Outsource in Claude, ChatGPT, and Copilot

Model Context Protocol (MCP) is an open standard by Anthropic that lets any AI assistant securely call external tools on behalf of a user. Outsource ships a compliant MCP server, so once you connect it, Claude / ChatGPT / Copilot can answer questions like:

• "What did we post about the Africa Cup last quarter?"
• "What's on our content calendar next week?"
• "Any market signals for our brand worth acting on?"
• "List all my in-progress content requests."

The assistant sees only the workspace(s) you belong to. All actions are read-only — the assistant cannot create requests, publish posts, or spend credits on your behalf.

Outsource exposes 4 read-only tools. Every response is scoped to the caller’s workspace membership — cross-tenant reads are structurally impossible.

• list_requests

  List content requests (briefs, drafts, published posts) for the caller's client. Filter by status when known. Returns compact rows suitable for a chat summary — each row includes title, status, service (Instagram, LinkedIn, …), created date, due date, and whether a draft has been delivered.

• search_content

  Full-text search over the caller's content — brief titles, brief text, and the latest delivered draft. Use to answer questions like 'what did we post about X last quarter' or 'find our best-performing Y post'. Returns up to `limit` matches ordered by recency.

• get_calendar

  Get the caller's upcoming and recent content calendar — both requests with due dates and planned posts. Defaults to the next 14 days; pass explicit dates to widen. Use to answer 'what's on our calendar this week' or 'what's launching next Thursday'. Returns items ordered by date.

• get_brand_intel

  Recent market intelligence signals surfaced to this client — news, competitor mentions, industry moves. Only signals that passed the internal relevance threshold and were approved for client visibility are returned. Use to answer 'what's happening in our space' or 'anything worth posting about'.

Two flows, both live today.

• Read-only in v1. The assistant cannot create, publish, delete, or spend credits.
• Scoped to the caller's active workspace membership(s). Cross-tenant queries are refused at the row level.
• Bearer tokens and OAuth access tokens are stored as sha256 hashes — a database leak cannot be replayed.
• PKCE (S256) required on the OAuth flow. No confidential-client secrets are issued to public MCP clients (Claude Desktop, ChatGPT).
• You can revoke any token or OAuth grant from Profile → Settings → AI Assistants at any time.
• All requests are logged to our internal audit trail with timestamp, tool called, and calling assistant.
• Outsource data is hosted in the EU (Supabase Frankfurt, GDPR baseline). Sub-processors are documented at /sub-processors.

The MCP server implements the standard endpoints per the current spec:

Full transport is Streamable HTTP per the current MCP spec (JSON responses; a streaming upgrade lands in v2 when write tools are added).

• Write tools (create_request, generate_draft, schedule_publish) — behind the same consent gate.
• Multi-workspace switcher for members of >1 workspace.
• Anthropic MCP Directory + ChatGPT connector-store listings for one-click discovery.
• Copilot for M365 store listing for enterprise deployments.

Questions, integration issues, or want us to add a tool your team needs? Email contact@thegoodpicture.com and a founder will respond within one business day.

Data handling is governed by our Privacy Policy and Terms of Service. Sub-processors are listed at /sub-processors.