Skip to main content
Glama
growsurf

GrowSurf MCP Server

Official
by growsurf
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Get Program Options

growsurf_get_campaign_options
Read-onlyIdempotent

Fetch a GrowSurf program's Options tab configuration—referral triggers, anti-fraud lists, affiliate settings, and notifications—for a campaign or default campaign ID.

Instructions

Fetch the Options tab configuration for your GrowSurf program (referral triggers, anti-fraud lists and toggles, affiliate enrollment and application review, notifications, and other behavior options). Returns the full object with every field and its current value, the same shape you send back on update. autoFulfillRewards: false permits manual fulfillment and does not prove that any reward went undelivered. Targets campaignId if you pass it, otherwise GROWSURF_CAMPAIGN_ID.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
campaignIdNoTarget program (campaign) id for this call. Defaults to GROWSURF_CAMPAIGN_ID when omitted. Program IDs also identify newly created programs without restarting the server.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
fraudNoAnti-fraud settings: `blockedEmails`/`blockedIps`/`blockedCountries` and matching allow lists, `blockBurnerEmails`, `blockDataCenterIps`, `blockHighRiskReferrers`, `autoBlockHighRiskIps`, per-IP signup rate limits, and `recaptcha`.
autoBlockFraudNoAutomatically block signups flagged as high fraud risk.
rewardEvidenceNoWhat this response establishes about rewards. Combine with other reads; unknown here does not override evidence elsewhere.
payoutThresholdNoAffiliate programs only. Minimum payout in minor currency units (e.g. cents). `0` or `null` means no minimum.
taxDocumentationNoAffiliate programs only. Company billing details (name, address, VAT number) used on affiliate payout invoices and for VAT handling.
autoFulfillRewardsNoReferral programs only. Automatically mark earned rewards as fulfilled. `false` permits manual fulfillment and does not establish a delivery failure.
notificationEmailsNoOwner notification settings: `recipients` plus per-event `events` toggles.
blockPaidAdsTrafficNoDo not attribute referrals from visitors who arrived through paid ads.
enforceGdprComplianceNoStore only the minimum participant data (no IP addresses, fingerprints, or mobile instance ids).
requireParticipantAuthNoRequire returning participants to authenticate. Affiliate programs require `true`.
affiliateApplicationModeNoAffiliate programs only. How public signups join the program. `OPEN_ENROLLMENT` enrolls them directly; `MANUAL_REVIEW` collects an application you approve or deny; `AUTO_APPROVE` collects the application and approves it immediately. A reviewed mode requires the program's published application page. Enrollment through the API, CSV import, dashboard, or invites is never blocked by this setting.
referralCookieWindowDaysNoHow long a referral-link click is remembered in the visitor's browser, in days.
referralCreditWindowDaysNoHow long a referred friend has to complete the qualifying action, in days. `null` means the credit never expires.
requireManualFraudApprovalNoFlag suspected fraud for review instead of blocking signups automatically.
requireManualRewardApprovalNoReferral programs only. Hold each earned reward for manual approval before it unlocks.
affiliateReapplicationPolicyNoAffiliate programs only. Whether a denied applicant may apply again. `AFTER_COOLDOWN` (the default) allows a new application once `affiliateReapplicationCooldownDays` has passed; `DISABLED` never allows one.
affiliateReapplicationCooldownDaysNoAffiliate programs only. How many days a denied applicant waits before they can apply again (1-365, default 30). Only used when `affiliateReapplicationPolicy` is `AFTER_COOLDOWN`.
affiliateApplicationReviewEstimateBusinessDaysNoAffiliate programs only. Optional review-time expectation shown to pending applicants, in business days (1-60). `null` clears it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.19.9
    • changedInput schema / properties / campaignId / description
      Previous value: -"Target program (campaign) id for this call. Defaults to GROWSURF_CAMPAIGN_ID when omitted. Pass the `id` returned by growsurf_create_campaign to configure or operate a program you just created, without restarting the server."New value: +"Target program (campaign) id for this call. Defaults to GROWSURF_CAMPAIGN_ID when omitted. Program IDs also identify newly created programs without restarting the server."
  2. Changed2 schema fields changedv0.14.0
    • changedOutput schema / properties / autoFulfillRewards / description
      Previous value: -"Referral programs only. Automatically mark earned rewards as fulfilled."New value: +"Referral programs only. Automatically mark earned rewards as fulfilled. `false` permits manual fulfillment and does not establish a delivery failure."
    • addedOutput schema / properties / rewardEvidence
      Added value: +{
+  "description": "What this response establishes about rewards. Combine with other reads; unknown here does not override evidence elsewhere.",
+  "properties": {
+    "approvalPolicy": {
+      "description": "Referral reward approval policy from requireManualRewardApproval, not affiliate commission approval or an individual reward state.",
+      "enum": [
+        "manual",
+        "automatic",
+        "unknown"
+      ],
+      "type": "string"
+    },
+    "automaticFulfillmentMarking": {
+      "description": "The autoFulfillRewards setting, when returned by an options read. Null means unknown; this controls marking, not delivery.",
+      "type": [
+        "boolean",
+        "null"
+      ]
+    },
+    "basis": {
+      "enum": [
+        "this_response_only"
+      ],
+      "type": "string"
+    },
+    "conclusion": {
+      "type": "string"
+    },
+    "deliveryStatus": {
+      "enum": [
+        "unknown"
+      ],
+      "type": "string"
+    },
+    "integrationConnection": {
+      "enum": [
+        "not_established"
+      ],
+      "type": "string"
+    },
+    "nextStep": {
+      "type": "string"
+    },
+    "programReferralTrigger": {
+      "enum": [
+        "not_established"
+      ],
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
  3. First observedv0.12.2

TDQS

A3.9/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds real value beyond them: it states the response contains every field with its current value, that it targets campaignId or falls back to the GROWSURF_CAMPAIGN_ID env var, and warns that autoFulfillRewards: false does not prove a reward went undelivered — a genuine misinterpretation guard.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then the return shape, then the default-targeting rule and the field caveat. Dense but every sentence carries information; the parenthetical field list is slightly long but aids scope recognition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't explain return values, yet it usefully frames the return as update-compatible. For a single-optional-parameter read call it is essentially complete, though it says nothing about failure or permission behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only one parameter with 100% schema description coverage, so the baseline is 3. The description restates the campaignId/GROWSURF_CAMPAIGN_ID fallback that the schema already documents, adding no new syntax or format detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Fetch) and a precisely scoped resource (the Options tab configuration of a GrowSurf program), then enumerates the content domains it covers (referral triggers, anti-fraud, affiliate enrollment, notifications). This clearly separates it from siblings like get_campaign_design, get_campaign_emails, and update_campaign_options.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: it notes the return is 'the same shape you send back on update,' which hints at the read-before-write pattern with update_campaign_options, but no alternative tool or condition is named explicitly. The autoFulfillRewards caveat is interpretive guidance, not a when-to-use rule.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools