7
Scope Categories
Workspace, publishing, drafts, media, campaigns, social accounts, and analytics.
Fine-grained MCP permissions for AI-native social publishing
Postly MCP lets AI agents securely execute real publishing operations through one hosted server, one shared backend, and one scope-based permission model. Agents can create drafts, schedule posts, publish content, upload media, manage campaigns, retrieve analytics, and check publishing status without bypassing workspace controls.
7
Workspace, publishing, drafts, media, campaigns, social accounts, and analytics.
31
Permission strings designed for safe AI and agent execution.
7
Read-only analytics coverage for major connected social platforms.
11
Built for today’s and future MCP-compatible AI systems.
Use the API page for direct REST integrations and backend workflows. Use this MCP page when an AI client needs scoped tools for drafts, media, scheduling, publishing, analytics, or status checks.
Postly is not just a dashboard or generic automation platform. It is the execution layer used by AI agents, AI copilots, chat interfaces, conversational assistants, multi-agent systems, enterprise AI systems, and publishing orchestration tools.
AI-native flow
Fine-grained scopes give users and workspaces precise control over what AI clients can read, create, update, publish, delete, and analyze.
Allow an AI client to understand which workspace it can operate in.
workspace:readRead the active workspace profile, settings, and execution context.
workspace:listList available workspaces the authenticated user can access.
Control post creation, updates, scheduling, publishing, deletion, and status checks.
posts:readRead post content, metadata, platform targets, and publishing history.
posts:createCreate new posts from AI-generated or user-approved content.
posts:updateUpdate post copy, media, schedule details, platform metadata, or campaign assignment.
posts:deleteDelete posts when the user has approved destructive publishing actions.
posts:scheduleSchedule posts for future publishing windows.
posts:publishPublish approved content immediately through Postly execution services.
posts:status:readRetrieve publishing status, failures, queue state, and execution progress.
Let agents assist with safe draft creation and editing before publication.
drafts:readRead existing drafts and draft metadata.
drafts:createCreate drafts for review, approval, collaboration, or scheduling.
drafts:updateUpdate draft copy, media references, campaign metadata, or target platforms.
drafts:deleteDelete drafts when explicitly allowed by the user or workspace policy.
Manage media assets used in AI-assisted publishing workflows.
media:readRead media library assets and metadata.
media:uploadUpload images, videos, and creative assets for publishing.
media:updateUpdate media metadata, captions, tags, or campaign assignment.
media:deleteDelete media assets when permitted by workspace policy.
Allow agents to organize posts into campaign-level workflows.
campaigns:readRead campaign details, status, related posts, and campaign metadata.
campaigns:createCreate new publishing campaigns and campaign containers.
campaigns:updateUpdate campaign names, goals, schedules, post assignments, or metadata.
campaigns:deleteDelete campaigns when explicitly permitted.
Expose connected social accounts without granting publishing power by default.
social_accounts:readRead connected social account metadata and platform identity.
social_accounts:listList social accounts available to the authenticated workspace.
Grant read-only analytics access across supported social platforms.
analytics:readRead general analytics summaries across connected platforms.
analytics:facebook:readRead Facebook analytics through Postly analytics tools and resources.
analytics:instagram:readRead Instagram analytics through Postly analytics tools and resources.
analytics:pinterest:readRead Pinterest analytics through Postly analytics tools and resources.
analytics:youtube:readRead YouTube analytics through Postly analytics tools and resources.
analytics:gmb:readRead Google My Business analytics through Postly analytics tools and resources.
analytics:linkedin:readRead LinkedIn analytics through Postly analytics tools and resources.
analytics:x:readRead X / Twitter analytics through Postly analytics tools and resources.
Use bundles to simplify setup while keeping MCP clients constrained to the exact permissions needed.
Recommended for AI assistants that answer analytics questions without publishing or editing content.
workspace:readworkspace:listsocial_accounts:readanalytics:readGrant broad analytics visibility across every supported analytics integration.
workspace:readworkspace:listsocial_accounts:readanalytics:readanalytics:facebook:readanalytics:instagram:readanalytics:pinterest:readanalytics:youtube:readanalytics:gmb:readanalytics:linkedin:readanalytics:x:readUseful for agents that can draft, schedule, publish, and monitor posts through Postly.
workspace:readworkspace:listsocial_accounts:listposts:readposts:createposts:updateposts:scheduleposts:publishposts:status:readdrafts:readdrafts:createdrafts:updatemedia:readmedia:uploadcampaigns:readcampaigns:updateBest for multi-step campaign planning, organization, content staging, and performance checks.
workspace:readworkspace:listcampaigns:readcampaigns:createcampaigns:updateposts:readposts:createposts:updateposts:scheduledrafts:createdrafts:updatemedia:readanalytics:readAnalytics can be exposed through MCP as read-only tools and resources. Platform-specific scopes let users grant access to one social network without granting broad analytics access.
analytics:facebook:readanalytics:instagram:readanalytics:pinterest:readanalytics:youtube:readanalytics:gmb:readanalytics:linkedin:readanalytics:x:readThe user asks an AI client or agent to draft, schedule, publish, retrieve analytics, or check status.
Postly verifies authentication, scoped token access, rate limits, and monetization controls.
The request is routed to the correct workspace and checked against fine-grained scopes.
Publishing, analytics, media, campaigns, and status operations run through one centralized execution layer.
MCP should become the primary AI-native integration layer for Postly so AI agents can securely connect directly to Postly infrastructure.
Postly should build one centralized backend infrastructure, then expose the same capabilities through MCP tools, MCP resources, REST APIs, and webhooks.
The MCP server should own AI tool definitions, authentication, workspace routing, permission enforcement, publishing execution, analytics retrieval, usage enforcement, rate limiting, and monetization enforcement.
Expose actions like create draft, schedule post, publish content, upload media, and retrieve status.
Expose safe read-only resources for workspace, campaign, social account, and analytics context.
Issue scoped session tokens after login, user approval, and workspace permission checks.
Keep every agent operation bound to the scopes the user explicitly granted.
The dashboard remains important, but the durable moat is AI-native execution infrastructure: scopes, authentication, orchestration, analytics, publishing services, workspace routing, and agent-compatible APIs.