MCP Server: ai.fodda/earnings-intelligence

The MCP server ai.fodda/earnings-intelligence provides cross-company earnings trends and executive divergence, along with citable sources. It is described as an information layer focused on earnings-related patterns and differences across executives, grounded in references.

🛠️ Key Features

Cross-company earnings trends
Executive divergence
Citable sources

🚀 Use Cases

Comparing earnings trends across multiple companies
Investigating divergences in executive-related performance or outlooks
Using citable sources for earnings and executive analysis

⚡ Developer Benefits

Standardized MCP access to earnings-trend and divergence data
Source-backed outputs via citable references

⚠️ Limitations

No additional tool details, topics, or counts were provided in the available server data.

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 with fk_live_...
Use the email address associated with your Fodda account for user_id.

Claude Code (CLI — SSE)

bash

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:

bash

https://mcp.fodda.ai/mcp

Gemini CLI

json

{
  "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:

code

Authorization: Bearer fk_live_...

In MCP request _meta:

json

{ "_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

bash

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.

bash

# Verify listing
curl "https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.piers-fawkes/fodda"

License

Proprietary — fodda.ai

mode	string	optional	Execution mode: "research" for topic research (15 API calls), "compare" for upload & compare intelligence (20 API calls). Defaults to "research".
graphId	string	optional	Optional graph ID. If omitted, searches ALL accessible graphs. Examples: 'retail', 'tech', 'food', 'travel', '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'
query	string	required	The search query. Location terms are auto-detected and used to filter results geographically.
userId	string	optional	Optional user identifier for trial usage tracking.
limit	number	optional	Maximum number of results (default 10, max 50)
use_semantic	boolean	optional	Whether to use semantic search (default true)
include_evidence	boolean	optional	If true, batch-fetch supporting evidence articles inline with results. Default: true.
skip_skills	boolean	optional	If 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.

graphId	string	required	The graph ID. Use list_graphs to see all options. Examples: 'retail', 'tech', 'food', 'travel', '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'
seed_node_ids	array	required	Array 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.
userId	string	optional	Optional user identifier for trial usage tracking.
relationship_types	array	optional	Filter by relationship types: 'EVIDENCED_BY', 'RELATED_TO', 'SEMANTICALLY_SIMILAR', 'ASSOCIATED_BRAND', 'MENTIONS_BRAND', 'IN_LOCATION'
direction	string	optional	Traversal direction: 'out' (default) follows outgoing edges, 'in' follows incoming edges
depth	number	optional	Traversal depth (default 1, max 2)
limit	number	optional	Maximum results (default 50)

graphId	string	required	The graph ID. Use list_graphs to see all options. Examples: 'retail', 'tech', 'food', 'travel', '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_id	string	required	The 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.
userId	string	optional	Optional user identifier for trial usage tracking.
top_k	number	optional	Number of evidence items to return (default 5)

graphId	string	required	The graph ID. Use list_graphs to see all options. Examples: 'retail', 'tech', 'food', 'travel', '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'
nodeId	string	required	The 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.
userId	string	optional	Optional user identifier for trial usage tracking.

graphId	string	required	The graph ID. Use list_graphs to see all options. Examples: 'retail', 'tech', 'food', 'travel', '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'
label	string	required	The label to fetch values for (e.g., 'Brand', 'Location', 'Technology', 'Audience', 'RetailerType', 'Trend')
userId	string	optional	Optional user identifier for trial usage tracking.
property	string	optional	Optional property to return values for. Defaults vary by label.

Fodda Earnings Intelligence

MCP Server: ai.fodda/earnings-intelligence

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

get_my_account

list_graphs

get_capabilities

search_graph

get_neighbors

get_evidence

get_node

get_label_values

get_earnings_intelligence

get_earnings_divergence

get_company_earnings

get_validated_trends

generate_visual

Fodda MCP Server

Quick Start

Claude (Web — Pro, Max, Team, Enterprise)

Claude Code (CLI — SSE)

Claude Enterprise

OpenAI Frontier or Streamable HTTP Client

Gemini CLI

Generic SSE Client

Available Tools

Discovery Endpoints

Authentication

Configuration

Build & Run

Self-Hosting

MCP Registry

License

Install

Remote endpoint

ticker	string	optional	Company stock ticker (e.g., 'NKE', 'LVMUY', 'HLT'). At least one filter required.
brand	string	optional	Brand name for fuzzy matching (e.g., 'Nike', 'Marriott')
industry	string	optional	Industry filter (e.g., 'hotels', 'sportswear', 'consumer electronics')
sector	string	optional	Sector filter (e.g., 'retail', 'technology', 'travel')
search	string	optional	Free text search in earnings summaries (e.g., 'labor costs', 'tariff guidance', 'AI investment')
dateFrom	string	optional	ISO date range start (e.g., '2025-01-01')
dateTo	string	optional	ISO date range end (e.g., '2026-06-01')
limit	integer	optional	Max results to return (default 20, max 50)
userId	string	optional	Optional user identifier for trial usage tracking.

chart_type	string	required	The type of visualization to generate
data	string	required	JSON 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}]}