HomeCustomer Feedback + MCP
Customer feedback MCP server
Manage your feedback backlog from your AI agent.
Every project ships its own remote MCP server with 42 tools. Connect your AI agent once, and it manages the project at your permission level: triage requests, reply to conversations, send announcements, configure the widget, manage the team.
OAuth 2.1 secured · Role-gated · Works with Claude, GPT, and any MCP client
What it is
A remote MCP server with 42 tools, built into every project
The Model Context Protocol (MCP) is an open standard that lets AI agents call external tools over a structured protocol. Reqio runs an MCP server for every project, and your agent manages the whole project through the same interface it already uses.
- Remote Streamable-HTTP server, connects over HTTPS, no local process required
- OAuth 2.1 authenticated, one token per project, audience-bound
- 42 tools covering backlog, conversations, announcements, widget config, members, and project
- Role-gated: the agent gets exactly the connecting user's permissions, nothing more
- Quota-gated per plan, Free, Pro, and Scale limits apply
42 MCP tools
What your AI agent can do
The Reqio MCP server exposes 42 tools across fifteen domains, each a thin wrapper over a real dashboard operation. Billing, project deletion, and token issuance are never tools.
list_features
List the backlog, filter by status, category, sort order. Returns titles, vote counts, current status.
get_feature
Get full detail on one request: title, status, Context, category, vote count, submitter.
get_project_stats
Get project stats: total requests, requests by status, total votes, requests by category.
change_status
Move a request through the pipeline: Needs action, In progress, Completed. Triggers subscriber notifications on Completed.
set_developer_note
Write or update the private Context on a request: implementation details, blockers, target release.
add_comment
Add a comment to a request. Visible to users who submitted or voted on it.
delete_comment
Remove a comment from a feature request. Requires comments:delete scope.
delete_feature
Delete a feature request entirely. Requires features:delete scope. Irreversible.
list_conversations
List the private inbox, filter by kind (bug, unexpected, feedback, question) and state. Returns unread counts and last-active times.
get_conversation
Get a full conversation thread including all messages, structured diagnostic context, and requester info.
reply_conversation
Post a team reply into a private conversation. Notifies the requester in-widget and by email.
convert_conversation_to_feature
Create a public feature request from any private conversation. Subscribes the original reporter automatically.
send_announcement
Send a project-wide announcement to all contactable project recipients. High-reach and irreversible, requires explicit confirmation.
get_widget_config
Read the project's current widget and branding configuration.
update_widget_config
Update widget and branding settings. Plan-gated fields (custom logo, badge removal) follow the same rules as the dashboard.
list_members
List all project members and pending invites, including roles.
invite_member
Invite a person to the project by email. Owner-only. Invited role is Developer.
remove_member
Remove a member's access to the project. Owner-only. Requires explicit confirmation.
rename_project
Rename the project. Reflected immediately in the dashboard and widget header.
OAuth 2.1 authentication
One token per project. Role-gated. Scope-gated.
The Reqio MCP server uses OAuth 2.1. Reqio is the Authorization Server, your agent is the client, and the flow is the standard one your tools already speak. Nothing bespoke to configure.
- Tokens are opaque and stored in the database, never exposed in logs
- Each token is audience-bound to one project URL (/p/{projectId})
- 42 tools grouped under 24 granular scopes, role-gated, covering all fifteen tool domains
- Role check runs live on every call, the same permission matrix as the dashboard
- Revoke any connected agent from the Settings MCP tab
Getting connected
Connect your AI agent in three steps
Create a Reqio project
Sign up and create a project. The MCP server is provisioned automatically. No separate setup required.
Connect your AI agent
Copy the MCP server URL from project settings. Add it to your AI agent's MCP server list. It'll prompt you for OAuth consent on first connection.
Approve the scopes
You see exactly which scopes the agent wants, across backlog, conversations, announcements, widget, members, and project. Approve what you want. The agent is connected and ready to work.
Use cases
What AI agents do with your project
Morning backlog triage
Ask your agent to read the backlog, summarize the top-voted requests, and flag any new error reports since yesterday. It reads live data, no copy-paste.
Reply to conversations
Point your agent at the private inbox. It reads open conversations, drafts a reply, and posts it using `reply_conversation`. The requester gets notified in-widget and by email.
Ship and announce
After a deploy, ask your agent to mark the matching request Completed and announce it to all project contacts. Notifications go out automatically, no dashboard tab required.
Onboard a new developer
Ask your agent to invite a new teammate by email using `invite_member`. The invite is sent immediately. Owner-only, so only your owner-connected agent can do it.
Questions
Questions about the Reqio MCP server
What is an MCP server?
MCP (Model Context Protocol) is an open standard from Anthropic that lets AI agents call external tools through a structured, typed protocol. A server exposes named tools with defined input and output schemas. An agent connects once, via OAuth, and calls those tools in any conversation, no custom integration code.
Is the Reqio MCP server a local server or a remote server?
Remote. It runs as a Streamable-HTTP endpoint on reqio.app. No local process to run, no port to expose. Your agent connects over HTTPS with a Bearer token. It works with any MCP client that supports remote servers, including Claude Desktop, Claude.ai, and any agent using the MCP SDK.
Which AI coding agents work with the Reqio MCP server?
Any MCP-compatible client works: Claude (Anthropic), GPT-based agents using the MCP SDK, and custom agents built on the open standard. Reqio speaks Streamable-HTTP, the current standard for remote MCP servers.
What scopes can I grant my AI agent?
Reqio supports 24 granular OAuth scopes across all 42 MCP tools and fifteen domains: backlog (read, write), status (write), notes (write), comments (write, delete), features (delete), conversations (read, write), announcements (write), widget (read, write), members (read, write, delete), project (write), requesters (read), notifications (read), email (read, write), identity (read, write), analytics (read), ship (read). Grant scopes at connection time; revoke any time from the MCP tab in project settings. Destructive scopes are listed separately, never bundled into one connect action.
Can the AI agent do anything my team members can't?
No. The MCP server re-runs a live permission check on every call, the same matrix that governs dashboard access. If a scope needs a capability the connecting user doesn't hold, the call is rejected. A developer agent can't invite or remove members, that's owner-only. Billing, project deletion, and token issuance aren't tools at all, no agent can reach them.
How many MCP calls can my agent make per day?
Your daily quota depends on your plan. Free has a limited quota; paid plans go higher. Each tool call counts as one. Exceed it, and calls return a quota-exceeded error until the next day's reset.
Is there a feedback tool with MCP support other than Reqio?
Reqio ships a built-in, production-ready, OAuth 2.1-secured MCP server with full project management as a core feature. Typed tool schemas, role-gated access, native AI-agent support, this is a different category from Zapier or webhook approaches.
Let your AI agent work the feedback backlog.
Connect your AI agent freeOAuth 2.1 secured · Free to start · Works with any MCP client