The Coupler Analytics MCP server enables AI tools like Claude to query and analyze multi-channel business data from Coupler.io data flows, transforming raw data from platforms like Google Ads, Facebook, HubSpot, and Salesforce into actionable insights.
Core Capabilities:
List Data Flows - Browse all data flows with AI destinations, retrieving IDs, names, and last successful run information
Get Data Flow Details - Fetch comprehensive metadata including sources, data connections, schedules (crontab format), execution status, and error details
Query Data - Execute read-only SQL queries on data flow results stored as SQLite files for flexible analysis and filtering
Get Data Schema - Retrieve table structure including column names, labels, data types, and type options to understand data before querying
Common Use Cases:
Marketing Analytics - Calculate customer acquisition costs, analyze ROI by channel, identify top-performing campaigns
Sales Intelligence - Pull pipeline reports, track conversion rates, forecast revenue based on deal probabilities
Financial Reporting - Compare quarterly profits, generate cash flow reports, monitor accounts receivable and overdue invoices
Data Visualization - Generate static visualizations from queried data without external file dependencies
Technical Features:
Access marketing, sales, finance, and e-commerce data from hundreds of sources
Containerized deployment via Docker with environment configuration
Supports local development with Node.js and integration with MCP inspector for debugging
All operations are idempotent and work with data flows that have successful execution runs
Allows retrieving and analyzing marketing metrics from Facebook through Coupler.io data flows.
Enables fetching and transforming marketing data from Google Ads for analysis through Coupler.io data flows.
Provides access to marketing and sales data from HubSpot through Coupler.io data flows for comprehensive business analysis.
Enables querying and analyzing sales and customer data from Salesforce through Coupler.io data flows.
Supports executing read-only SQL queries on data flow results stored as SQLite files to extract insights from business data.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Coupler Analytics show me our sales pipeline report for this month"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Chat with your business data inside the AI assistant you already use. The Coupler.io Model Context Protocol (MCP) server connects your Coupler.io data flows — built from 400+ sources like Google Ads, Facebook, HubSpot, Salesforce, Stripe, Shopify, GA4 and more — to your AI tool, so you can ask questions about your marketing, sales, finance and product data in plain language.
Every answer is backed by Coupler.io's Analytical Engine: the AI never queries your source systems directly — it asks Coupler.io, which executes the query, verifies the calculations, and returns only validated results.
Looking to just use it? You don't need this repository. Most users connect through the hosted remote MCP in a few clicks — see Connect your AI tool below. This repo is the local (self-hosted) MCP server, for users who prefer to run it on their own machine.
Get data from your Coupler.io data flows and ask your AI tool questions about it, like you would ask a fellow data analyst:
What's our overall customer acquisition cost across all paid channels this quarter compared to last quarter? I need this for the board meeting.
Show me the ROI breakdown by marketing channel for the past 6 months. I need to reallocate our annual budget.
Which campaigns are contributing most to our pipeline revenue? I want to double down on what's working.
Can you pull the sales pipeline report for this month? I need to see how many deals are in each stage and the total value at each stage.
What are our conversion rates from lead to opportunity and from opportunity to closed-won for the last quarter? How do they compare to our targets?
How many deals are expected to close this month based on their probability scores? What's our forecasted revenue vs our monthly target?
Check the profit for this quarter, compare it to last quarter, and provide a breakdown by department.
Could you provide a cash flow report for the last 30 days, including all incoming and outgoing transactions?
Share the current accounts receivable status and tell me how many overdue invoices we have and which customers owe the most.
Related MCP server: Marketing Analytics AI MCP
Coupler.io AI integrations work with all the major assistants. Set up a data flow with an AI destination once, then query it from any of these:
AI tool | How it connects |
Claude — Claude.ai, Claude Desktop, Claude Code, Cowork | Web/org connector, or local Desktop Extension (this repo) |
ChatGPT — incl. Codex | Connector (remote MCP) |
MCP / Desktop Extension | |
Native connector | |
Remote MCP over HTTP ( | |
Remote MCP over HTTP | |
Connector (remote MCP) | |
Remote MCP via the | |
Custom MCP | Any MCP-capable client, using your remote MCP URL |
See the AI Integrations overview and the docs for the latest list and per-tool setup guides.
There are two ways to connect Coupler.io to your AI assistant.
Each tool connects differently. In every flow you first create and run a data flow in
Coupler.io with the matching tool set as the destination (only data flows with that
destination are exposed to it). Your account-specific connection URL,
https://mcp.coupler.io/mcp/<your-account-id>, is shown on the MCP page at
app.coupler.io/app/mcp.
For Claude.ai chat and Claude Cowork:
Create and run a data flow with Claude as the destination.
In Claude, open Settings → Connectors, add the Coupler.io connector and click Connect. On Team/Enterprise plans an admin must add it first.
Click Connect once more and log in to Coupler.io to authorize.
Open a new chat and start asking about your data.
Create and run a data flow with Claude as the destination.
Start a new session in Claude Code and run:
claude mcp add coupler-io --transport http https://mcp.coupler.io/mcpRestart the session.
Run /mcp, select Coupler.io, and complete authentication in the browser when prompted.
Create and run a data flow with ChatGPT as the destination.
In ChatGPT, add the Coupler.io app, click Connect, and authorize in the browser.
Click Start chat. For later sessions, make sure the Coupler.io app is active via + → More (a checkmark should appear next to it).
Create and run a data flow with Gemini as the destination, and make sure Gemini CLI is installed.
Add the Coupler.io MCP server:
gemini mcp add coupler --transport=http --scope=user https://mcp.coupler.io/mcp/<your-account-id>Start Gemini CLI and authenticate: /mcp auth coupler.
A browser window opens — sign in and authorize access to your Coupler.io account.
In Coupler.io, create OAuth credentials for Gemini Enterprise (account admin/owner only) — Coupler.io issues a Client ID and Client Secret (the secret is shown once).
In GCP, open Gemini Enterprise → Data stores → Create data store and choose Custom MCP server (see Google's guide).
Paste the values Coupler.io shows: MCP Server URL (https://mcp.coupler.io/mcp/<your-account-id>), Authorization URL, Token URL, Scopes (mcp), and the Client ID / Client Secret.
Create and run a data flow with Gemini Enterprise as the destination.
Open Microsoft Copilot Studio, pick the agent to extend, and make sure generative orchestration is on (the default for new agents).
Go to Tools → Add a tool → New tool → Model Context Protocol and paste the MCP URL (https://mcp.coupler.io/mcp/<your-account-id>).
Set Authentication to OAuth 2.0 with Dynamic discovery — no client ID or secret needed; Copilot Studio registers itself automatically. Click Create; users consent and sign in to Coupler.io once.
Create and run a data flow with Microsoft Copilot Studio as the destination.
mcporter skill)Create and run a data flow with OpenClaw as the destination.
Collect the Coupler.io skill from ClawHub.
Ask OpenClaw to connect the Coupler.io MCP using that skill, and complete the auth flow in the browser.
Cursor and Perplexity connect through a local install rather than the hosted endpoint — see Local MCP below.
Step-by-step guides with screen recordings for every tool live in the Coupler.io docs.
The hosted remote MCP exposes a much broader, continuously growing tool set. Some operations are gated behind account feature flags.
Data & analysis (available to all clients):
get-data — Query a Coupler.io data flow's data (the data table) with read-only SQL.
get-schema — Get the typed column schema and AI context for a data flow / dataset.
list-datasets — Discover available datasets, optionally filtered by data flow.
search-datasets — Search across datasets to find relevant data.
list-dataflows — List the user's data flows.
get-dataflow — Get a data flow's current state, sources, and destinations.
list-templates — Discover prebuilt templates by source, metric, or category.
run-dataflow — Trigger a data flow run to refresh its data.
update-dataset — Persist an AI-context (markdown) description for a dataset.
update-dataset-schema — Update a dataset's schema definition.
Skills:
list-skills — List specialized, end-to-end workflows.
get-skill — Fetch a skill's full procedure by name.
Guided data flow setup (feature-flagged):
list-credentials — List the user's source/destination credentials.
list-integrations — List available source or destination integrations.
get-integration — Get an integration's parameters, auth requirements, and options.
get-integration-field-options — Resolve dynamic option values for an integration field.
create-dataflow — Create a new, empty data flow.
create-dataflow-from-template — Create a data flow from a template.
create-dataflow-source / update-dataflow-source — Add or modify a data flow's source.
create-dataflow-destination / update-dataflow-destination — Add or modify a data flow's destination.
Run the MCP server on your own machine so analysis stays local. Two options:
A. Claude Desktop Extension (.mcpb) — the simplest local option:
Download the Coupler.io extension (.mcpb) — see build instructions, or grab it from the Coupler.io MCP page.
In Claude Desktop: Settings → Extensions → Install Extension, select the file.
Paste your Coupler.io Personal Access Token when prompted.
B. Docker — run the published image directly:
Prerequisites: Docker installed and running, and a Coupler.io Personal Access Token.
{
"mcpServers": {
"coupler": {
"command": "docker",
"args": [
"run",
"--pull=always",
"-e",
"COUPLER_ACCESS_TOKEN",
"--rm",
"-i",
"ghcr.io/railsware/coupler-io-mcp-server"
],
"env": {
"COUPLER_ACCESS_TOKEN": "<your_token>"
}
}
}
}
--pull=alwayskeeps the image up to date by pulling the latest on each run. Remove it if you're offline or want to pin a previously pulled image.
The self-hosted server (this repository) exposes a focused, read-only set of data-flow tools:
get-data — Gets the result of a data flow run as a SQLite file and runs a read-only query on it. The data flow must have an AI destination.
dataflowId (string, required), executionId (string, required), query (string, required)
get-schema — Gets the data flow schema file (data flows built from a dashboard or dataset template).
dataflowId (string, required), executionId (string, required)
list-dataflows — Lists data flows that have an AI destination.
get-dataflow — Gets data flow metadata: sources, connections, last successful execution, and error details.
dataflowId (string, required)
AI tools never connect to your source systems — all access flows through Coupler.io's secure layer.
Connections use scoped, read-only, short-lived tokens; the AI can list, query and inspect schemas, but cannot modify, delete, or reach raw source credentials.
Coupler.io is SOC 2 Type II certified and GDPR / HIPAA / DORA compliant. See the Trust Center.
Install Node.js and dependencies:
asdf plugin add nodejs https://github.com/asdf-vm/asdf-nodejs.git
asdf install
npm install
lefthook install
cp .env.example .env.localRun the server (use --silent so npm logs don't break the stdio transport):
npm run --silent devDebug with the MCP inspector (keep a single inspector tab open):
npm run inspect:nodeLogs go to a file (stdio transport):
tail -f log/development.log | npx pino-prettyBuild and self-sign the .mcpb extension:
bin/build_mcpb # => mcpb_output/coupler-mcp.mcpb
npm run mcpb:selfsignInstall the .mcpb file, or load the unpacked mcpb_output/ dir from Claude Desktop's Developer menu.
Licensed under the terms of the MIT open source license.
Get data from a Coupler.io data flow run. Make sure to first query a sample of 5 rows from data table, e.g. SELECT * from data LIMIT 5, and then run the get-schema tool, to better understand the structure. The get-schema tool will return the JSON-encoded schema of the data table. When visualizing the data, do not try to read any files or fetch any URLs, just generate a static page and use the data you get from the tools.
| Name | Required | Description | Default |
|---|---|---|---|
| dataflowId | Yes | The ID of the data flow with a successful run | |
| executionId | Yes | The ID of the last successful run (execution) of the data flow. | |
| query | Yes | The SQL query to run on the data flow sqlite file. |
| Name | Required | Description |
|---|---|---|
| data | Yes | The data returned from the query. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations include idempotentHint: true, which already indicates that the tool is safe to repeat. The description adds no behavioral details beyond that, such as side effects, authentication needs, or rate limits. It does not contradict the annotations, but it also does not provide extra disclosure beyond the purpose (getting data). Given the annotations cover the main behavioral trait, a score of 3 is appropriate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is front-loaded with the main purpose in the first sentence. It includes necessary workflow instructions but could be more concise by separating usage guidelines from the core purpose. The length is reasonable and does not contain fluff, though the sample query and get-schema instructions could be part of a separate section.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has an output schema (per context signals), so the description does not need to explain return values. The description gives enough context to use the tool in combination with the sibling tools (get-schema, list-dataflows). It covers the prerequisite steps and important caveats (no file/URL fetching). Overall, combined with the structured information, the description is sufficiently complete for an agent to use the tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with each parameter (dataflowId, executionId, query) having a clear description in the input schema. The tool description does not add any semantic information beyond what the schema already provides. The example query in the description ('SELECT * from data LIMIT 5') is a usage hint, not parameter semantics. Therefore, no added value beyond the schema baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The tool name 'get-data' and title 'Get and query data from a Coupler.io data flow' clearly indicate that the tool retrieves data. The description starts with 'Get data from a Coupler.io data flow run', which aligns with the purpose. However, it does not explicitly distinguish itself from sibling tools like get-schema or list-dataflows, though the name and context imply the distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit workflow guidance: first query a sample of 5 rows using a SELECT statement, then run get-schema to understand the structure. It also instructs on visualization behavior ('do not try to read any files or fetch any URLs'). While it gives clear context on when to use this tool, it does not mention when not to use it or explicitly name alternatives, though get-schema is referenced as a prerequisite.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a Coupler.io data flow by ID.
| Name | Required | Description | Default |
|---|---|---|---|
| dataflowId | Yes | The ID of the data flow with a successful run. |
| Name | Required | Description |
|---|---|---|
| dataflow | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description is accurate but does not disclose any behavioral traits beyond being a read operation. With minimal annotations (title only), the description carries the burden but omits details like idempotency, caching, or error behavior. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise (one sentence) with no wasted words. However, it lacks additional details that could be included without bloat.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (1 parameter, output schema exists), the description is minimally adequate. It misses usage guidelines and any prerequisites, but the output schema compensates for return value documentation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the schema already provides a description for the only parameter (dataflowId). The tool description adds no additional meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (Get) and the resource (a Coupler.io data flow by ID). It distinguishes from siblings like 'list-dataflows' (list) and 'get-data'/'get-schema' (different entities).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives (e.g., when to use 'list-dataflows' or 'get-data'). No explicit 'when to use' or 'when not to use' context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get data table schema from a Coupler.io data flow. Get column names from columnName properties in column definitions. Example: {"columns":[{"key":"Row Updated At.0","label":"Row Updated At","schema":{"type":"string"},"typeOptions":{},"columnName":"col_0"},{"key":"Dimension: Source.0","label":"Dimension: Source","schema":{"type":"string"},"typeOptions":{},"columnName":"col_1"}]}. Here the columns are col_0 and col_1.
| Name | Required | Description | Default |
|---|---|---|---|
| dataflowId | Yes | The ID of the data flow with a successful run | |
| executionId | Yes | The ID of the last successful run (execution) of the data flow. |
| Name | Required | Description |
|---|---|---|
| schema | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations set idempotentHint=true, confirming safe reuse. The description adds behavioral context by explaining how to interpret the response (columnName properties) and providing a concrete example. No contradictions with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, no filler. First sentence defines the action, second explains how to extract column names, third provides an illustrative example. Every sentence adds value, and the structure is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 2 required parameters, existing output schema, and idempotent annotation, the description adequately covers purpose and response interpretation. Lacks explicit error scenarios or prerequisites beyond parameter descriptions, but overall complete enough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Both parameters (dataflowId, executionId) have clear descriptions in the input schema, achieving 100% schema coverage. The description does not add additional meaning to these parameters, focusing instead on the output format. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Get data table schema from a Coupler.io data flow' with a specific verb and resource. It distinguishes from siblings by focusing on schema retrieval, differentiating from get-data (data), get-dataflow (metadata), and list-dataflows (enumeration).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool versus alternatives. It implies usage for obtaining column names before fetching data, but lacks explicit when-to-use or when-not-to-use guidance. The example helps but does not clarify selection criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List my Coupler.io data flows. Use this to get the ID (uuid format) of a data flow by its name.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| dataflows | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations include idempotentHint=true, indicating no side effects. Description adds that it lists 'my' data flows (scope) and returns IDs, which is consistent and adds value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short, informative sentences with no extraneous information. Purpose and specific usage are front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a parameterless list tool with an output schema, the description covers the essential: it lists flows and can be used to find an ID by name. No further guidance is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has zero parameters, baseline is 4. Description does not add parameter info, but schema coverage is 100% since there are no parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it lists Coupler.io data flows and specifies the use case: to get a data flow's UUID by name. Distinguishes from sibling tools like get-dataflow (which likely returns a single flow) by its listing nature.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly advises using it to retrieve a data flow ID by name, providing a clear context. Does not mention when not to use or alternatives, but for a simple list tool this is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v1.0.0get-dataget-dataflowget-schemalist-dataflowsEach tool has a distinct purpose: listing flows, getting a specific flow, retrieving schema, and fetching data. No functional overlap exists.
All tool names follow a consistent verb-noun pattern (get-data, get-dataflow, get-schema, list-dataflows) using lowercase with hyphens. Minor variation between 'get' and 'list' but the structure is uniform.
With only 4 tools, the set is well-scoped for exploring and fetching data from Coupler.io data flows. No unnecessary tools, and the count fits the domain.
The set covers the full read workflow: list flows, examine metadata, get schema, retrieve data. Missing CRUD operations (create/update/delete) but that aligns with a read-only analysis tool.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
MCP server for querying and analyzing data from ad platforms, analytics tools, and spreadsheets
Analytics your AI agent can actually use. Track, experiment, and optimize via MCP.
Marketing-measurement MCP: dashboards, cross-channel queries, integrations, and knowledge files.
Let AI agents query data and act across all your business apps via MCP.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/railsware/coupler-io-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
