Skip to main content
Glama
Cloudflare Workers MCP Server

Cloudflare Workers MCP Server

Create Deployment

create_deployment
Destructive

Direct live Worker traffic to one version at 100% or split it across two versions for gradual rollouts; percentages must sum to 100.

Instructions

Point live traffic at Worker versions: a single version at 100%, or a gradual rollout splitting traffic across two versions (e.g. 90/10). Percentages must sum to 100.

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": {
      "script_name": "<script_name>",
      "versions": "<versions>"
    },
    "name": "create_deployment"
  }
}

Input Schema

NameRequiredDescriptionDefault
forceNoDeploy even if normally blocked (e.g. a secret changed since the target version)
messageNoDeployment message (workers/message annotation)
versionsYesOne version at 100%, or two versions splitting traffic (e.g. 90/10 for a gradual rollout). Percentages must sum to 100.
script_nameYesThe name of the Worker script

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.4.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. First observedv1.0.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true, and idempotentHint=false, so the risk profile is covered structurally. The description adds the shape constraint on traffic splitting but says nothing about what happens to the prior deployment, whether the change is reversible, or what the force flag means in practice — details an agent would want before a destructive operation.

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?

Two tight sentences with the primary action front-loaded, followed by the configuration shapes and the summation constraint. Nothing redundant and nothing padded.

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 mutation with no output schema, the description conveys the operation's shape and constraints adequately, and annotations carry the safety signal. The main missing piece is the effect on the existing live deployment and the relationship to rollback_worker, which would matter for recovery.

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

Parameters3/5

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

With 100% schema description coverage, the baseline is 3: the schema already documents force ('deploy even if normally blocked'), message, script_name, and the version/percentage pair. The description restates the versions shape and the sum-to-100 rule, which duplicates rather than extends the schema, and never touches force or message.

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

Purpose4/5

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

The description states a specific verb and resource ('point live traffic at Worker versions') and enumerates the two supported shapes: single version at 100% or a two-way split. It does not, however, distinguish itself from the sibling deploy_worker, which likely performs a very similar action, leaving the boundary between the two implicit.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: the mention of a 'gradual rollout' signals when this tool is appropriate, but no alternatives are named and no exclusions given. An agent cannot tell from this text whether to prefer this over deploy_worker, deploy_preview, or rollback_worker.

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