MCP server
Every action in Odexy — as an AI tool.
We run a Model Context Protocol server that auto-generates a typed tool for every user-performable action in the platform. Point Claude, Cursor, Zed, Sourcegraph, or your own MCP-speaking agent at it, and the AI can operate the same UI your team uses — under the same permissions, into the same audit log.
What ships
One MCP server. Every module. Every action.
- Auto-generated tool catalogue. Every action in the platform's action registry becomes an MCP tool at server boot. Zero hand-authored tool definitions; when we ship a new action, it shows up in MCP the same release.
- Typed input + output schemas. Zod-authored per-action schemas surface as JSON Schema on the tool's input + output — so your LLM knows the exact shape, and malformed inputs get rejected at the boundary.
- Per-actor authorization. AI tokens are separate from user cookies. Each token is scoped (can be restricted below the delegating user's permissions), short-lived, revocable. Never a "god mode" for the AI.
-
dangerous: truegating. Actions the platform marks dangerous (delete, void, force-password- reset, refund, etc.) surface the flag in their MCP schema. The AI runtime is expected to confirm with a human before invoking; our own agent enforces this. - Query actions vs mutations. Read-only queries (`crm.deal.list`, `hrm.employee.get`) return paginated + typed projections. Mutations always emit events + audit rows; queries never do.
- OAuth-style token minting. Delegate an AI agent from your session via `ai.token.create`, scoped to a subset of your permissions + a TTL. Revoke any time.
Clients we test with
MCP is a protocol, not a lock-in.
We test our server against Claude (Anthropic's flagship MCP client), Cursor, Zed, Sourcegraph Cody, and our own in-app agent. Any MCP-speaking client works; if it doesn't, that's a bug on our side, not yours.
- Claude Desktop / Claude Code
Reference MCP client; our default target. - Cursor
MCP tool support in the sidebar; tested against every release. - Zed
Native MCP support since Zed 0.148. - Custom agents
Any MCP-speaking runtime (Python `mcp` package, Node `@modelcontextprotocol/sdk`, self-authored).
Setup
Three steps.
- 1. Mint a token. Settings → API keys → New MCP token. Pick the scope (which actions can be called) + TTL. Copy the `mcp_*` bearer.
- 2. Add the server to your MCP client. Point the client at your org's MCP endpoint (default: `https://api.yourorg.com/mcp/v1`) with the token in the `Authorization: Bearer` header.
- 3. Ask the AI to do something. "Show me the deals that closed this week." "Draft a follow-up to Acme." "Advance Maria's application to interview." The AI picks the right tool, calls it, and the result flows back into the conversation.
MCP
Wire your agent up.
No plugin. No custom SDK. Standard MCP over your existing token.