mcp-interaction-studio
Provides tools to manage datasets, campaigns, segments, templates, recipes, and campaign performance stats for Salesforce Interaction Studio / Marketing Cloud Personalization via its internal admin APIs.
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., "@mcp-interaction-studio list my datasets"
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.
mcp-interaction-studio
MCP (Model Context Protocol) server for Salesforce Interaction Studio / Marketing Cloud Personalization admin APIs.
Connect Cursor, Claude Desktop, or any MCP client to your Interaction Studio instance to list datasets, campaigns, segments, templates, recipes, and campaign performance stats through natural language.
How it works
Interaction Studio’s admin UI uses undocumented internal APIs under /internal/.... This server authenticates the same way your browser does: with a session cookie (JSESSIONID) from an active UI login.
Auth method | Used for |
| All tools in this package ( |
API token (Basic auth) | Public |
Related MCP server: Salesforce MCP Server
Prerequisites
Node.js 18+
Access to Interaction Studio admin UI (Gears) for your org
An MCP host (e.g. Cursor, Claude Desktop)
Step 1 — Find your IS_BASE_URL
Log into Interaction Studio. The URL in your browser looks like:
https://{accountName}.{instance}.evergage.com/ui/...Your base URL is everything before /ui:
https://{accountName}.{instance}.evergage.comExample: if you seehttps://demo.us-1.evergage.com/ui/
then:
IS_BASE_URL=https://demo.us-1.evergage.comDo not include a trailing slash.
You can also find this from any Network request to *.evergage.com — use the scheme + host only.
Step 2 — Get your IS_SESSION_ID (JSESSIONID)
The session ID is a cookie set when you log into the admin UI. It expires when you log out or after idle timeout.
Chrome / Edge
Log into Interaction Studio at
{IS_BASE_URL}/ui/Open DevTools → Network tab
Reload the page (or click any screen that loads data)
Click any request to your
*.evergage.comhostUnder Request Headers, find the
CookieheaderCopy the value after
JSESSIONID=up to the next;
Example cookie header:
Cookie: JSESSIONID=274fb681-ebf1-4dbb-8e4d-5b03bb8a1752; AWSALBTG=...Copy only:
274fb681-ebf1-4dbb-8e4d-5b03bb8a1752Firefox
Log into the UI
DevTools → Network → select a request → Headers → Cookie
Copy the
JSESSIONIDvalue the same way
Verify with curl
curl -k "https://YOUR_ACCOUNT.us-4.evergage.com/internal/datasetSummaries/" \
-H "Cookie: JSESSIONID=YOUR_SESSION_ID_HERE" \
-H "X-Requested-With: XMLHttpRequest"If you get a JSON array of datasets, the session is valid. If you get 401 or "Bad Credentials", log in again and copy a fresh JSESSIONID.
Security: Treat
JSESSIONIDlike a password. Do not commit it to git or share it in chat. Refresh it when it expires.
Step 3 — Install the MCP server
Option A — Run with npx (recommended)
No global install needed:
npx mcp-interaction-studioOption B — Global install
npm install -g mcp-interaction-studio
mcp-interaction-studioOption C — Clone and run locally
git clone <your-repo-url>
cd mcp-interaction-studio
npm install
npm startStep 4 — Configure your MCP host
Cursor
Open Cursor Settings → MCP (or edit ~/.cursor/mcp.json):
{
"mcpServers": {
"interaction-studio": {
"command": "npx",
"args": ["-y", "mcp-interaction-studio"],
"env": {
"IS_BASE_URL": "https://YOUR_ACCOUNT.us-4.evergage.com",
"IS_SESSION_ID": "paste-your-JSESSIONID-here",
"IS_DEFAULT_DATASET": "my-dataset",
"IS_TLS_INSECURE": "true"
}
}
}
}If installed globally:
{
"mcpServers": {
"interaction-studio": {
"command": "mcp-interaction-studio",
"env": {
"IS_BASE_URL": "https://YOUR_ACCOUNT.us-4.evergage.com",
"IS_SESSION_ID": "paste-your-JSESSIONID-here",
"IS_DEFAULT_DATASET": "my-dataset",
"IS_TLS_INSECURE": "true"
}
}
}
}Restart MCP in Cursor Settings after changing config.
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"interaction-studio": {
"command": "npx",
"args": ["-y", "mcp-interaction-studio"],
"env": {
"IS_BASE_URL": "https://YOUR_ACCOUNT.us-4.evergage.com",
"IS_SESSION_ID": "paste-your-JSESSIONID-here",
"IS_DEFAULT_DATASET": "my-dataset",
"IS_TLS_INSECURE": "true"
}
}
}
}Environment variables
Variable | Required | Description |
| Yes | Interaction Studio host, e.g. |
| Yes |
|
| No | Default dataset name when a tool omits the |
| No | Set to |
| No | Set to |
| No | Path to your corporate root CA |
Copy .env.example to .env when running locally:
cp .env.example .env
# edit .env, then:
npm startCorporate SSL (Zscaler / proxy)
If you see:
SSL certificate problem: unable to get local issuer certificateQuick fix (dev): set IS_TLS_INSECURE=true
Proper fix: export your org’s Zscaler/corporate root CA and set:
export NODE_EXTRA_CA_CERTS=/path/to/corporate-root.pemThen remove IS_TLS_INSECURE.
Session expiration
When JSESSIONID expires, tools return:
Session expired or invalid (401). Log into Interaction Studio, copy a fresh JSESSIONID...Fix: log into the UI again → copy new JSESSIONID → update IS_SESSION_ID in MCP config → restart MCP.
There is no API token alternative for /internal/* admin routes today.
Available tools
Tool | Description |
| Validate |
| All datasets in the account |
| Dataset metadata and content zones |
| Campaigns in a dataset |
| Campaign details: state, targeting, experiences |
| Impressions, clicks, goals, orders, revenue |
| Segments in a dataset |
| Segment details and targeting rules |
| Segments across all datasets (or filter one) |
| Item/message templates |
| Recommendation recipes |
| Campaign experiences, messages, and runtime context |
| Surveys in a dataset |
| Content zone activity logs |
| Extended segment info including membership counts |
| Dataset audit report (markdown or JSON); optional file output |
| Executive-ready orchestrated audit: narrative, health score, governance, consumption, settings; markdown + DOCX |
| Side-by-side comparison of two datasets |
| Map recipes to campaigns (resolves inUse vs actual linkage) |
| Batch segment membership counts and calc status |
| Publish or disable a campaign (write; gated) |
| Enable or disable a segment (write; gated) |
Set IS_DEFAULT_DATASET to skip passing dataset on every call.
Write tools (v1.0)
Write operations are disabled by default. To enable:
Set
IS_WRITES_ENABLED=truein MCP configCall with
dry_run=falseandconfirm=true
Always preview first with dry_run=true (default):
"Dry run: publish campaign Q07yv in eharper"
"Disable segment uvoSx in eharper — dry run only"
Execute only when intentional:
"Set campaign qDArI to Disabled in eharper with dry_run false and confirm true"
Endpoint | Method | Operation |
| PUT | Publish / disable campaign (full object, |
| POST | Enable / disable segment ( |
Executive audit (audit_mcp_dataset)
Board-ready assessment with health rating, strengths/gaps narrative, domain assessments, and prioritized recommendations. Writes markdown and DOCX when output_path is set.
Parameter | Description |
|
|
|
|
| When saving |
|
|
Example:
"Full MCP audit of eharper — save to audit/eharper-audit.md"
"audit_mcp_dataset dataset=eharper report_style=executive output_path=audit/report.md"
Example prompts
"Check my Interaction Studio session"
"List my Interaction Studio datasets"
"Audit the eharper dataset and save to audit/eharper-audit.md"
"Full executive MCP audit of eharper with markdown and docx"
"Compare mathes and eharper datasets"
"Which campaigns use recipe 4RhQk in eharper?"
"List segment stats for all segments in eharper"
"Get stats for campaign ABC123 in my-dataset"
"List all segments across every dataset"
"Get segment XYZ789 from my-dataset"
Campaign stats time ranges
For get_campaign_stats and list_campaigns, use time_range:
pastDay,pastWeek(default),pastMonth,pastQuarter,TodayCustom:
YYYY-MM-DD..YYYY-MM-DD(max range limits apply per IS API)
CLI audit script
After building locally, run a full audit from the command line:
npm run build
node dist/scripts/audit-dataset.js eharper --output ../audit/eharper-audit.mdOr use the npm script:
npm run audit -- eharper --output ../audit/eharper-audit.mdTroubleshooting
Problem | Solution |
| Refresh |
SSL certificate error |
|
Tool not found in Cursor | Restart MCP after upgrading the package |
| Set env in MCP config |
Zero campaign stats | Campaign may have no traffic in the selected time window; try a wider custom range |
| Use a valid |
License
MIT
Available Tools
22 toolsaudit_datasetB
Run a complete Interaction Studio dataset audit: configuration, campaigns, segments, templates, recipe usage, stats, and findings. Returns markdown or JSON; optionally writes to a file.
Inputs: dataset, time_range, output_path, output_format, +1 more.
audit_mcp_datasetA
Executive-ready orchestrated dataset audit: narrative assessment with health rating, strengths/gaps, recommendations, governance, consumption, and settings. Outputs markdown and/or DOCX.
Inputs: dataset, sections, time_range, export_docx, +6 more.
check_sessionA
Validate the Interaction Studio session (JSESSIONID) and list available datasets. Use this first when other tools return 401 errors.
Inputs: no named parameters.
compare_datasetsB
Compare two Interaction Studio datasets side-by-side: counts, campaign states, segment populations, recipe linkage, and activity.
Inputs: dataset_b (required), dataset_a, time_range.
get_campaignA
Get details for a single Interaction Studio campaign, including state, targeting, and experiences.
Inputs: campaign_id (required), dataset, include_raw.
get_campaign_contextB
Get runtime context for an Interaction Studio campaign: experiences, messages, and content configuration.
Inputs: campaign_id (required), dataset, include_raw.
get_campaign_statsB
Get performance stats for an Interaction Studio campaign: impressions, clicks, goals, orders, and revenue.
Inputs: campaign_id (required), dataset, time_range.
get_datasetB
Get Interaction Studio dataset metadata including label, state, tracking settings, and content zones.
Inputs: dataset, include_content_zones.
get_recipe_usageA
Map recommendation recipes to campaigns by scanning experience configuration. Resolves API inUse flag vs actual campaign linkage.
Inputs: dataset, recipe_id, time_range, include_raw.
get_segmentB
Get details for a single Interaction Studio segment by id, including optional targeting rules.
Inputs: segment_id (required), dataset, include_raw, include_rules.
get_segment_detailsA
Get extended segment details including membership counts and optional live stats.
Inputs: segment_id (required), dataset, time_range, include_raw, +1 more.
list_all_segmentsA
List segments across all Interaction Studio datasets, or filter to a single dataset.
Inputs: dataset.
list_campaignsA
List campaigns in an Interaction Studio dataset. Returns campaign id, name, state, priority, and last modified time.
Inputs: dataset, time_range.
list_content_zone_logsB
List content zone activity logs for an Interaction Studio dataset within a time range.
Inputs: dataset, time_range.
list_datasetsA
List all Interaction Studio (Marketing Cloud Personalization) datasets available in the connected account. Returns each dataset's name, label, state, type, and active campaign count.
Inputs: no named parameters.
list_recipesB
List recommendation recipes in an Interaction Studio dataset.
Inputs: dataset.
list_segmentsB
List all segments in an Interaction Studio dataset, including segment id and name.
Inputs: dataset.
list_segment_statsC
List membership counts and calculation status for all segments (or a filtered list) in a dataset.
Inputs: dataset, time_range, include_raw, segment_ids.
list_surveysB
List surveys configured in an Interaction Studio dataset.
Inputs: dataset.
list_templatesA
List item/message templates in an Interaction Studio dataset used for campaign content.
Inputs: dataset.
set_campaign_stateA
Publish or disable an Interaction Studio campaign by updating its state (Published or Disabled). Requires IS_WRITES_ENABLED=true and confirm=true. Defaults to dry_run preview.
Inputs: state (required), campaign_id (required), confirm, dataset, +1 more.
set_segment_enabledA
Enable or disable an Interaction Studio segment. Requires IS_WRITES_ENABLED=true and confirm=true. Defaults to dry_run preview.
Inputs: enabled (required), segment_id (required), confirm, dataset, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 22 tools
Tools are mostly distinct but several overlap: list_segments vs list_all_segments, get_segment vs get_segment_details, and audit_dataset vs audit_mcp_dataset could confuse an agent. Descriptions help differentiate but ambiguity remains.
All tools follow a consistent verb_noun pattern with lowercase and underscores (e.g., list_recipes, set_campaign_state). The verbs vary appropriately but the pattern is uniform across all 22 tools.
22 tools is on the higher side of reasonable for a complex domain like Interaction Studio, covering datasets, campaigns, segments, recipes, and audits. It is slightly above the typical well-scoped range but not excessive.
The tool set heavily favors read operations and state toggles but lacks create, update, or delete tools for campaigns, segments, recipes, or surveys. This is a significant gap for full lifecycle management.
Related MCP Connectors
Marketing intelligence MCP server providing campaign performance data and analytics tools.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for searching Airweave collections with natural language queries.
Related MCP Servers
- AlicenseAqualityAmaintenanceAn MCP server implementation that integrates Claude with Salesforce, enabling natural language interactions with Salesforce data and metadata for querying, modifying, and managing objects and records.153,410 npm165MIT
- AlicenseAqualityDmaintenanceAn MCP server implementation that integrates Claude with Salesforce, enabling natural language interactions with Salesforce data and metadata for querying, modifying, and managing objects and records.759 npm15MIT
- AlicenseAqualityDmaintenanceAn MCP server implementation that integrates Claude with Salesforce, enabling natural language interactions with Salesforce data and metadata.859 npmMIT
- FlicenseBqualityDmaintenanceA customizable MCP server for integrating Salesforce APIs with GenAI applications, supporting SOQL queries, record CRUD, metadata access, and more.138-