Model Context Protocol (MCP)

This feature is only enabled on certain environments and tenants. Please contact Support for more information about this feature.

This feature is a work in progress and updates may be made from release to release. Please contact Support if you have any questions or feedback.

Upgrades to implement the 2026-07-28 specification are planned when broader support is available in AI clients.

Model Context Protocol (MCP) enables AI systems to securely connect to external tools and data. In the context of Coherent Spark, MCP allows AI agents to interact directly with Spark-generated APIs, unlocking agentic use cases that build on existing Excel logic. To support this, Coherent provides a remote MCP server that clients can use to integrate Spark into AI-driven workflows.

What is the Model Context Protocol (MCP)? - Model Context ProtocolModel Context Protocol

Prerequisites

Before connecting to the Coherent MCP server, make sure you have the following:

• Access credentials to a Spark tenant. Access can be authenticated using either:

  • User login.

  • Authorization token: This can be retrieved from the User menu.

• MCP compatible AI client: e.g. Claude, Cursor, Visual Studio Code, etc.

Connect to the Coherent MCP Server

This guide explains how to connect your AI client to the Coherent MCP server to access Coherent Spark tools and capabilities.

Configure for Claude

Claude desktop

The Claude desktop apps bring Claude's capabilities directly to your computer, allowing for seamless integration with your workflow.

1. Follow the instructions for connectors.

   • Name: coherent-spark (can be customized).

   • Remote MCP server URL: https://mcp.{environment}.coherent.global/{tenant}/mcp, replacing {environment} and {tenant}, with your specific environment and tenant details.

   • If Custom connectors are not available, they may need to be provisioned by the plan owner.

2. Click Connect and you will be prompted for a Coherent Spark login.

Claude code CLI

Claude Code is an agentic coding tool that reads your codebase, edits files, runs commands, and integrates with your development tools. Reference Add a remote HTTP server.

User login authentication

The name coherent-spark can be customized. Update myenvironment and mytenant then submit.

When trying to access the server, you will be prompted for a Coherent Spark login.

claude mcp add --transport http coherent-spark https://mcp.myenvironment.coherent.global/mytenant/mcp

Authorization token

The name coherent-spark can be customized. Update myenvironment, mytenant, and {token} then submit.

claude mcp add --transport http coherent-spark https://mcp.myenvironment.coherent.global/mytenant/mcp --header "Authorization: Bearer {token}"

Configure for Cursor

Cursor is an AI-assisted integrated development environment for Windows, macOS, and Linux. It is a fork of Visual Studio Code with additional AI features. Reference Model Context Protocol (MCP).

1. Open Cursor Settings, Tools & MCP.

2. Click Add Custom MCP.

3. Add the appropriate snippet from below based upon your choice of authentication.

4. For Cursor, it is recommended to restart the application to use the new Custom MCP.

User login authentication

If you do not have any MCP servers configured, add the following snippet into the document. If you already have other MCP servers defined, add coherent-spark into mcpServers{}.

The name coherent-spark can be customized. Update myenvironment and mytenant then save.

When trying to access the server, you will be prompted for a Coherent Spark login.

{
  "mcpServers": {
    "coherent-spark": {
      "url": "https://mcp.myenvironment.coherent.global/mytenant/mcp",
      "type": "streamableHttp"
    }
  }
}

Authorization token

If you do not have any MCP servers configured, add the following snippet into the document. If you already have other MCP servers defined, add coherent-spark into mcpServers{}.

The name coherent-spark can be customized. Update myenvironment, mytenant, and {token} then save.

{
  "mcpServers": {
    "coherent-spark": {
      "url": "https://mcp.myenvironment.coherent.global/mcp",
      "type": "streamableHttp",
      "headers": {
        "Authorization": "Bearer {token}"
      }
    }
  }
}

Configure for Visual Studio Code

Visual Studio Code (commonly referred to as VS Code) is an integrated development environment developed by Microsoft for Windows, Linux, macOS and web browsers. Reference Add and manage MCP servers in VS Code.

1. Open the Command Palette (Ctrl+Shift+P or F1).

2. Select the command MCP: Open User Configuration.

3. Add the appropriate snippet from below based upon your choice of authentication.

4. From the editor you can Start the server.

User login authentication

If you do not have any MCP servers configured, add the following snippet into the document. If you already have other MCP servers defined, add coherent-spark into servers{}.

The name coherent-spark can be customized. Update myenvironment and mytenant then save.

When trying to access the server, you will be prompted for a Coherent Spark login.

{
  "servers": {
    "coherent-spark": {
      "type": "http",
      "url": "https://mcp.myenvironment.coherent.global/mytenant/mcp"
    }
  }
}

Authorization token

If you do not have any MCP servers configured, add the following snippet into the document. If you already have other MCP servers defined, add coherent-spark into servers{}.

The name coherent-spark can be customized. Update myenvironment , mytenant, and {token} then save.

{
  "servers": {
    "coherent-spark": {
      "type": "http",
      "url": "https://mcp.myenvironment.coherent.global/mytenant/mcp",
      "headers": {
        "Authorization": "Bearer {token}"
      }
    }
  }
}

Configure for other MCP Clients

For other MCP-compatible clients, use the following connection details:

Key	Value
Transport	http
Server URL	https://mcp.{environment}.coherent.global/{tenant}/mcp The {environment} is part of your Log in to Spark URL. Example: https://mcp.myenvironment.coherent.global/mcp
Protocol Version	2024-11-05 or later
Authentication	If using the authorization token, then include the Authorization request header. Example: Authorization: Bearer eyJhbGciO...

Use Coherent MCP tools

Once connected to the MCP server, your AI client will have access to the following tools.

Spark Execute v3

• Name: spark_execute_v3

• Description: Execute an API call to a Spark service.

• Reference: Execute API (v3).

Property	Description
folder *	Spark service folder name.
service *	Spark service name.
revision	Spark service version number.
version_id	version_id of Spark service version. Identifies specific service version.
requestPayload	Request payload as JSON object.
call_purpose	Call purpose for tagging API call.
source_system	Source system for tagging API call.
correlation_id	Correlation ID for tagging API call.
service_category	Comma separated string of subservices to invoke.
transaction_date	Transaction date to resolve a version number if revision or version_id are not provided.

Spark service info

• Name: spark_service_info

• Description: Get information about a Spark service.

• Reference: Get service version.

Property	Description
folder *	Spark service folder name.
service *	Spark service name.
version_id	version_id of Spark service version. Identifies specific service version.

Spark service generate code snippet

• Name: spark_generate_snippet

• Description: Generate code to call Spark service Execute API using postman-code-generators.

Property	Description
folder *	Spark service folder name.
service *	Spark service name.
version_id	version_id of a Spark service version. This identifies the specific service version to use.
language_code	Language code for code snippet generation. Common values: "curl", "javascript", "python". Default: "curl".
language_variant	Language variant for code snippet generation. Common values for language_code "curl": "cURL". Common values for language_code "javascript": "Fetch", "jQuery", "XHR". Common values for language_code "python": "http.client", "Requests". Default to the value of language_code.

List supported snippet languages

To get the list of language_code and language_variant, run the following script.

JavaScript

var codegen = require('postman-code-generators'),
    supportedCodegens = codegen.getLanguageList();

var table = supportedCodegens.map(function (lang) {
    return {
        key: lang.key,
        label: lang.label,
        syntax_mode: lang.syntax_mode,
        variants: lang.variants.map(function (v) { return v.key; }).join(', ')
    };
});

console.log('key,label,syntax_mode,variants');
table.forEach(function (row) {
    console.log([row.key, row.label, row.syntax_mode, '"' + row.variants + '"'].join(','));
});

This is the list of language_code and language_variants:

language_code	language_variant
curl	cURL
dart	dio, http
go	Native
http	HTTP
java	OkHttp, Unirest
javascript	Fetch, jQuery, XHR
kotlin	Okhttp
c	libcurl
nodejs	Axios, Native, Request, Unirest
objective-c	NSURLSession
ocaml	Cohttp
php	cURL, Guzzle, HTTP_Request2, pecl_http
postman-cli	Postman CLI
powershell	RestMethod
python	http.client, Requests
r	httr, RCurl
ruby	Net::HTTP
rust	reqwest
shell	Httpie, wget
swift	URLSession

Testing Center tools

Spark service download testbed template

• Name: spark_download_testbed_template

• Description: For Testing Center. Testbeds contain data to run on Spark service. Download Excel testbed template for Spark service to add testbed.

Property	Description
folder *	Spark service folder name.
service *	Spark service name.

Spark download testbed result

• Name: spark_download_testbed_result

• Description: For Testing Center. Testbed results contain calculated results after testbed run on Spark service. Download completed testbed result.

Property	Description
folder *	Spark service folder name.
service *	Spark service name.
testbed *	Testbed name.
testbed_result *	Testbed result name.

Spark list testbeds

Name: spark_list_testbeds

Description: For Testing Center. Testbeds contain data to run on Spark service. List testbeds for Spark service.

Property	Description
folder *	Spark service folder name.
service *	Spark service name.
testbed *	Testbed name.

Spark list testbed results

Name: spark_list_testbed_results

Description: For Testing Center. Testbed results contain calculated results after testbed run on Spark service. List testbed results for Spark service testbed.

Property	Description
folder *	Spark service folder name.
service *	Spark service name.
testbed *	Testbed name.
testbed_result_name *	Testing Center testbed result name.

Spark run testbed

Name: spark_run_testbed

Description: For Testing Center. Testbeds contain data to run on Spark service. Start testbed run on Spark service.

Property	Description
folder *	Spark service folder name.
service *	Spark service name.
revision	Spark service version number.
version_id	version_id of Spark service version. Identifies specific service version.
service_category	Comma separated string of subservices to invoke.
testbed *	Testbed name.
testbed_result	Testbed result name. Default "Spark_1.0.0_<yyyy_mm_dd_hh_mm>" UTC.
testbed_result_description	Testbed result description.
testbed_list_max_pages	Maximum pages to search for testbed name. Default 10.

Spark run status testbed

Name: spark_run_status_testbed

Description: For Testing Center. Check status of Spark testbed run started via spark_run_testbed. Default poll_interval_seconds 5 up to default 100 max_iterations until run reaches terminal status. If still in progress after max_iterations results make this tool call again or check in Spark application.

Property	Description
run_id *	run_id returned by spark_run_testbed.
wait_for_complete	Poll until terminal status or max_iterations. When false, perform a single status check. Default true.
poll_interval_seconds	Seconds between status polls. Ignored when wait_for_completion is false. Default 5.
max_iterations	Maximum poll iterations before returning the in-progress snapshot. Default 100.
folder	Spark service folder name to render summary table.
service	Spark service name to render summary table.
testbed *	Testbed name to render summary table and download hint.
revision	Spark service version number.
version_id	version_id of Spark service version. Identifies specific service version.
service_category	Comma separated string of subservices to invoke.
testbed_result	Testbed result name. Default "Spark_1.0.0_<yyyy_mm_dd_hh_mm>" UTC.
testbed_result_description	Testbed result description.
testbed_list_max_pages	Maximum pages to search for testbed name. Default 10.

Spark compare testbed results

Name: spark_compare_testbed_results

Description: For Testing Center. Testbed results contain calculated results after testbed run on Spark service. Compare testbed results for Spark service testbed.

Property	Description
folder *	Spark service folder name.
service *	Spark service name.
testbed *	Testbed name.
testbed_result_1 *	Testbed result name (base).
testbed_result_2 *	Testing result name (comparison).

Troubleshoot issues

Issue	Cause(s)	Solution(s)
Error: "Bad Request: Server not initialized"	The server requires initialization before handling requests.	This should be handled automatically by the MCP client. If you see this error: 1. Ensure you're using an MCP-compatible client. 2. Verify the client sends an initialize request first. 3. Check that the server URL is correct.
Error: "No authorization token available"	Missing or invalid authorization token.	1. Verify your token is included in the Authorization header 2. Ensure the format is Bearer YOUR_TOKEN (with Bearer prefix). 3. Check that your token has not expired. 4. Obtain a fresh token if needed.
Error: "Invalid or expired token"	The JWT token has expired or is invalid.	1. Obtain a new token. 2. Update your client configuration with the new token. 3. Restart your AI client.
Error: "Tenant is not available"	The token doesn't contain tenant information.	1. Verify your user account has proper tenant assignment. 2. Check with your administrator to ensure proper claims in the JWT 3. Ensure the token contains the required tenant claim.
Tools not appearing in AI client	Possible causes: 1. Server connection failed. 2. Token authentication failed. 3. Client not properly configured.	1. Check the client's console/logs for connection errors. 2. Verify the server URL is correct. 3. Ensure Authorization header is properly formatted. 4. Test the token with a direct API call.
CORS errors in browser-based clients	Browser security restrictions.	The server has CORS enabled. If you still see errors: 1. Ensure you're using HTTPS (not HTTP). 2. Check that your client properly sends the Origin header. 3. Verify the server allows your origin.

If you encounter issues not covered in this guide:

1. Confirm the server status to verify the server is operational.

2. Review logs and check your AI client's console/logs for detailed errors.

3. Contact Support.

Security best practices

1. Never commit tokens to version control.

   • Add config files to .gitignore .

   • Use environment variables or secure vaults.

2. Rotate tokens regularly.

   • Obtain fresh tokens periodically.

   • Use token refresh mechanisms when available.

3. Use HTTPS only.

   • Never send tokens over unencrypted connections.

   • Verify the server URL uses https:// .

4. Limit token scope.

   • Request only the scopes you need.

   • Follow principle of least privilege.

5. Monitor token usage.

   • Review your authentication logs.

   • Report suspicious activity immediately.