Skip to main content
Glama

socialloop-mcp

by io.github.socialloopai
OverviewDiscussionsAdmin

Inspect Email Workspace

inspect_email_workspace
Read-onlyIdempotent

details (campaignId) returns retained campaign preview and metadata; deliveries (campaignId, optional exact email/status/cursor) searches the full history; context (eventId/communityId) returns authorized display names. libraryEditorialGet (libraryId) reads a bounded news review list and sources. Read Email Campaigns and newsletter data shared with the web studio. Actions: estimateAudience (audience {collectiveId?, networkFilters, rules, excludeListIds, excludeRules}, optional withAvailability true) counts current eligible unique people with the same checks as preparation, returns exclusion reasons, exact false when capped (count is then a floor) and, with withAvailability, conditions that have no recorded data; it prepares and sends nothing. libraryPeople (libraryId, expectedRevision, returned cursor; current eligible source rows, not unique people or approval); brandGet (saved default design/voice and revision); brandKitList/assetList (search name prefix, archived, asset category/tag, returned cursor); brandKitGet (kitId), assetGet (assetId); capabilities; list (cursor; optional status/search/eventId/communityId; order recent = newest first with word-start search; rows include sentAtMs/scheduledAtMs/updatedAtMs and a short failureReason); sources (payload.kind: lists, segments, domains or communities); listNames (ids, up to 50 list IDs a draft references; unavailable lists return available false); get/preview/review/report/purchaseHistory/deliveries/sample (campaignId, expectedRevision for review); recipientPreview (campaignId, expectedRevision, memberId returned by sample; current eligibility rechecked; sends nothing); workspaceReport; calendar (startAtMs/endAtMs, up to 42 days, returned cursor); libraryList (kind: template/newsletter/segment/section), libraryGet/libraryIssues/libraryRecurrenceGet (libraryId). Preparation may build the catalog. purchaseHistory returns bounded verified purchase amounts/times and email-click evidence, with currencies, refunds and unknown historical evidence preserved. Results distinguish queued, accepted and delivered; attribution is bounded observed activity. Workflow guide (MCP resource): socialloop://guides/email-campaigns.

Input Schema

NameRequiredDescriptionDefault
actionYes
payloadYesAction parameters used by the web workspace: IDs, expectedRevision, draft/definition, cursor, and reviewHash where required. Identity is supplied by the connected account.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "details",
-  "context",
-  "libraryEditorialGet",
-  "libraryPeople",
-  "brandGet",
-  "brandKitList",
-  "brandKitGet",
-  "assetList",
-  "assetGet",
-  "capabilities",
-  "list",
-  "calendar",
-  "sources",
-  "listNames",
-  "get",
-  "preview",
-  "recipientPreview",
-  "review",
-  "report",
-  "purchaseHistory",
-  "deliveries",
-  "sample",
-  "workspaceReport",
-  "libraryList",
-  "libraryGet",
-  "libraryIssues",
-  "libraryRecurrenceGet"
-]New value: +[
+  "details",
+  "context",
+  "libraryEditorialGet",
+  "libraryPeople",
+  "estimateAudience",
+  "brandGet",
+  "brandKitList",
+  "brandKitGet",
+  "assetList",
+  "assetGet",
+  "capabilities",
+  "list",
+  "calendar",
+  "sources",
+  "listNames",
+  "get",
+  "preview",
+  "recipientPreview",
+  "review",
+  "report",
+  "purchaseHistory",
+  "deliveries",
+  "sample",
+  "workspaceReport",
+  "libraryList",
+  "libraryGet",
+  "libraryIssues",
+  "libraryRecurrenceGet"
+]
  2. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "details",
-  "context",
-  "libraryEditorialGet",
-  "libraryPeople",
-  "brandGet",
-  "brandKitList",
-  "brandKitGet",
-  "assetList",
-  "assetGet",
-  "capabilities",
-  "list",
-  "calendar",
-  "sources",
-  "get",
-  "preview",
-  "recipientPreview",
-  "review",
-  "report",
-  "purchaseHistory",
-  "deliveries",
-  "sample",
-  "workspaceReport",
-  "libraryList",
-  "libraryGet",
-  "libraryIssues",
-  "libraryRecurrenceGet"
-]New value: +[
+  "details",
+  "context",
+  "libraryEditorialGet",
+  "libraryPeople",
+  "brandGet",
+  "brandKitList",
+  "brandKitGet",
+  "assetList",
+  "assetGet",
+  "capabilities",
+  "list",
+  "calendar",
+  "sources",
+  "listNames",
+  "get",
+  "preview",
+  "recipientPreview",
+  "review",
+  "report",
+  "purchaseHistory",
+  "deliveries",
+  "sample",
+  "workspaceReport",
+  "libraryList",
+  "libraryGet",
+  "libraryIssues",
+  "libraryRecurrenceGet"
+]
  3. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "libraryEditorialGet",
-  "libraryPeople",
-  "brandGet",
-  "brandKitList",
-  "brandKitGet",
-  "assetList",
-  "assetGet",
-  "capabilities",
-  "list",
-  "calendar",
-  "sources",
-  "get",
-  "preview",
-  "recipientPreview",
-  "review",
-  "report",
-  "purchaseHistory",
-  "deliveries",
-  "sample",
-  "workspaceReport",
-  "libraryList",
-  "libraryGet",
-  "libraryIssues",
-  "libraryRecurrenceGet"
-]New value: +[
+  "details",
+  "context",
+  "libraryEditorialGet",
+  "libraryPeople",
+  "brandGet",
+  "brandKitList",
+  "brandKitGet",
+  "assetList",
+  "assetGet",
+  "capabilities",
+  "list",
+  "calendar",
+  "sources",
+  "get",
+  "preview",
+  "recipientPreview",
+  "review",
+  "report",
+  "purchaseHistory",
+  "deliveries",
+  "sample",
+  "workspaceReport",
+  "libraryList",
+  "libraryGet",
+  "libraryIssues",
+  "libraryRecurrenceGet"
+]
  4. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "libraryEditorialGet",
-  "libraryPeople",
-  "brandGet",
-  "brandKitList",
-  "brandKitGet",
-  "assetList",
-  "assetGet",
-  "capabilities",
-  "list",
-  "calendar",
-  "sources",
-  "get",
-  "preview",
-  "recipientPreview",
-  "review",
-  "report",
-  "deliveries",
-  "sample",
-  "workspaceReport",
-  "libraryList",
-  "libraryGet",
-  "libraryIssues",
-  "libraryRecurrenceGet"
-]New value: +[
+  "libraryEditorialGet",
+  "libraryPeople",
+  "brandGet",
+  "brandKitList",
+  "brandKitGet",
+  "assetList",
+  "assetGet",
+  "capabilities",
+  "list",
+  "calendar",
+  "sources",
+  "get",
+  "preview",
+  "recipientPreview",
+  "review",
+  "report",
+  "purchaseHistory",
+  "deliveries",
+  "sample",
+  "workspaceReport",
+  "libraryList",
+  "libraryGet",
+  "libraryIssues",
+  "libraryRecurrenceGet"
+]
  5. Changed1 schema field changed
    • changedInput schema / properties / action / enum
      Previous value: -[
-  "libraryEditorialGet",
-  "libraryPeople",
-  "brandGet",
-  "capabilities",
-  "list",
-  "calendar",
-  "sources",
-  "get",
-  "preview",
-  "recipientPreview",
-  "review",
-  "report",
-  "deliveries",
-  "sample",
-  "workspaceReport",
-  "libraryList",
-  "libraryGet",
-  "libraryIssues",
-  "libraryRecurrenceGet"
-]New value: +[
+  "libraryEditorialGet",
+  "libraryPeople",
+  "brandGet",
+  "brandKitList",
+  "brandKitGet",
+  "assetList",
+  "assetGet",
+  "capabilities",
+  "list",
+  "calendar",
+  "sources",
+  "get",
+  "preview",
+  "recipientPreview",
+  "review",
+  "report",
+  "deliveries",
+  "sample",
+  "workspaceReport",
+  "libraryList",
+  "libraryGet",
+  "libraryIssues",
+  "libraryRecurrenceGet"
+]
  6. Added

TDQS

B3.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety is covered structurally. The description adds real behavioral context beyond that: capped estimates report exact=false and the count becomes a floor, exclusion reasons are returned, results distinguish queued/accepted/delivered, and attribution is 'bounded observed activity'. That is meaningful extra disclosure.

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

Conciseness2/5

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

It is a single semicolon-chained paragraph with no headings or bullets, opening on an action signature rather than the tool's purpose. For a 28-action mega-tool some length is warranted, but the lack of front-loading and scannable structure makes it hard to use.

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

Completeness3/5

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

Given 28 actions, a generic payload schema and no output schema, the description is the sole source of semantics and it does cover many actions and return behaviors. Still, several actions (capabilities, workspaceReport, brandGet, libraryRecurrenceGet) get only a name-drop, and the absence of any output schema means return shapes remain under-specified.

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

Parameters4/5

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

Schema coverage is only 50% and the payload is a free-form object with additionalProperties, so the schema supplies almost no per-parameter meaning. The description compensates by naming arguments per action (campaignId, expectedRevision, memberId, cursor, eventId/communityId, list IDs up to 50), which is substantial value over the bare schema.

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

Purpose3/5

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

The description eventually states the purpose ('Read Email Campaigns and newsletter data shared with the web studio') and enumerates the action semantics, so the agent can infer this is a read/inspection surface. However, the purpose sentence is buried mid-paragraph after a dense action listing, and nothing distinguishes this inspector from sibling read tools like inspect_email_replies or inspect_email_sequence, nor from the write-side edit_email_campaign.

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

Usage Guidelines2/5

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

There is no explicit when-to-use/when-not guidance or comparison to alternative tools. The only routing help is a trailing pointer to an MCP resource ('socialloop://guides/email-campaigns'), which pushes the decision off-tool. A few action notes ('sends nothing', 'it prepares and sends nothing') hint at safe usage but do not tell the agent when to pick this over siblings.

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

All socialloop-mcp toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources