# AI agents & MCP

> AI agents work with Convia Pro in two ways: they read these docs as markdown, and they act on a workspace through the Convia MCP server. These pages cover connecting Claude or another MCP client, every MCP tool, agent workflows, access and audit, and the machine-readable docs.

> For the complete documentation index, see [llms.txt](https://docs.conviapro.com/llms.txt).

- [Convia for AI agents](https://docs.conviapro.com/docs/ai-agents-overview.md): Learn the two ways AI agents work with Convia, reading these docs and acting on a workspace through MCP, plus what an agent can and cannot do.
- [Connect an AI assistant (MCP)](https://docs.conviapro.com/docs/mcp-quickstart.md): Connect Claude, Claude Code or another MCP client to a Convia workspace, using a claude.ai connector or a workspace token, and check it works.
- [MCP tool reference](https://docs.conviapro.com/docs/mcp-tools.md): Look up every tool the Convia MCP server exposes, with exact parameters, limits, return shapes, side effects, errors and the instructions it sends clients.
- [Agent workflows](https://docs.conviapro.com/docs/mcp-workflows.md): Follow step-by-step MCP recipes for AI agents in Convia, from drafting an on-brand post to building a campaign, revising drafts and taking posts back.
- [MCP access, permissions & audit](https://docs.conviapro.com/docs/mcp-security.md): Learn who can connect an AI client to a Convia workspace, how tokens and OAuth work, what each request is checked against, and how to audit activity.
- [Machine-readable docs](https://docs.conviapro.com/docs/machine-readable-docs.md): Read the Convia docs as markdown, through llms.txt, llms-full.txt, a .md version of every page, content negotiation and the Copy page menu.
- [Glossary](https://docs.conviapro.com/docs/glossary.md): Look up the Convia terms customers and AI agents meet, from Brand Brain and beats to Autopilot, AI credits and MCP tokens, each linked to its page.