# @instantreply.co/mcp

AI agent toolkit for WhatsApp, Instagram, and Messenger automation with zero-key MCP pairing, Barq AI, inbox tools, campaigns, templates, and developer diagnostics.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the package rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.2.2
- **Author:** Unknown
- **License:** MIT
- **npm:** @instantreply.co/mcp
- **Endpoints:** streamable-http https://api.instantreply.co/mcp
- **Source:** https://github.com/suleimandoescsec/instantreply-mcp
- **Endpoint health:** reachable (last checked 2026-09-27T08:05:47.049Z, 1 sample) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the package rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 0 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-27T08:05:15.186Z
- **Version scanned:** 0.2.2
- **CVEs:** none found by OSV at scan time

## Tools

40 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `draft_reply` — Draft a reply to a customer message in your brand voice
- `customer_message` — The customer message to reply to
- `tone` — Tone: friendly, professional, empathetic, concise
- `context` — Additional context about the customer or situation
- `summarize_conversation` — Summarize a conversation for a quick handoff or review
- `messages` — JSON array of messages from list_messages tool
- `find_urgent_unanswered` — Identify urgent or unanswered messages that need immediate attention
- `conversations` — JSON from list_conversations
- `weekly_inbox_digest` — Generate a weekly performance digest from analytics data
- `analytics` — JSON from get_analytics_summary
- `suggest_macros` — Suggest canned response macros based on recent conversation patterns
- `escalation_note` — Write an internal escalation note for a difficult conversation
- `conversation_summary` — Summary of the conversation
- `escalation_reason` — Why this needs escalation
- `audit_template_cost` — Audit WhatsApp templates for category, approval state, and cheaper UTILITY-safe alternatives
- `templates` — JSON from list_templates with stats=true when available
- `business_context` — Business, user action, or event that justifies each template
- `utility_rewrite_loop` — Plan a safe rewrite-submit-poll loop for templates that should legitimately be UTILITY
- `template_goal` — The business event and recipient action the template supports
- `current_copy` — Current template copy or rejected/marketing copy
- `language` — Language code, e.g. en or ar
- `journey_recommendation` — Recommend WhatsApp journeys, trigger names, templates, and status checks for a business workflow
- `workflow` — Business workflow or product event map
- `audience` — Recipient type and consent/source of the phone number
- `image_to_whatsapp_template_brief` — Turn a provided image, campaign asset, or product screenshot into compliant WhatsApp template ideas
- `image_description` — Description of the uploaded/generated image or screenshot
- `objective` — What the business wants the WhatsApp message to accomplish
- `recipient_context` — Why the recipient expects this message
- `debug_last_failure` — Explain the most recent WhatsApp delivery/template failure and recommend the next action
- `failure_json` — JSON from check_journey_status, list_messages, or explain_delivery_failure
- `get_connection_guide` — Get how to connect each channel (Instagram, WhatsApp, Messenger, Telegram, Shopify, calendars): where the user clicks, what Meta requires first, and how long it
- `start_setup` — Start connecting this AI agent to InstantReply. Call this first if no other tools are available. Returns a short code and a link — tell the user to open the lin
- `check_setup` — Check whether the user has approved the setup link from start_setup, and wait a short while if not. Once approved, the AI agent has a live InstantReply connecti
- `list_conversations` — List inbox conversations. Filter by status (active/closed/pending), platform (instagram/whatsapp/messenger), or assignee.
- `get_conversation` — Get a single conversation by ID, including customer details and last message.
- `list_messages` — List messages in a conversation. Returns most recent first.
- `send_message` — Send a reply message in a conversation. Use for responding to customers across Instagram, WhatsApp, or Messenger.
- `assign_conversation` — Assign or unassign a conversation to a team member. Pass null to unassign.
- `close_conversation` — Close an active conversation.
- `list_contacts` — List contacts (leads) in the workspace. Filter by platform.

## Install

**Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for.
**Cautions** (coverage gaps and advisories — never blocking)
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"mcp\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@instantreply.co/mcp\"\n      ],\n      \"env\": {\n        \"INSTANTREPLY_API_KEY\": \"<YOUR_INSTANTREPLY_API_KEY>\"\n      }\n    }\n  }\n}"
```
**Credentials it will ask for** (names only — Forge never holds a value):
- `INSTANTREPLY_API_KEY` — Instantreply API Key (optional)
Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each <YOUR_NAME> in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one.
- This entry needs 1 credential (0 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset.

## Blast radius

Moderate blast radius — runs locally and hosted; holds an api key.
- Floor 27, ceiling 27 (tier: moderate)
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40instantreply.co%2Fmcp
- Install plan: https://forgeregistry.com/api/v1/packages/%40instantreply.co%2Fmcp/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40instantreply.co%2Fmcp
- HTML page: https://forgeregistry.com/registry/%40instantreply.co%2Fmcp
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.
