Developers
Build agents that compose decks against your firm's brand.
Codexroom exposes its workspace through a Model Context Protocol server and a REST API. Your engineering team wires it into Claude, Cursor, the OpenAI Agents SDK, or your internal stack. The reference below covers every endpoint and every tool.
Where to start
Five surfaces. One workspace.
MCP server
Connect any MCP client over OAuth.
OAuth 2.0 with PKCE. Scope-gated tools. Authorise a Claude Desktop or Cursor session against your workspace.
Read →
REST API
Same surface, available server-to-server.
Mirror every MCP tool as a typed HTTP endpoint. Service-token authentication. Webhooks with HMAC-SHA256.
Read →
Agent recipes
Worked examples your team can lift.
Five worked prompts + tool-call traces for sales pitches, QBRs, RFP responses, watermarked shares, and analytics.
Read →
SDKs
Typed clients for TypeScript and Python.
Both SDKs wrap the REST API and the MCP server. Edge-runtime support for read-only calls.
Read →
Changelog
Every dated API, MCP, and SDK change.
Breaking changes carry a 90-day deprecation window. Subscribe to the RSS feed.
Read →
What you can build
Three patterns most teams ship in the first quarter.
An agent that drafts decks for sellers. Wire Claude Desktop into the workspace. The seller prompts, the agent composes, the link arrives in Slack.
A pipeline that ships quarterly updates. Schedule a job that pulls the latest metrics, composes the quarterly LP letter from the template, and creates per-LP shares.
A copilot inside your existing app. Embed the API into the internal tool your team uses every day. The deck assembly stays in their workflow.
Authentication
OAuth for agents. Service tokens for servers.
OAuth 2.0 with PKCE for MCP clients. Service tokens for server-to-server calls. Both scope-gated to the workspace, the user, and the operations you authorise.
Rate limits
Generous by default.
Published per endpoint, with overage rates on the pricing page. Enterprise contracts include custom limits.
See it work