognition test.","version":"1.0.0","serverInfo":{"name":"Intent Panel Survey","version":"1.0.0"},"protocolVersion":"2025-06-18","remotes":[{"type":"streamable-http","url":"https://daas-icss.listeningmind.ai/mcp"}],"tools":[{"name":"get_config","description":"Returns which back-ends are switched on: llm (bool), provider, chain, model, daas (bool), maistro (bool). Call first; if llm is false the survey, FGD and question generation cannot run."},{"name":"start_study","description":"Starts one Intent Panel Survey study and returns {study_id, expires_at}. This is the app's only paid call: a study costs the Intent Panel Survey price once (the open-sale price while the sale runs), however many calls it makes and however long it takes. Every data call of the same study (analyze_topic, get_keyword_info, compare_brands, get_category_journey, probe_ai_overview, get_cluster_serp, start_cep_build, build_grounding_pack, build_grounding_pack_new) carries the id in the X-IP-Study header or the study_id field and costs nothing more, so adding keywords, re-reading, extra collection, surveys and FGDs stay inside the study. A study lasts until a new one is started or 72 hours pass. Ask a person before calling it."},{"name":"analyze_topic","description":"Pulls the full search-behavior analysis for one keyword (demand, gender/age audience, search journeys, behavior clusters, SERP) from the maistro-lmpipe analyze service. This is the first data step of the app; the UI calls it once per keyword and merges the results in the browser. Cached on the server for 12 hours. Returns the raw analysis JSON."},{"name":"get_keyword_info","description":"Calls the ListeningMind keyword_info endpoint through the app proxy: monthly volume, trend, competition, CPC, gender/age demography and intents for a list of keywords. The UI uses it to add demography and volume to the chosen cluster keywords. Cached 12 hours."},{"name":"get_evidence","description":"Looks up existing CEP Finder runs and Intent KG runs that match the topic and returns a short evidence summary (top CEPs with keywords, KBF, constraints, brands; KG nodes such as KBF, CEP, heuristics, pitfalls). Reads stored runs only, never builds. Returns {topic, locale, cep, kg, cep_error, kg_error}."},{"name":"compare_brands","description":"Runs the maistro-lmpipe compare analysis for 2 to 5 brands or items in one market (search demand, audience and intent side by side). The UI starts it when the user enters comparison items. Cached 12 hours."},{"name":"get_category_journey","description":"Calls the maistro-lmpipe category scope analysis that the UI uses as the substrate for the 5-stage consumer decision journey (CDJ) view. Returns the top_n category keywords with stage signals. Cached 12 hours."},{"name":"get_analysis_prompt","description":"Fetches a purpose-specific analysis prompt template from maistro-lmpipe (first 4,000 chars of analysis_prompt). The UI uses it to build insight prompts. Returns {id, analysis_prompt, version}."},{"name":"probe_ai_overview","description":"Collects Google AI Overview and People Also Ask text for the keyword plus probe queries such as 'keyword + downsides / side effects / caveats' in the market language. The UI uses it to fill category-specific avoidance and decision criteria in the intent state vector. Returns {keyword, gl, queries, aio:[{text, from}], paa:[{q, from}]}."},{"name":"get_cluster_serp","description":"For up to 6 keywords of the chosen search cluster, collects AI Overview text, People Also Ask, people-also-search-for and top organic titles, merged and de-duplicated. The UI uses it when a custom panel is built from one cluster. Returns {aio, paa, pasf, organic, per_keyword, n_keywords}."},{"name":"find_cep_run","description":"Searches the CEP Finder run history for a run that matches the topic in the same market (prefers deep over standard over quick, and the market language). Free. Returns {found, run, candidates:[{run_id, topic, keyword, gl, depth, score}]}."},{"name":"get_cep_states","description":"Converts a CEP Finder run (cep_map) into the ICSS intent-state distribution: per CEP weight, volume, nano intents, KBF, constraints, avoidances, alternatives, thresholds, brands, journey, demography with evidence labels. This is P(IntentState) used to sample the synthetic panel. Free."},{"name":"start_cep_build","description":"Starts a new CEP Finder analysis for the keyword when no stored run exists. Returns {job_id}; poll get_cep_job, then call get_cep_states with the finished run_id. Spends Data API credits."},{"name":"get_cep_job","description":"Returns the CEP Finder job state: status, progress [{pct, msg, stage}] and run_id when finished. Repeat until status is done, completed or error."},{"name":"get_grounding_pack","description":"Reads the stored deep-grounding pack for a topic and market (CEP map states, related CEP runs, KG nodes and sentences with evidence grades, sufficiency verdict, credits). Returns {found:false} when none exists. Use full=1 for the whole pack as the UI does."},{"name":"list_grounding_packs","description":"Lists all stored grounding packs: {items:[{topic, gl, built_at, sufficiency, stats, credits}]}."},{"name":"build_grounding_pack","description":"Builds and saves a grounding pack from existing CEP Finder and Intent KG runs for the topic and related topics, without starting any new build (0 credits). Returns {job_id}; poll get_grounding_job."},{"name":"build_grounding_pack_new","description":"Same as build_grounding_pack but also starts a new CEP Finder build (cep_build) and/or a new Intent KG build (kg_build) when stored runs are missing. Requires confirm_credits=true, which this tool sends. Returns {job_id}; poll get_grounding_job."},{"name":"get_grounding_job","description":"Returns the grounding job: status (running, done, error), stage (start, cep, kg, related, assemble), steps log, and a pack summary when done. Repeat until done or error, then call get_grounding_pack with full=1."},{"name":"ask_llm","description":"Sends one prompt to the server LLM chain (Gemini first, then OpenAI on failure; 75 s limit per provider) and returns {text, provider}. The UI builds every synthetic-respondent prompt in the browser (state-first persona: CEP, nano intent, KBF, constraint, avoidance, consideration, journey, then demography as reference) and calls this for question suggestions, survey batches, open-answer theming, FGD turns and summaries. An agent must build those prompts itself."},{"name":"save_run","description":"Saves a full session snapshot (data, panel, questions, results, FGD log, chats) on the server so it opens at /#run=<id> on any PC. The UI does this automatically after a survey finishes. The id must match run_<letters/digits/_ 6-64>. Body limit 25 MB. Returns {ok, id, bytes}."},{"name":"list_runs","description":"Lists stories saved on the server, newest first: {runs:[{id, q, locale, label, n, mode, at, panelMeta, hasResults, fgdN, chatN, bytes}], total}."},{"name":"get_run","description":"Returns the full saved snapshot of a story (cur, panel, questions, results, fgd, chatLogs, gateLog, dba)."},{"name":"delete_run","description":"Moves a saved story to the server trash; it disappears from every PC's archive. Returns {ok, id}."},{"name":"check_asset_masking","description":"Brand asset test (DBA) step 1: checks that each asset description contains no target or competitor brand name and, for images, transcribes visible text with a vision model to detect brand names. Returns {assets:[{id, img}], checks:[{id, ok, textLeaks, imageText, imageLeaks, note}]}. Uploaded data-URL images are stored and replaced by /api/dba/img paths."},{"name":"start_dba_ai_test","description":"Brand asset test, AI-response mode: asks Gemini and OpenAI directly (no persona) 'which brand is this?' for every masked asset, reps times per model, then scores fame and uniqueness on first-mentioned brand and saves the test. This is a GEO metric, not consumer response. Returns {job}; poll get_dba_job."},{"name":"get_dba_job","description":"Returns {id, status (running, done, error), done, total, error, testId} and, when done, the full scored test. Repeat until done or error."},{"name":"ask_dba_llm","description":"One vision-capable LLM call used by the synthetic-panel asset test: the UI sends a batch prompt built from ICSS personas plus up to 4 images and parses brand answers. Returns {text, provider, model}."},{"name":"score_dba_synthetic","description":"Scores synthetic-panel answers (fame, uniqueness, quadrant, baseline) and saves the test. Send the same test fields plus responses collected with ask_dba_llm. Returns {test}."},{"name":"list_dba_tests","description":"Lists saved brand-asset tests with per-asset fame, uniqueness and quadrant. Filter by brand (exact name or alias), locale and kind. Returns {tests, total, providers}."},{"name":"get_dba_test","description":"Returns one saved test in full: brand, assets, responses, per-asset results, baseline, disclaimer."},{"name":"get_dba_image","description":"Downloads a stored stimulus image referenced by a test asset (img field /api/dba/img/<name>)."}],"documentation":"https://daas-icss.listeningmind.ai/llms.txt"},"docs":"https://daas-icss.listeningmind.ai/llms.txt"}