Model Context Protocol

Connect AI agents to your Quickly command center.

Quickly exposes a hosted MCP server so compatible clients can discover workspace knowledge, list agents and playbooks, trigger governed workflows, and inspect audit logs through the same permission model as the public API.

Open MCP setup View API reference

Server URL

https://mcp.askquickly.ai/api/mcp/v1

Protected resource metadata

https://mcp.askquickly.ai/.well-known/oauth-protected-resource

Authorization server metadata

https://app.askquickly.ai/.well-known/oauth-authorization-server

Install from Codex

Create a workspace API key in Quickly, store it as an environment variable, then register the Streamable HTTP MCP server.

export QUICKLY_API_KEY="qk_..."

codex mcp add quickly --url https://mcp.askquickly.ai/api/mcp/v1 \
  --bearer-token-env-var QUICKLY_API_KEY

Tool surface

The v1 MCP catalog is curated for agent workflows: read knowledge, inspect records, trigger playbooks, and audit outcomes. Destructive actions require the right scope and still pass through Quickly's workflow safety controls.

OAuth/API scopes

knowledge:readknowledge:writeplaybooks:readplaybooks:executelogs:readagents:readmcp:tools

knowledge_search

Search workspace knowledge bases and return grounded results.

knowledge_base_list

List available workspace knowledge bases.

playbook_list

Find playbooks an agent can run.

playbook_trigger

Trigger a governed playbook run with approval and audit controls.

playbook_run_get

Fetch a specific playbook run.

playbook_run_list

List recent playbook runs.

entity_list

Search workspace entities and CRM-style records.

entity_get

Fetch a specific entity record.

entity_create

Create a workspace-scoped entity record.

entity_update

Update a workspace-scoped entity record.

task_list

List recent Quickly task and audit records.

task_get

Fetch one task with execution details.

agent_list

List scheduled playbook agents.

Agent-readable discovery

AI agents can start with the public discovery files below to find the API, MCP server, setup instructions, and safety model without crawling the full marketing site.

/llms.txt

Curated AI-readable site map

/llms-full.txt

Expanded API and MCP context

/openapi.json

Machine-readable REST API surface