Skip to main content
Glama
mcp-creatio

mcp-creatio

by CRACKISH

Run a business process

execute-process
Destructive

Start a Creatio business process by its schema name, pass optional parameter values, and return the process result. Use it to trigger automated workflows that may change data.

Instructions

Start a Creatio business process by its schema name, with optional parameters, and return its result. A process can change any data it is designed to — make sure the user wants it run. User/contact parameters take a contact id (get-guide: contactid-guide).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "processName": "<processName>"
    },
    "name": "execute-process"
  }
}

Input Schema

NameRequiredDescriptionDefault
parametersNoProcess parameters by their codes, e.g. { "ContactId": "<guid>", "Amount": 1000, "SendNotification": true }. Values are passed to the process as written.
processNameYesSchema name of the process (e.g. "UsrLeadQualification"), not its caption. To find it from a caption, read VwProcessLib: select ["Name", "Caption"], filters { all: [{ field: "Caption", op: "contains", value: "<caption>" }] }, and use `Name`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.8.0
    • changedInput schema / properties / parameters / description
      Previous value: -"Parameters to pass to the business process as key-value pairs. Parameter names typically start with uppercase letter. Examples:\n- ContactId: \"2ad0270b-dc4c-4fbf-9219-df32ce4c34fc\" (GUID values)\n- Amount: 1000 (numeric values)\n- Text: \"SomeText\" (string values)\n- BoolParam: true (boolean values)\nCommon parameter patterns: ContactId, AccountId, OpportunityId, Amount, Description, etc."New value: +"Process parameters by their codes, e.g. { \"ContactId\": \"<guid>\", \"Amount\": 1000, \"SendNotification\": true }. Values are passed to the process as written."
    • changedInput schema / properties / processName / description
      Previous value: -"REQUIRED: Schema name of the Creatio business process (e.g., \"RunActualizeProcess\").\nIMPORTANT: This parameter accepts ONLY schema names, NOT display names/captions.\nIf user provides a display name/caption (e.g., \"Actualize Process\"), you MUST first use the \"read\" tool to find the corresponding schema name in VwProcessLib table:\n- Use filter: contains(Caption,'user_provided_name')\n- Select fields: [\"Name\", \"Caption\"]\n- Use the \"Name\" field value as processName parameter."New value: +"Schema name of the process (e.g. \"UsrLeadQualification\"), not its caption. To find it from a caption, read VwProcessLib: select [\"Name\", \"Caption\"], filters { all: [{ field: \"Caption\", op: \"contains\", value: \"<caption>\" }] }, and use `Name`."
  2. First observedv0.6.5

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructive=true, non-idempotent, non-read-only, so the safety bar is lower. The description still adds real value by explaining that effects are unbounded ('can change any data it is designed to') and requiring user confirmation before invoking — context an annotation flag alone cannot convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences: what it does, the risk/confirmation warning, and the parameter-type caveat — front-loaded with zero padding. Each sentence carries distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, non-idempotent execution tool with a nested parameters object and no output schema, the description covers the essential unknown — unbounded side effects and confirmation. It only lightly describes what 'its result' looks like and says nothing about failure modes, which is a minor residual gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description goes beyond the schema by stating that user/contact parameters must carry a contact id and pointing to get-guide: contactid-guide. It says parameters are optional, matching the schema, though it does not restate the code-keyed shape the schema already documents.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Start a Creatio business process by its schema name'), notes optional parameters, and says it returns the result. No sibling in the list executes processes, and the schema-name-vs-caption distinction makes the target unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly warns that a process can change any data it is designed to and instructs the agent to confirm the user actually wants it run — a clear when/when-cautious signal. It does not name an alternative tool, but there is no comparable sibling to route to, so the guidance is nearly complete.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.