Summary
Connects Claude and other MCP clients to expert-curated knowledge graphs from PSFK covering retail, beauty, sports, and institutional datasets. Exposes seven tools: hybrid search across graphs, neighbor traversal for exploring relationships, evidence retrieval with source provenance, node metadata lookups, and trend discovery. Runs over stdio or SSE with Bearer token auth. Useful when you need structured industry intelligence backed by editorial curation rather than raw web scraping. The get_neighbors and discover_adjacent_trends tools let you walk concept networks to surface non-obvious connections between brands, behaviors, and market signals. Deployed via npm package or self-hosted container.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Tools
Public tool metadata for what this MCP can expose to an agent.
30 tools
get_my_accountCheck the current user's account status: API call balance, plan, enabled/disabled graphs, and profile info. Use when the user asks "how many API calls do I have?", "what plan am I on?", "what graphs can I access?", or similar account questions. Returns live data — not cached f...
Check the current user's account status: API call balance, plan, enabled/disabled graphs, and profile info. Use when the user asks "how many API calls do I have?", "what plan am I on?", "what graphs can I access?", or similar account questions. Returns live data — not cached f...
No parameter schema in public metadata yet.
list_graphsList all knowledge graphs the user can access — IDs, descriptions, authors, sectors, signal counts. Use FIRST in any session to discover available sources before searching. Returns graph metadata needed for graphId parameters in other tools. Deprecated: waldo, psfk (use retail...1 params
List all knowledge graphs the user can access — IDs, descriptions, authors, sectors, signal counts. Use FIRST in any session to discover available sources before searching. Returns graph metadata needed for graphId parameters in other tools. Deprecated: waldo, psfk (use retail...
Parameters* required
userIdstringOptional user identifier. Authenticated users are identified automatically via API key. For trial users, this helps track usage.
list_analystsList available Synthetic Analysts — named expert personas grounded in specific knowledge graphs. Each analyst has a unique voice, methodology, and domain expertise that cannot be replicated by web search. Use when user asks to "talk to" or "consult" an expert, or when you need...1 params
List available Synthetic Analysts — named expert personas grounded in specific knowledge graphs. Each analyst has a unique voice, methodology, and domain expertise that cannot be replicated by web search. Use when user asks to "talk to" or "consult" an expert, or when you need...
Parameters* required
userIdstringOptional user identifier.
search_graphSearch expert-curated knowledge graphs for trend clusters, signals, and consumer behavior evidence across retail, beauty, luxury, fashion, sport, consumer electronics, F&B, travel, and 30+ specialist domains. Returns structured trend data with cited evidence chains, source att...7 params
Search expert-curated knowledge graphs for trend clusters, signals, and consumer behavior evidence across retail, beauty, luxury, fashion, sport, consumer electronics, F&B, travel, and 30+ specialist domains. Returns structured trend data with cited evidence chains, source att...
Parameters* required
limitnumberMaximum number of results (default 10, max 50)
querystringThe search query. Location terms are auto-detected and used to filter results geographically.
userIdstringOptional user identifier for trial usage tracking.
graphIdstringOptional graph ID. If omitted, searches ALL accessible graphs. Examples: 'retail', 'beauty', 'sports', 'sic', 'pew', 'ce-design', 'ezra-eeman-wayfinder', 'dhl-ecommerce-trends-2026', 'automotive-color-trends', 'alyson-stevens-macro', 'generative-realities', 'pwc/sxsw-2026-key-insights', 'green-house/thrive-report', 'delta/the-connection-index'
skip_skillsbooleanIf true, skip applying any enabled skills (Paralogy, Igloo, etc.) for this query only. Use when the user says "without skills", "skip Paralogy", or "just the raw results". Default: false.
use_semanticbooleanWhether to use semantic search (default true)
include_evidencebooleanIf true, batch-fetch supporting evidence articles inline with results. Default: true.
get_neighborsTraverse graph relationships from a specific trend node to discover connected signals, brands, technologies, and locations. Returns structured relationship data that web search cannot provide — the curated editorial connections between trends. Use after search_graph to map the...7 params
Traverse graph relationships from a specific trend node to discover connected signals, brands, technologies, and locations. Returns structured relationship data that web search cannot provide — the curated editorial connections between trends. Use after search_graph to map the...
Parameters* required
depthnumberTraversal depth (default 1, max 2)
limitnumberMaximum results (default 50)
userIdstringOptional user identifier for trial usage tracking.
graphIdstringThe graph ID. Use list_available_graphs to see all options. Examples: 'retail', 'beauty', 'sports', 'sic', 'pew', 'ce-design', 'ezra-eeman-wayfinder', 'dhl-ecommerce-trends-2026', 'automotive-color-trends', 'alyson-stevens-macro', 'generative-realities', 'pwc/sxsw-2026-key-insights', 'green-house/thrive-report', 'michaels-2026-creativity-trend-report', 'delta/the-connection-index'
directionstringTraversal direction: 'out' (default) follows outgoing edges, 'in' follows incoming edgesone of
in · outseed_node_idsarrayArray of node IDs to start traversal from. MUST be actual node_id values from a prior search_graph result (e.g. ["2507.0"]). Node IDs are NOT sequential integers — do NOT guess or invent IDs like "1", "2", "3". Always call search_graph first to obtain valid IDs.
relationship_typesarrayFilter by relationship types: 'EVIDENCED_BY', 'RELATED_TO', 'SEMANTICALLY_SIMILAR', 'ASSOCIATED_BRAND', 'MENTIONS_BRAND', 'IN_LOCATION'
get_evidenceRetrieve curated source articles and structured evidence for a specific trend node — case studies, statistics, expert quotes, and analysis with full source attribution. Returns evidence that has been editorially selected and categorized, not raw web results. Each item includes...4 params
Retrieve curated source articles and structured evidence for a specific trend node — case studies, statistics, expert quotes, and analysis with full source attribution. Returns evidence that has been editorially selected and categorized, not raw web results. Each item includes...
Parameters* required
top_knumberNumber of evidence items to return (default 5)
userIdstringOptional user identifier for trial usage tracking.
graphIdstringThe graph ID. Use list_available_graphs to see all options. Examples: 'retail', 'beauty', 'sports', 'sic', 'pew', 'ce-design', 'ezra-eeman-wayfinder', 'dhl-ecommerce-trends-2026', 'automotive-color-trends', 'alyson-stevens-macro', 'generative-realities', 'pwc/sxsw-2026-key-insights', 'green-house/thrive-report', 'michaels-2026-creativity-trend-report', 'delta/the-connection-index'
for_node_idstringThe node_id from a prior search_graph result (e.g. '2507.0'). MUST come from the search result's node_id field. Node IDs are NOT sequential integers — do NOT guess or invent IDs like '1', '2', '3'. Do NOT pass the trend name.
get_nodeRetrieve complete metadata for a specific trend node — full description, signal score, lifecycle, geographic scope, adjacent possibilities, and all properties. Use when you need the full detail on a single trend after search_graph returned a summary. Requires node_id from a pr...3 params
Retrieve complete metadata for a specific trend node — full description, signal score, lifecycle, geographic scope, adjacent possibilities, and all properties. Use when you need the full detail on a single trend after search_graph returned a summary. Requires node_id from a pr...
Parameters* required
nodeIdstringThe node_id from a prior search_graph result (e.g. '2507.0'). MUST come from the search result's node_id field. Node IDs are NOT sequential integers — do NOT guess or invent IDs like '1', '2', '3'. Do NOT pass the trend name.
userIdstringOptional user identifier for trial usage tracking.
graphIdstringThe graph ID. Use list_available_graphs to see all options. Examples: 'retail', 'beauty', 'sports', 'sic', 'pew', 'ce-design', 'ezra-eeman-wayfinder', 'dhl-ecommerce-trends-2026', 'automotive-color-trends', 'alyson-stevens-macro', 'generative-realities', 'pwc/sxsw-2026-key-insights', 'green-house/thrive-report', 'michaels-2026-creativity-trend-report', 'delta/the-connection-index'
get_label_valuesList all values for a structured category within a graph — Brand names, Locations, Technologies, Audiences, RetailerTypes. Use when you need to enumerate what entities exist in a graph before filtering, or when the user asks "what brands are in the retail graph?" or "what loca...4 params
List all values for a structured category within a graph — Brand names, Locations, Technologies, Audiences, RetailerTypes. Use when you need to enumerate what entities exist in a graph before filtering, or when the user asks "what brands are in the retail graph?" or "what loca...
Parameters* required
labelstringThe label to fetch values for (e.g., 'Brand', 'Location', 'Technology', 'Audience', 'RetailerType', 'Trend')
userIdstringOptional user identifier for trial usage tracking.
graphIdstringThe graph ID. Use list_available_graphs to see all options. Examples: 'retail', 'beauty', 'sports', 'sic', 'pew', 'ce-design', 'ezra-eeman-wayfinder', 'dhl-ecommerce-trends-2026', 'automotive-color-trends', 'alyson-stevens-macro', 'generative-realities', 'pwc/sxsw-2026-key-insights', 'green-house/thrive-report', 'michaels-2026-creativity-trend-report', 'delta/the-connection-index'
propertystringOptional property to return values for. Defaults vary by label.
discover_adjacent_trendsFind trends semantically similar to a given trend using pre-computed embeddings — surfaces connections that keyword search would miss. Returns scored similarity matches and optionally editorial links across graphs. Use to expand research briefs, discover unexpected cross-domai...6 params
Find trends semantically similar to a given trend using pre-computed embeddings — surfaces connections that keyword search would miss. Returns scored similarity matches and optionally editorial links across graphs. Use to expand research briefs, discover unexpected cross-domai...
Parameters* required
limitnumberMaximum number of adjacent trends to return. Default: 10
userIdstringOptional user identifier for trial usage tracking.
graphIdstringThe graph ID. Use list_available_graphs to see all options. Examples: 'retail', 'beauty', 'sports', 'sic', 'pew', 'ce-design', 'ezra-eeman-wayfinder', 'dhl-ecommerce-trends-2026', 'automotive-color-trends', 'alyson-stevens-macro', 'generative-realities', 'pwc/sxsw-2026-key-insights', 'green-house/thrive-report', 'michaels-2026-creativity-trend-report', 'delta/the-connection-index'
trend_idstringThe node_id from a prior search_graph result (e.g. '2507.0'). MUST come from the search result's node_id field. Node IDs are NOT sequential integers — do NOT guess or invent IDs like '1', '2', '3'. Do NOT pass the trend name.
min_scorenumberMinimum similarity score threshold (0-1). Default: 0.80
include_editorialbooleanIf true, also include editorially linked trends. Default: false
brand_trackerBuild a complete Brand Intelligence Profile by searching ALL knowledge graphs for a specific brand. Returns trend footprint (which trends the brand appears in), competitive landscape (co-occurring brands ranked by overlap), cross-graph presence, evidence timeline, lifecycle di...5 params
Build a complete Brand Intelligence Profile by searching ALL knowledge graphs for a specific brand. Returns trend footprint (which trends the brand appears in), competitive landscape (co-occurring brands ranked by overlap), cross-graph presence, evidence timeline, lifecycle di...
Parameters* required
userIdstringOptional user identifier for trial usage tracking.
graph_idsarrayOptional: specific graph IDs to search. If omitted, searches ALL accessible graphs.
brand_namestringThe brand name to look up (e.g. 'Nike', 'Adidas', 'Apple'). Case-insensitive.
max_evidencenumberMaximum evidence items per graph. Default: 10. Max: 25.
include_evidencebooleanIf true (default), include individual evidence items. Set to false for summary-only.
get_supplemental_contextGet institutional market data from up to 10 sources in a single call. The server automatically selects the most relevant sources based on your query and domain — economic indicators, trade data, product landscape, food economics, agricultural production, nutritional compositio...5 params
Get institutional market data from up to 10 sources in a single call. The server automatically selects the most relevant sources based on your query and domain — economic indicators, trade data, product landscape, food economics, agricultural production, nutritional compositio...
Parameters* required
querystringThe topic or query to get supplemental data for (e.g., 'sustainable packaging', 'tequila spirits market', 'Gen Z beauty')
brandsarrayBrand names to include in demand/product lookups (e.g., ['Nike', 'Adidas']). Triggers Google Trends comparison and Amazon product search.
domainstringDomain hint to improve source routing: 'retail', 'beauty', 'fashion', 'sports', 'food', 'technology', 'culture', 'travel', 'design'. If omitted, inferred from query.
userIdstringOptional user identifier for trial usage tracking.
graph_idsarrayGraph IDs from prior search results — helps refine domain inference.
check_supplemental_statusCheck the status of a long-running supplemental data gathering job. If complete, this tool returns the full JSON data payload. You MUST poll this periodically until the status is COMPLETE or FAILED.1 params
Check the status of a long-running supplemental data gathering job. If complete, this tool returns the full JSON data payload. You MUST poll this periodically until the status is COMPLETE or FAILED.
Parameters* required
job_idstringThe Job ID returned by get_supplemental_context
get_domain_intelligenceSearch PSFK-curated domain graphs (retail, beauty, fashion, sports, consumer electronics, F&B) for trend intelligence with bundled evidence. No graph ID needed — searches all relevant domain graphs in parallel. Returns expert-curated trends with categorized evidence (statistic...6 params
Search PSFK-curated domain graphs (retail, beauty, fashion, sports, consumer electronics, F&B) for trend intelligence with bundled evidence. No graph ID needed — searches all relevant domain graphs in parallel. Returns expert-curated trends with categorized evidence (statistic...
Parameters* required
limitnumberMax trends to return (default: 10, max: 50)
querystringNatural language search query (e.g., 'sustainable packaging trends', 'Gen Z beauty habits')
userIdstringOptional user identifier for trial usage tracking.
min_scorenumberMinimum relevance threshold (default: 0.6)
include_evidencebooleanBundle evidence for each trend (default: true)
max_evidence_per_trendnumberEvidence items per trend (default: 5, max: 20)
get_expert_intelligenceSearch specialist knowledge graphs built by named strategists and industry leaders — contains proprietary analysis, expert interviews, and high-density statistics not available via web search. No graph ID needed — searches all expert graphs in parallel. Use when the query requ...6 params
Search specialist knowledge graphs built by named strategists and industry leaders — contains proprietary analysis, expert interviews, and high-density statistics not available via web search. No graph ID needed — searches all expert graphs in parallel. Use when the query requ...
Parameters* required
limitnumberMax trends to return (default: 10, max: 50)
querystringNatural language search query (e.g., 'tequila spirits market', 'future of work')
userIdstringOptional user identifier for trial usage tracking.
min_scorenumberMinimum relevance threshold (default: 0.6)
include_evidencebooleanBundle evidence for each trend (default: true)
max_evidence_per_trendnumberEvidence items per trend (default: 5, max: 20)
get_report_intelligenceSearch industry report knowledge graphs for published research findings, market forecasts, and quantitative projections from organizations like DHL, PwC, Delta, and specialist research firms. Returns structured findings with bundled evidence — not raw PDFs or summaries, but ed...6 params
Search industry report knowledge graphs for published research findings, market forecasts, and quantitative projections from organizations like DHL, PwC, Delta, and specialist research firms. Returns structured findings with bundled evidence — not raw PDFs or summaries, but ed...
Parameters* required
limitnumberMax trends to return (default: 10, max: 50)
querystringNatural language search query (e.g., 'luxury resale market size', 'electric vehicle adoption rates')
userIdstringOptional user identifier for trial usage tracking.
min_scorenumberMinimum relevance threshold (default: 0.6)
include_evidencebooleanBundle evidence for each trend (default: true)
max_evidence_per_trendnumberEvidence items per trend (default: 5, max: 20)
search_statisticsSearch for specific quantitative data points — market sizes, growth rates, expert quotes, and brand case studies — directly in Fodda's knowledge graphs. Each result includes its parent trend context, enabling reverse lookup: data point → expert trend. Use this BEFORE supplemen...6 params
Search for specific quantitative data points — market sizes, growth rates, expert quotes, and brand case studies — directly in Fodda's knowledge graphs. Each result includes its parent trend context, enabling reverse lookup: data point → expert trend. Use this BEFORE supplemen...
Parameters* required
limitnumberMax results to return (default: 10, max: 50)
querystringWhat data to search for (e.g., 'luxury resale market size', 'secondhand clothing sales volume', 'Gen Z spending behavior')
userIdstringOptional user identifier for trial usage tracking.
graph_idstringGraph ID to search. Works on ALL graphs — PSFK curated ('retail', 'fashion', 'beauty', 'sports', 'sic', 'ce-design', 'pew') AND expert graphs. Search across multiple graphs for best coverage.
min_scorenumberMinimum relevance threshold, 0-1 (default: 0.60). Use 0.60 for broad queries, 0.70+ only for precise data lookups.
include_signalsbooleanAlso include Signal nodes (case studies, brand examples). Default: false
search_insightsSearch for expert quotes, editorial interpretations, and qualitative evidence across knowledge graphs. Returns categorized evidence (metric, quote, interpretation, signal) with source attribution and parent trend context. Works on ALL graphs. Use when you need named-expert voi...6 params
Search for expert quotes, editorial interpretations, and qualitative evidence across knowledge graphs. Returns categorized evidence (metric, quote, interpretation, signal) with source attribution and parent trend context. Works on ALL graphs. Use when you need named-expert voi...
Parameters* required
limitnumberMax results to return (default: 10, max: 50)
querystringNatural language search query. E.g. 'expert views on Gen Z luxury' or 'resale market statistics'
typesstringComma-separated evidence types to search: metric, quote, interpretation, signal, or 'all' (default: 'metric,quote,interpretation')
userIdstringOptional user identifier for trial usage tracking.
graph_idstringGraph ID to search. Works on ALL graphs — PSFK curated ('retail', 'sic', 'beauty', 'sports', 'fashion', 'ce-design', 'pew') AND expert graphs. Search across multiple graphs for best coverage.
min_scorenumberMinimum relevance threshold 0-1 (default: 0.60). Use 0.60 for broad queries, 0.70+ for precise lookups.
get_earnings_intelligenceQuery earnings call intelligence across companies, industries, or sectors. Returns structured evidence from public company earnings calls — management commentary, guidance, key topics, and analyst Q&A. Use for cross-company comparisons ("what are hotel companies saying about l...9 params
Query earnings call intelligence across companies, industries, or sectors. Returns structured evidence from public company earnings calls — management commentary, guidance, key topics, and analyst Q&A. Use for cross-company comparisons ("what are hotel companies saying about l...
Parameters* required
brandstringBrand name for fuzzy matching (e.g., 'Nike', 'Marriott')
limitintegerMax results to return (default 20, max 50)
dateTostringISO date range end (e.g., '2026-06-01')
searchstringFree text search in earnings summaries (e.g., 'labor costs', 'tariff guidance', 'AI investment')
sectorstringSector filter (e.g., 'retail', 'technology', 'travel')
tickerstringCompany stock ticker (e.g., 'NKE', 'LVMUY', 'HLT'). At least one filter required.
userIdstringOptional user identifier for trial usage tracking.
dateFromstringISO date range start (e.g., '2025-01-01')
industrystringIndustry filter (e.g., 'hotels', 'sportswear', 'consumer electronics')
get_earnings_divergenceDetect divergence between analyst concerns and management responses in earnings calls. Surfaces where executives are deflecting, reframing, or avoiding specific topics. Premium intelligence — shows the gap between what Wall Street is worried about and what companies are saying...7 params
Detect divergence between analyst concerns and management responses in earnings calls. Surfaces where executives are deflecting, reframing, or avoiding specific topics. Premium intelligence — shows the gap between what Wall Street is worried about and what companies are saying...
Parameters* required
limitintegerMax results to return (default 10, max 25)
dateTostringISO date range end
searchstringFree text search (e.g., 'tariffs', 'AI capex', 'margin erosion')
sectorstringSector filter (e.g., 'retail', 'technology', 'travel')
userIdstringOptional user identifier for trial usage tracking.
dateFromstringISO date range start
industrystringIndustry filter (e.g., 'hotels', 'sportswear', 'luxury')
update_user_profileSave the user's research profile to improve the relevance of future responses. Call this after you understand the user's role, industry, and research needs. The profile persists across sessions — you only need to set it once, then update if their focus changes. Write BEHAVIORA...2 params
Save the user's research profile to improve the relevance of future responses. Call this after you understand the user's role, industry, and research needs. The profile persists across sessions — you only need to set it once, then update if their focus changes. Write BEHAVIORA...
Parameters* required
userContextstringBehavioral framing instructions for this person. Format: one sentence of identity, then numbered FRAMING INSTRUCTIONS. Example: "Agency strategist doing time-pressured pitches. (1) Lead with landscape orientation — top 3-5 macro forces. (2) Prioritize commercially validated signals over design concepts. (3) ALWAYS differentiate by geography. (4) Executive-ready framing — concise, pitch-deck-ready. (5) Strongest findings first, not exhaustive lists." Max 2000 chars.
accountContextstringDescription of their company: industry, size, key markets, competitive position, mission. Shared across all users on this account. Max 2000 chars.
toggle_graph_preferenceEnable or disable any knowledge graph, supplemental data source, or skill for the user. Use this when the user says "Turn off Paralogy", "Enable igloo", "Disable the economics data", or similar. The change is permanent until toggled again.3 params
Enable or disable any knowledge graph, supplemental data source, or skill for the user. Use this when the user says "Turn off Paralogy", "Enable igloo", "Disable the economics data", or similar. The change is permanent until toggled again.
Parameters* required
enabledbooleantrue to enable (turn on), false to disable (turn off).
target_idstringThe ID of the graph, skill, or data source to toggle (e.g., "paralogy", "igloo", "retail", "get_bea_spending_snapshot"). Use the exact ID from list_graphs.
user_emailstringOptional. Use ONLY when operating as an Admin on behalf of another user to specify their email.
send_feedbackForward user feedback, feature requests, complaints, or exit reasons to the Fodda team via email and Slack. Call this whenever a user shares feedback — including when they want to leave, report a problem, or suggest an improvement.3 params
Forward user feedback, feature requests, complaints, or exit reasons to the Fodda team via email and Slack. Call this whenever a user shares feedback — including when they want to leave, report a problem, or suggest an improvement.
Parameters* required
categorystringCategory: 'feedback', 'bug', 'feature_request', 'exit_reason', 'complaint'
feedbackstringThe user's feedback, complaint, suggestion, or exit reason
user_emailstringUser's email if known (for follow-up)
sign_up_free_accountCreate a Fodda Base account for a trial user who has run out of credits. Call this when a trial user provides their email after being prompted. Creates an account with 100 API calls/month across ALL knowledge graphs and sends a confirmation email. Can also be called with addit...4 params
Create a Fodda Base account for a trial user who has run out of credits. Call this when a trial user provides their email after being prompted. Creates an account with 100 API calls/month across ALL knowledge graphs and sends a confirmation email. Can also be called with addit...
Parameters* required
namestringUser's full name (optional — collect conversationally after signup)
emailstringUser's email address (required)
companystringUser's company name (optional)
job_titlestringUser's job title (optional)
brainstorm_topicExplore and brainstorm around a topic using knowledge graph connections. Unlike search (which finds what matches), this tool discovers what CONNECTS — adjacent trends, unexpected cross-domain links, key brands, and geographic hotspots. Use when the user wants to brainstorm, ex...3 params
Explore and brainstorm around a topic using knowledge graph connections. Unlike search (which finds what matches), this tool discovers what CONNECTS — adjacent trends, unexpected cross-domain links, key brands, and geographic hotspots. Use when the user wants to brainstorm, ex...
Parameters* required
depthnumberTraversal depth: 1 (immediate connections) or 2 (connections of connections). Default: 2. Use 1 for focused brainstorms, 2 for wider exploration.
querystringThe topic or theme to brainstorm around (e.g., 'tequila', 'sustainable packaging', 'Gen Z beauty')
userIdstringOptional user identifier for trial usage tracking.
generate_visualGenerate a branded SVG data visualization from structured insight data. Use after research to create presentation-ready visuals. Available chart types: "cultural_shifts" (From→To transitions), "competitive_compass" (brands on 2 axes), "trend_constellation" (network of related...2 params
Generate a branded SVG data visualization from structured insight data. Use after research to create presentation-ready visuals. Available chart types: "cultural_shifts" (From→To transitions), "competitive_compass" (brands on 2 axes), "trend_constellation" (network of related...
Parameters* required
datastringJSON string containing the chart data. Structure depends on chart_type. cultural_shifts: {shifts:[{from,to}]}. competitive_compass: {brands:[{name,x,y}], axes:{left,right,top,bottom}}. trend_constellation: {trends:[{name,x,y}], connections:[{from,to,strength}]}. implication_ladder: {signal,trend,so_what,do_what}. innovation_pathway: {now,near_term,future}. opportunity_map: {items:[{name,consumer_desire,market_activity}]}
chart_typestringThe type of visualization to generateone of
cultural_shifts · competitive_compass · trend_constellation · implication_ladder · innovation_pathway · opportunity_mapmanage_scheduled_reportsCreate, list, cancel, update, pause, or resume scheduled intelligence briefings. Users can set up autonomous research that runs weekly (Mondays) or daily (Mon-Fri) at 9am in their timezone, delivered via email or Slack. Costs 20 API calls per run. Supports topic research or br...10 params
Create, list, cancel, update, pause, or resume scheduled intelligence briefings. Users can set up autonomous research that runs weekly (Mondays) or daily (Mon-Fri) at 9am in their timezone, delivered via email or Slack. Costs 20 API calls per run. Supports topic research or br...
Parameters* required
emailstringEmail address to deliver reports to
querystringFor "create": the research query to run
actionstringone of
create · list · cancel · update · pause · resumebrandsarrayFor brand_intelligence: brand names to track (e.g., ["Nike", "Patagonia"])
graphsarraySpecific graph IDs to search. Default: all accessible
cadencestringweekly or daily (Mon-Fri). Default: weeklyone of
weekly · dailytimezonestringDelivery timezone for 9am delivery. Default: new_yorkone of
london · new_york · san_francisco · sydneyreport_typestringtopic_research for sector trends, brand_intelligence for competitive trackingone of
topic_research · brand_intelligenceschedule_idstringFor cancel/update/pause/resume: the schedule ID
slack_webhookstringOptional Slack webhook URL for delivery
read_urlExtract clean text content from any URL. Use this when a user shares a link (competitor site, news article, client brief, trend report) and wants to cross-reference it against Fodda knowledge graphs. Returns structured text ready for analysis. Costs 15 API calls.2 params
Extract clean text content from any URL. Use this when a user shares a link (competitor site, news article, client brief, trend report) and wants to cross-reference it against Fodda knowledge graphs. Returns structured text ready for analysis. Costs 15 API calls.
Parameters* required
urlstringThe URL to read and extract content from
userIdstringOptional user identifier for usage tracking.
deep_research_topicLaunch an autonomous Deep Research session that combines Fodda knowledge graph intelligence with live web research to produce a comprehensive editorial-quality report. The Research Agent plans its own strategy, searches multiple graphs, validates with institutional data, and s...4 params
Launch an autonomous Deep Research session that combines Fodda knowledge graph intelligence with live web research to produce a comprehensive editorial-quality report. The Research Agent plans its own strategy, searches multiple graphs, validates with institutional data, and s...
Parameters* required
depthstringResearch depth: "light" for faster single-pass (20 API calls), "heavy" for comprehensive multi-pass (30 API calls). Defaults to "light".one of
light · heavyquerystringThe research query/topic
userIdstringOptional user identifier.
graphIdstringOptional specific graph ID to limit the research to
check_research_statusCheck the status of a long-running deep research job. If complete, this tool returns the final report. You MUST poll this periodically until the status is COMPLETE or FAILED.1 params
Check the status of a long-running deep research job. If complete, this tool returns the final report. You MUST poll this periodically until the status is COMPLETE or FAILED.
Parameters* required
job_idstringThe Job ID returned by deep_research_topic
consult_analystConsult a named Synthetic Analyst who answers in their expert voice using their curated knowledge graph. Each analyst has a unique methodology, domain expertise, and analytical lens that produces insights distinct from generic search or standard graph queries. Use when the use...3 params
Consult a named Synthetic Analyst who answers in their expert voice using their curated knowledge graph. Each analyst has a unique methodology, domain expertise, and analytical lens that produces insights distinct from generic search or standard graph queries. Use when the use...
Parameters* required
querystringThe question or topic to discuss with the analyst
userIdstringOptional user identifier.
analyst_idstringThe analyst ID (e.g., 'ben-dietz-sic')
Fodda MCP Server
Expert-curated knowledge graphs for AI agents — PSFK Retail, Beauty, Sports and partner datasets via the Model Context Protocol.
Quick Start
Claude (Web — Pro, Max, Team, Enterprise)
⚡ Quick Connect: Use this Add to Claude quick link (replace YOUR_API_KEY and YOUR_EMAIL in the URL before pressing enter).
Manual Setup:
- In Claude, go to Settings → Connectors → Add custom connector
- Enter URL:
https://mcp.fodda.ai/mcp?api_key=YOUR_API_KEY&user_id=YOUR_EMAIL - Under Advanced settings — leave OAuth Client ID and Secret blank (Fodda uses API key auth, not OAuth)
- Click Add — then start chatting with your Fodda knowledge graphs
Get your API key at app.fodda.ai → Account → MCP Integration.
Your API key starts withfk_live_...
Use the email address associated with your Fodda account foruser_id.
Claude Code (CLI — SSE)
claude mcp add --transport sse fodda https://mcp.fodda.ai/sse \
--header "Authorization: Bearer YOUR_API_KEY"
Claude Enterprise
For Claude Enterprise with admin-managed connectors, your workspace admin can register the Fodda MCP server using the same Streamable HTTP endpoint (https://mcp.fodda.ai/mcp) via the Admin Console. See Enterprise MCP Setup for full details.
OpenAI Frontier or Streamable HTTP Client
Connect to the /mcp endpoint using HTTP GET to establish a stream and POST to execute:
https://mcp.fodda.ai/mcp
Gemini CLI
{
"tools": [{
"type": "mcp",
"name": "fodda",
"url": "https://mcp.fodda.ai/sse",
"headers": { "Authorization": "Bearer YOUR_API_KEY" }
}]
}
Generic SSE Client
Connect to https://mcp.fodda.ai/sse with an Authorization: Bearer YOUR_API_KEY header.
Available Tools
| Tool | Description | Deterministic |
|---|---|---|
list_graphs | Discover available knowledge graphs and their schemas | ✅ |
search_graph | Hybrid keyword + semantic search on a knowledge graph | ❌ |
get_neighbors | Traverse from seed nodes to discover related concepts | ✅ |
get_evidence | Source signals, articles, and provenance for a node | ✅ |
get_node | Retrieve metadata for a single node by ID | ✅ |
get_label_values | Discover valid values for a node label/category | ✅ |
discover_adjacent_trends | Find semantically similar trends to a given trend | ✅ |
All tools require userId and — except list_graphs — a graphId.
Discovery Endpoints
| Endpoint | Description |
|---|---|
GET /mcp/tools | Full tool schemas, versions, and capabilities |
GET /health | Health check ({ "status": "ok" }) |
GET /.well-known/mcp.json | MCP server auto-discovery manifest |
Authentication
Pass your Fodda API key as a Bearer token:
Authorization: Bearer fk_live_...
In MCP request _meta:
{ "_meta": { "authorization": "Bearer fk_live_..." } }
Configuration
| Variable | Description | Default |
|---|---|---|
PORT | HTTP server port (omit for stdio mode) | — |
FODDA_API_URL | Upstream API base URL | https://api.fodda.ai |
FODDA_MCP_SECRET | HMAC signing secret for API requests | — |
NODE_ENV | Environment (development / production) | production |
Build & Run
npm install
npm run build
# Stdio mode
npm start
# SSE mode
PORT=8080 npm start
Self-Hosting
- Docker:
docker build -t fodda-mcp . && docker run -p 8080:8080 -e PORT=8080 fodda-mcp - Cloud Run:
./deploy_cloud_run.sh - Kubernetes: See
deployment/k8s/ - Terraform: See
deployment/terraform/
MCP Registry
This server is published to the Official MCP Registry as io.github.piers-fawkes/fodda.
# Verify listing
curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.piers-fawkes/fodda"
License
Proprietary — fodda.ai
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Configuration
FODDA_API_KEY*secretYour Fodda API key
FODDA_API_URLdefault: https://api.fodda.aiUpstream Fodda API URL
Categories
Registryactive
Packagefodda-mcp
TransportSTDIO
AuthRequired
UpdatedMay 21, 2026
