ReputeMap MCP
Enables AI agents to manage Google Business Profile reviews, including a filterable review inbox, per-location stats, and honest review-request campaigns.
README
ReputeMap MCP — Google review management for AI agents
The Model Context Protocol surface of ReputeMap: Google Business Profile reviews — a filterable review inbox, per-location stats, and honest review-request campaigns — for Claude, Cursor, Codex, Gemini CLI and any other MCP-capable agent.
"Show me every unanswered review under 3 stars from the last week, worst first." "Draft replies to the three newest negative reviews in a calm tone." "We just finished the Hendersons' job — send them a review request."
You probably don't need to run anything. The server is hosted:
https://api.reputemap.com/mcp Streamable HTTP · JSON-RPC 2.0
Authorization: Bearer rmk_YOUR_KEY app.reputemap.com → Settings → API keys
Registry: com.reputemap/reputemap · any paid plan (the 14-day free trial counts).
Setup per client
Claude Code — one command, no restart:
claude mcp add --transport http reputemap https://api.reputemap.com/mcp \
--header "Authorization: Bearer rmk_YOUR_KEY"
Cursor — .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"reputemap": {
"url": "https://api.reputemap.com/mcp",
"headers": { "Authorization": "Bearer rmk_YOUR_KEY" }
}
}
}
Claude Desktop — claude_desktop_config.json, then restart the app fully:
{
"mcpServers": {
"reputemap": {
"command": "npx",
"args": ["-y", "@reputemap/mcp"],
"env": { "REPUTEMAP_API_KEY": "rmk_YOUR_KEY" }
}
}
}
VS Code (Copilot agent mode) — .vscode/mcp.json:
{
"servers": {
"reputemap": {
"type": "http",
"url": "https://api.reputemap.com/mcp",
"headers": { "Authorization": "Bearer rmk_YOUR_KEY" }
}
}
}
Windsurf — ~/.codeium/windsurf/mcp_config.json (the field is serverUrl):
{
"mcpServers": {
"reputemap": {
"serverUrl": "https://api.reputemap.com/mcp",
"headers": { "Authorization": "Bearer rmk_YOUR_KEY" }
}
}
}
Codex CLI — ~/.codex/config.toml, then export REPUTEMAP_API_KEY:
[mcp_servers.reputemap]
url = "https://api.reputemap.com/mcp"
bearer_token_env_var = "REPUTEMAP_API_KEY"
Gemini CLI — ~/.gemini/settings.json (the field is httpUrl):
{
"mcpServers": {
"reputemap": {
"httpUrl": "https://api.reputemap.com/mcp",
"headers": { "Authorization": "Bearer rmk_YOUR_KEY" }
}
}
}
ChatGPT — Settings → Connectors → create a custom connector (Developer
mode), point it at https://api.reputemap.com/mcp and pick API key
authentication, then paste your key.
Full walkthroughs with screenshots: reputemap.com/docs/mcp.
More recipes (cron digests, CRM sync): reputemap/examples.
Companion agent skills:
reputemap/review-skills
(npx skills add reputemap/review-skills).
What's in this repo
A zero-dependency stdio bridge for clients that speak MCP over stdio and
can't send HTTP headers — in two flavours: bin/cli.mjs
(Node 18+, published as
@reputemap/mcp) and
server.py (Python 3.9+, stdlib only). Both forward every
JSON-RPC message to the hosted endpoint over TLS and stream responses back.
# Node — one-liner, no install
REPUTEMAP_API_KEY="rmk_..." npx -y @reputemap/mcp
# Python — no dependencies
REPUTEMAP_API_KEY="rmk_..." python3 server.py
server.json is the manifest published to the
official MCP registry as
com.reputemap/reputemap.
Being ~120 readable lines, the bridge doubles as a reference for what
travels over the wire: your API key goes only into the Authorization
header of TLS requests to api.reputemap.com — nothing else, nowhere else.
Tools
| Tool | What it does | Credits |
|---|---|---|
list_locations |
Every location the org manages, with ids | 1 |
list_reviews |
Reviews, filterable (location, rating range, unanswered, last N days) — includes published reply text | 1 |
get_review_stats |
Per-location + totals: counts, average rating, 1–5 breakdown, unanswered, trailing-window activity | 1 |
send_review_request |
Sends a real review-request email through the campaign engine (respects opt-outs; idempotent) | 1 |
get_usage |
Current month's credit usage | free |
Credits ship with every ReputeMap plan (1,000/month, shared with the
REST API); get_usage is free and tells you
where you stand. Rate limit: 60 requests/minute per org.
The one write action — send_review_request — goes through the same
suppression/opt-out engine as in-app campaigns, so an over-eager agent can't
spam your customers. Tools carry MCP annotations
(readOnlyHint/destructiveHint), and discovery (initialize, tools/list)
works without a key, so clients can render the catalog before you authenticate.
Revoke the key at any time and access dies instantly.
Protocol notes
- Methods:
initialize→notifications/initialized→tools/list/tools/call. Protocol errors use standard JSON-RPC codes; tool-level errors (bad id, out of credits) come back as tool results your agent can read. - The server is stateless — no session required; the bridge still honours
Mcp-Session-Idand accepts both JSON and SSE-framed responses. - Batch requests are rejected (removed in MCP 2025-11-25); foreign
Originheaders are refused.
Links
- 🌐 reputemap.com — Google review management for agencies & local businesses
- 📚 API docs · MCP docs
- ✉️ yaro@reputemap.com
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.