Integrations: Official respond.io MCP server
in progress
Lucas Clemente
Business Problem:
Agencies and advanced users increasingly use AI assistants (Claude, Claude Code, ChatGPT, Cursor) to build, configure, and maintain customer workspaces. Today this creates two distinct blockers:
- For everything the REST API covers (contacts, messages, custom fields, broadcasts), users must write custom scripts every time instead of asking the assistant directly.
- For everything the API does not cover (Workflows, AI Agents, Snippets, channel configuration), the work is 100% manual in the UI — no AI assistance, auditing, or automation is possible at all.
- For agencies managing dozens of client workspaces, this multiplies onboarding time and increases configuration errors.
Desired Outcome:
An official respond.io MCP (Model Context Protocol) server that allows any compatible AI assistant to connect via a standard connector and execute actions in natural language without writing code.
- Contact management: Search, update, tag, and move contacts across lifecycle stages via natural language.
- Messaging and broadcasts: Send broadcasts to tagged segments, read and summarize unanswered conversations.
- Snippets: Create, list, and detect duplicate or outdated snippets programmatically.
- Audit and diagnosis (stretch goal): Read and inspect Workflow and AI Agent configurations to assist with setup, auditing, and cross-workspace comparison.
Minimum actions the MCP should expose:
- Read / create / update contacts, custom fields, tags, and lifecycle stages
- Send individual messages and broadcasts
- Read conversation history and internal comments
- Programmatically create, list, and edit Snippets
- (Stretch goal) Read and inspect Workflow and AI Agent configuration for auditing and setup assistance
Neranjan Embogama
Adding two specific, tested gaps to this request — both hit while running a recurring batch-analysis workflow through the MCP server.
- No multi-Workspace access, and no visibility when it switches. The connection authorizes one Workspace at a time. Worse: no tool response returns which Workspace it's scoped to, so a silent re-authorization to a different Workspace (including from another session on the same account) is undetectable except by manually cross-checking results like channel names. For multi-brand/agency use, that's a correctness risk, not just friction.
- No bulk contact matching. Contact search only supports single-value isEqualTo on phone/email — no hasAnyOf/in batch operator (unlike tags/lifecycle, which have one). There's also no bulk contact export. Matching a batch of leads against existing Contacts — a normal weekly/monthly task — currently takes one API call per lead instead of one call total.
Use case: match externally-sourced leads against respond.io Contacts by phone/email, read the real conversation for each match, and classify lead quality for downstream reporting. This depends on raw, unsummarized message history, not the Lifecycle field or an AI summary — we tested this directly, and Lifecycle disagreed with the verified real outcome multiple times, including one contact with a recorded transaction value still tagged as unqualified. Any bulk solution needs to keep raw conversation access, not replace it with another layer of classification.
Asks:
hasAnyOf support for phone/email in contact search, or a paginated bulk contact export
Every tool response includes the active workspace_id, so a switch is always visible
Ideally: one connection spanning multiple Workspaces, with an optional workspace_id param per call
N
Nabilah Binti Salleh
Merged in a post:
API for developers: Endpoint for querying broadcasts
D
Diana Cuenca
We need an endpoint to list broadcasts and view their API submission metrics, including:
- total sent
- total failed
- total delivered
- total read
- percentages by state
Use case:
We want to integrate these metrics into our internal system to automate campaign monitoring and reporting, without relying on the panel manually.
Expected impact:
- automated reporting
- centralized campaign monitoring
- integration with internal dashboards
N
Nabilah Binti Salleh
updated the status to
in progress
S
Shi Hui
updated the status to
planned