MarTech MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MarTech MCP Server What offers are available for lapsed customers?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MarTech MCP Server
An industry-agnostic Model Context Protocol server that exposes marketing catalogs — offers, assets, campaigns, and computed offer metrics — to any MCP client (Claude Desktop, other AI assistants, or an orchestration platform).
It reads catalogs from CSV today and is designed so the data source can be swapped for a database or object storage (R2/S3) later without changing the tools. A customer integrates by exporting CSVs from whatever backend they use, placing them in a configured location, and pointing the server at it — the server and any connected AI tool never store the data and never touch the source systems.
This is a reference implementation with a defined catalog contract, not a universal connector for every martech vendor. Extend the CSV contract and the
CatalogSourceto fit your systems.
Tools
Reference lookups:
search_offers— find offers by free-text query, category, and/or segmentget_offer— full offer record by ID or nameget_assets_for_offer— creative assets linked to an offersearch_campaigns— find campaigns by query and/or segmentget_campaign— full campaign record by ID or name
Computed metrics (from an event fact table; individual profiles are only ever counted, never exposed):
get_offer_performance— impressions, clicks, CTR, unique reach for an offer; optional breakdown by segment or placementget_top_offers— offers ranked by CTR, optionally filtered by segment/placementget_campaign_performance— aggregate performance for a campaign
Related MCP server: semantic-model-kit
Catalog contract (CSV)
Multi-value fields use a semicolon (;) delimiter.
offers.csv: Offer ID, Offer Name, Offer Category, Offer Tone, Offer Segments, Offer Title, Offer Description, Offer Subtitle, Offer Eyebrow Text, Offer Image Asset URL, Offer CTA Text, Offer CTA URL, Offer CTA 2 Text, Offer CTA 2 URL
assets.csv: Asset ID, Asset Name, Asset URL, Asset Tags
campaigns.csv: Campaign ID, Campaign Name, Campaign Brief, Campaign Segments, Campaign Offers, Campaign Attribution IDs, Targeted Placements
offer_metrics.csv: Offer ID, Placement, Segment, Profile ID, Action (View/Click), Campaign ID
Run locally
npm install
npm run build
npm start # runs the compiled server on stdio
# or, during development:
npm run dev # runs from source with tsx
npm run inspect # opens the MCP Inspector against the serverSet MARTECH_DATA_DIR to use a different catalog directory (defaults to ./data).
Connect to Claude Desktop
Add this to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"martech": {
"command": "node",
"args": ["/absolute/path/to/martech-mcp-server/dist/index.js"]
}
}
}Restart Claude Desktop, then ask things like "What offers do we have for lapsed customers?" or "What's the click-through rate for campaign TMO-CMP-001?" — Claude will call the tools and read your catalogs live.
Roadmap
Swap
CsvCatalogSourcefor an R2/S3-backed source (read CSVs from a bucket) and a database source.Per-customer configuration (point at a customer's bucket/prefix).
Remote transport (HTTP/SSE) for hosted, multi-client access.
Run as a remote server (for Claude custom connectors)
The server also runs over HTTP (Streamable HTTP transport) so it can be added as a remote custom connector in Claude (claude.ai, Claude Desktop, Cowork).
npm install
npm run build
npm start # HTTP server on :3000 (or $PORT), MCP endpoint at POST /mcpHealth check: GET / · MCP endpoint: POST /mcp
Deploy free on Render
Push this repo to GitHub.
On render.com: New → Web Service → connect this repo.
Render reads
render.yamlautomatically (buildnpm install && npm run build, startnpm start, free plan).After deploy you get a URL like
https://martech-mcp-server.onrender.com.In Claude → Add custom connector → Remote MCP server URL =
https://martech-mcp-server.onrender.com/mcp(leave OAuth blank).
Note: Render's free tier sleeps after inactivity; the first request after idle may take ~30–60s to wake.
Run locally for Claude Desktop (stdio)
npm run build
npm run start:stdioThen point claude_desktop_config.json at dist/index.js (see earlier example).
Available Tools
8 toolsget_assets_for_offerA
Get creative assets linked to an offer (by Offer ID or name).
Inputs: offer (required).
get_campaignA
Get a single campaign's full record by Campaign ID (or name), including its offers, segments, attribution IDs, and placements.
Inputs: id (required).
get_campaign_performanceA
Computed aggregate performance for a campaign: impressions, clicks, CTR, unique reach.
Inputs: campaignId (required).
get_offerA
Get a single offer's full record by Offer ID (or exact name).
Inputs: id (required).
get_offer_performanceA
Computed performance for an offer: impressions, clicks, CTR, and unique reach. Optionally broken down by segment or placement.
Inputs: offerId (required), by.
get_top_offersA
Top offers ranked by CTR, optionally filtered to a segment and/or placement.
Inputs: limit, segment, placement.
search_campaignsC
Search campaigns by free-text query and/or segment.
Inputs: limit, query, segment.
search_offersB
Search marketing offers by free-text query, category, and/or segment. Returns matching offers with title, copy, image, and CTAs.
Inputs: limit, query, segment, category.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 8 tools
Each tool targets a distinct resource and action: campaigns vs offers, search vs get, performance vs details vs assets. No ambiguity between tools.
All tools follow a consistent verb_noun pattern in snake_case (e.g., get_campaign, search_offers), making them predictable and easy to parse.
8 tools is appropriate for a read-focused MarTech server, covering listing, searching, performance, and assets without feeling sparse or bloated.
Covers retrieval and performance analytics for campaigns and offers, plus assets and top offers. Lacks write operations (create/update/delete), but the server appears designed for read-only insights.
Maintenance
Related MCP Connectors
Governed data discovery, exact queries, decisions, simulations, and runtime utilities over MCP.
Read-only discovery of ChatGXT's integration catalog and public MCP capabilities.
Read-only AgentiScript concept search, catalog, authenticity, license, and approved asset discovery.
Public read-only MCP for products, frameworks, guides, methodology, and blog metadata.
Related MCP Servers
- FlicenseBqualityCmaintenanceProvides AI clients with a governed, searchable catalog of go-to-market context, including ownership, measurement, lineage, runbooks, and bulk-change templates. Optionally integrates with the UTM Builder for governed UTM reference data, preview, and issuance.15-
- AlicenseAqualityBmaintenanceEnables agents to query governed metrics through MCP, including describing metrics, running deterministic SQL against a warehouse, explaining join path preferences, and searching semantically ambiguous terms.8MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to browse a read-only catalog of published products and their documented interfaces, listing entries, fetching one by stable ID, and searching names, descriptions, and limitations with optional protocol filters. It also exposes the versioned manifest as a resource and a prompt that helps clients match a task to catalog entries without inventing unsupported capabilities.MIT
- AlicenseNot gradedqualityBmaintenanceEnables chat, document search (RAG), and a declarative SQL tool builder over MCP so any client can use these capabilities.AGPL 3.0